Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,63 @@
+---
+library_name: peft
+license: other
+base_model: meta-llama/Llama-3.1-70B
+tags:
+- base_model:adapter:/workspace/meta-llama/Llama-3.1-70B
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: IEEE-DLD-llama3_70b_LoRA
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# IEEE-DLD-llama3_70b_LoRA
+
+This model is a fine-tuned version of [/workspace/meta-llama/Llama-3.1-70B](https://huggingface.co//workspace/meta-llama/Llama-3.1-70B) on the Abbey_College_London_DLD_all_rephrased dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 24
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 384
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.56.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.1

README.md

@@ -0,0 +1,63 @@
+---
+library_name: peft
+license: other
+base_model: meta-llama/Llama-3.1-70B
+tags:
+- base_model:adapter:/workspace/meta-llama/Llama-3.1-70B
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: IEEE-DLD-llama3_70b_LoRA
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# IEEE-DLD-llama3_70b_LoRA
+
+This model is a fine-tuned version of [/workspace/meta-llama/Llama-3.1-70B](https://huggingface.co//workspace/meta-llama/Llama-3.1-70B) on the Abbey_College_London_DLD_all_rephrased dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 24
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 384
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.56.2
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/meta-llama/Llama-3.1-70B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706c0dc63a0f2c4291b7037a8a2d8bbc3032605bb3567a4bcae96db169a8eb59
+size 414339864

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "num_input_tokens_seen": 100663200,
+    "total_flos": 2377568804143104.0,
+    "train_loss": 0.697018449810835,
+    "train_runtime": 22008.2973,
+    "train_samples_per_second": 4.45,
+    "train_steps_per_second": 0.012
+}

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|end_of_text|>' + '
+' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|end_of_text|>' + '
+Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '
+' }}{% endif %}{% endfor %}

checkpoint-260/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /workspace/meta-llama/Llama-3.1-70B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/workspace/meta-llama/Llama-3.1-70B
+- llama-factory
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-260/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/meta-llama/Llama-3.1-70B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-260/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706c0dc63a0f2c4291b7037a8a2d8bbc3032605bb3567a4bcae96db169a8eb59
+size 414339864

checkpoint-260/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|end_of_text|>' + '
+' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|end_of_text|>' + '
+Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '
+' }}{% endif %}{% endfor %}

checkpoint-260/global_step260/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bb682347561733dc3841fa2c66162ae4f69b68b34dd268c7229e9191823e0a4
+size 621285637

checkpoint-260/global_step260/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c12a74a36a9fb896503bf821368ca48fd52952d795c520cee8ac63e27225d8b
+size 621285637

checkpoint-260/global_step260/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de0986cbd0a9c67912418c7aef2ee5cd269c4c430d35cca7b89d0e0d12d5de59
+size 621285637

checkpoint-260/global_step260/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250eac8ac5051a491bf2cb03c7afa9528a37bab1fd14c40bb8ac571eef419172
+size 621285637

checkpoint-260/global_step260/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a64cc086f9a9b0cd01de6c8749cf37d5fa41a3579fbf814045a8c34cf3d6357f
+size 1108113

checkpoint-260/global_step260/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4a2f7968faa29e3b61bfea42be0add9a355ff69f3198fd1fb58accc11e3e3f
+size 1108113

checkpoint-260/global_step260/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193f06aff0322b6a0bc789087a2e21bb8fcc23b75496d889030e8b1a60d077d2
+size 1108113

checkpoint-260/global_step260/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18995e5a49db029b70eada9778dace024591b0961ea080a9154f5e0148e5693a
+size 1108113

checkpoint-260/latest

@@ -0,0 +1 @@
+global_step260

checkpoint-260/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e194728aaa10c0651a28dd077b8d2c23c9f33fe417ad98434b9d53b89331c8ad
+size 15429

checkpoint-260/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf96eb5be532d73f38945749361f3edd34b97cc076d4be7e2cde686e5359b8d7
+size 15429

checkpoint-260/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3730e5abab5d2c549528777cb61f23b5504fcdf03bc11ecbc1c43cde06a8681
+size 15429

checkpoint-260/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d3c11250a36c56988f28d2935067da0ae1298b63289c54f8eae528ff166c9fa
+size 15429

checkpoint-260/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9655e129d871161f2af0cb4bce0cc09811c5802ee17c1cdee81964107370c5c
+size 1465

checkpoint-260/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

checkpoint-260/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-260/tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-260/trainer_state.json

@@ -0,0 +1,2634 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01951219512195122,
+      "grad_norm": 0.15858030701789594,
+      "learning_rate": 0.0001,
+      "loss": 1.9481,
+      "num_input_tokens_seen": 392832,
+      "step": 1,
+      "train_runtime": 90.5356,
+      "train_tokens_per_second": 4338.977
+    },
+    {
+      "epoch": 0.03902439024390244,
+      "grad_norm": 0.20614269950817926,
+      "learning_rate": 9.999635004278054e-05,
+      "loss": 1.9426,
+      "num_input_tokens_seen": 785664,
+      "step": 2,
+      "train_runtime": 176.3121,
+      "train_tokens_per_second": 4456.097
+    },
+    {
+      "epoch": 0.05853658536585366,
+      "grad_norm": 0.11931287845406353,
+      "learning_rate": 9.998540070400966e-05,
+      "loss": 1.8808,
+      "num_input_tokens_seen": 1178496,
+      "step": 3,
+      "train_runtime": 261.8343,
+      "train_tokens_per_second": 4500.924
+    },
+    {
+      "epoch": 0.07804878048780488,
+      "grad_norm": 0.1061877717922271,
+      "learning_rate": 9.996715358227206e-05,
+      "loss": 1.8827,
+      "num_input_tokens_seen": 1571328,
+      "step": 4,
+      "train_runtime": 347.2723,
+      "train_tokens_per_second": 4524.772
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.2303512070226615,
+      "learning_rate": 9.994161134161634e-05,
+      "loss": 1.8196,
+      "num_input_tokens_seen": 1964160,
+      "step": 5,
+      "train_runtime": 432.7972,
+      "train_tokens_per_second": 4538.292
+    },
+    {
+      "epoch": 0.11707317073170732,
+      "grad_norm": 0.10282606368495031,
+      "learning_rate": 9.990877771116589e-05,
+      "loss": 1.7928,
+      "num_input_tokens_seen": 2356992,
+      "step": 6,
+      "train_runtime": 518.285,
+      "train_tokens_per_second": 4547.676
+    },
+    {
+      "epoch": 0.13658536585365855,
+      "grad_norm": 0.09334879403165187,
+      "learning_rate": 9.986865748457457e-05,
+      "loss": 1.7726,
+      "num_input_tokens_seen": 2749824,
+      "step": 7,
+      "train_runtime": 603.8579,
+      "train_tokens_per_second": 4553.76
+    },
+    {
+      "epoch": 0.15609756097560976,
+      "grad_norm": 0.08922352642855319,
+      "learning_rate": 9.982125651932681e-05,
+      "loss": 1.7569,
+      "num_input_tokens_seen": 3142656,
+      "step": 8,
+      "train_runtime": 689.4943,
+      "train_tokens_per_second": 4557.915
+    },
+    {
+      "epoch": 0.17560975609756097,
+      "grad_norm": 0.08017329983520603,
+      "learning_rate": 9.976658173588244e-05,
+      "loss": 1.7263,
+      "num_input_tokens_seen": 3535488,
+      "step": 9,
+      "train_runtime": 775.2129,
+      "train_tokens_per_second": 4560.667
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.09081767257053708,
+      "learning_rate": 9.970464111666626e-05,
+      "loss": 1.7278,
+      "num_input_tokens_seen": 3928320,
+      "step": 10,
+      "train_runtime": 860.7493,
+      "train_tokens_per_second": 4563.837
+    },
+    {
+      "epoch": 0.2146341463414634,
+      "grad_norm": 0.09473566656122094,
+      "learning_rate": 9.96354437049027e-05,
+      "loss": 1.719,
+      "num_input_tokens_seen": 4321152,
+      "step": 11,
+      "train_runtime": 946.3458,
+      "train_tokens_per_second": 4566.145
+    },
+    {
+      "epoch": 0.23414634146341465,
+      "grad_norm": 0.09855985009583386,
+      "learning_rate": 9.955899960329547e-05,
+      "loss": 1.6873,
+      "num_input_tokens_seen": 4713984,
+      "step": 12,
+      "train_runtime": 1031.9306,
+      "train_tokens_per_second": 4568.121
+    },
+    {
+      "epoch": 0.25365853658536586,
+      "grad_norm": 0.08976785941545291,
+      "learning_rate": 9.947531997255256e-05,
+      "loss": 1.6583,
+      "num_input_tokens_seen": 5106816,
+      "step": 13,
+      "train_runtime": 1117.6812,
+      "train_tokens_per_second": 4569.117
+    },
+    {
+      "epoch": 0.2731707317073171,
+      "grad_norm": 0.13069965458083008,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 1.6484,
+      "num_input_tokens_seen": 5499648,
+      "step": 14,
+      "train_runtime": 1203.3824,
+      "train_tokens_per_second": 4570.158
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.09614160184332628,
+      "learning_rate": 9.928630404658255e-05,
+      "loss": 1.6392,
+      "num_input_tokens_seen": 5892480,
+      "step": 15,
+      "train_runtime": 1288.9765,
+      "train_tokens_per_second": 4571.441
+    },
+    {
+      "epoch": 0.3121951219512195,
+      "grad_norm": 0.11451137531983133,
+      "learning_rate": 9.918099534735718e-05,
+      "loss": 1.6079,
+      "num_input_tokens_seen": 6285312,
+      "step": 16,
+      "train_runtime": 1374.5203,
+      "train_tokens_per_second": 4572.731
+    },
+    {
+      "epoch": 0.33170731707317075,
+      "grad_norm": 0.1000369686921647,
+      "learning_rate": 9.906850630697068e-05,
+      "loss": 1.614,
+      "num_input_tokens_seen": 6678144,
+      "step": 17,
+      "train_runtime": 1460.267,
+      "train_tokens_per_second": 4573.235
+    },
+    {
+      "epoch": 0.35121951219512193,
+      "grad_norm": 0.11186890632545277,
+      "learning_rate": 9.894885334863044e-05,
+      "loss": 1.5871,
+      "num_input_tokens_seen": 7070976,
+      "step": 18,
+      "train_runtime": 1545.8916,
+      "train_tokens_per_second": 4574.044
+    },
+    {
+      "epoch": 0.37073170731707317,
+      "grad_norm": 0.12930001237850156,
+      "learning_rate": 9.882205394146361e-05,
+      "loss": 1.5864,
+      "num_input_tokens_seen": 7463808,
+      "step": 19,
+      "train_runtime": 1631.4769,
+      "train_tokens_per_second": 4574.878
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.11111621443548497,
+      "learning_rate": 9.868812659796668e-05,
+      "loss": 1.547,
+      "num_input_tokens_seen": 7856640,
+      "step": 20,
+      "train_runtime": 1717.1186,
+      "train_tokens_per_second": 4575.479
+    },
+    {
+      "epoch": 0.4097560975609756,
+      "grad_norm": 0.10197780896100014,
+      "learning_rate": 9.85470908713026e-05,
+      "loss": 1.5349,
+      "num_input_tokens_seen": 8249472,
+      "step": 21,
+      "train_runtime": 1802.6996,
+      "train_tokens_per_second": 4576.177
+    },
+    {
+      "epoch": 0.4292682926829268,
+      "grad_norm": 0.11362815005489417,
+      "learning_rate": 9.839896735244614e-05,
+      "loss": 1.5123,
+      "num_input_tokens_seen": 8642304,
+      "step": 22,
+      "train_runtime": 1888.2112,
+      "train_tokens_per_second": 4576.98
+    },
+    {
+      "epoch": 0.44878048780487806,
+      "grad_norm": 0.5028658075504846,
+      "learning_rate": 9.824377766717759e-05,
+      "loss": 1.4901,
+      "num_input_tokens_seen": 9035136,
+      "step": 23,
+      "train_runtime": 1973.7336,
+      "train_tokens_per_second": 4577.688
+    },
+    {
+      "epoch": 0.4682926829268293,
+      "grad_norm": 0.12820339687555396,
+      "learning_rate": 9.808154447292539e-05,
+      "loss": 1.4924,
+      "num_input_tokens_seen": 9427968,
+      "step": 24,
+      "train_runtime": 2059.3532,
+      "train_tokens_per_second": 4578.121
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.13588084054069685,
+      "learning_rate": 9.791229145545831e-05,
+      "loss": 1.4489,
+      "num_input_tokens_seen": 9820800,
+      "step": 25,
+      "train_runtime": 2145.0524,
+      "train_tokens_per_second": 4578.35
+    },
+    {
+      "epoch": 0.5073170731707317,
+      "grad_norm": 0.13132153795044452,
+      "learning_rate": 9.773604332542729e-05,
+      "loss": 1.4188,
+      "num_input_tokens_seen": 10213632,
+      "step": 26,
+      "train_runtime": 2230.6879,
+      "train_tokens_per_second": 4578.692
+    },
+    {
+      "epoch": 0.526829268292683,
+      "grad_norm": 0.13496880260647526,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.4272,
+      "num_input_tokens_seen": 10606464,
+      "step": 27,
+      "train_runtime": 2316.1437,
+      "train_tokens_per_second": 4579.364
+    },
+    {
+      "epoch": 0.5463414634146342,
+      "grad_norm": 0.14799450429263764,
+      "learning_rate": 9.736266567289253e-05,
+      "loss": 1.3815,
+      "num_input_tokens_seen": 10999296,
+      "step": 28,
+      "train_runtime": 2401.7043,
+      "train_tokens_per_second": 4579.788
+    },
+    {
+      "epoch": 0.5658536585365853,
+      "grad_norm": 0.32782733922481533,
+      "learning_rate": 9.716559066288715e-05,
+      "loss": 1.3752,
+      "num_input_tokens_seen": 11392128,
+      "step": 29,
+      "train_runtime": 2487.3215,
+      "train_tokens_per_second": 4580.079
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.1534924395682076,
+      "learning_rate": 9.696162955735577e-05,
+      "loss": 1.3629,
+      "num_input_tokens_seen": 11784960,
+      "step": 30,
+      "train_runtime": 2572.9464,
+      "train_tokens_per_second": 4580.336
+    },
+    {
+      "epoch": 0.6048780487804878,
+      "grad_norm": 0.23747387980155885,
+      "learning_rate": 9.675081213427076e-05,
+      "loss": 1.3163,
+      "num_input_tokens_seen": 12177792,
+      "step": 31,
+      "train_runtime": 2658.4902,
+      "train_tokens_per_second": 4580.717
+    },
+    {
+      "epoch": 0.624390243902439,
+      "grad_norm": 0.1724017252468989,
+      "learning_rate": 9.653316917261512e-05,
+      "loss": 1.3058,
+      "num_input_tokens_seen": 12570624,
+      "step": 32,
+      "train_runtime": 2743.9643,
+      "train_tokens_per_second": 4581.191
+    },
+    {
+      "epoch": 0.6439024390243903,
+      "grad_norm": 0.1619965153711787,
+      "learning_rate": 9.630873244788883e-05,
+      "loss": 1.2774,
+      "num_input_tokens_seen": 12963456,
+      "step": 33,
+      "train_runtime": 2829.4055,
+      "train_tokens_per_second": 4581.689
+    },
+    {
+      "epoch": 0.6634146341463415,
+      "grad_norm": 0.18133620259351485,
+      "learning_rate": 9.607753472746966e-05,
+      "loss": 1.2585,
+      "num_input_tokens_seen": 13356288,
+      "step": 34,
+      "train_runtime": 2914.8292,
+      "train_tokens_per_second": 4582.185
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 0.20121493987838818,
+      "learning_rate": 9.583960976582913e-05,
+      "loss": 1.2429,
+      "num_input_tokens_seen": 13749120,
+      "step": 35,
+      "train_runtime": 3000.3011,
+      "train_tokens_per_second": 4582.58
+    },
+    {
+      "epoch": 0.7024390243902439,
+      "grad_norm": 0.2485985257238104,
+      "learning_rate": 9.559499229960451e-05,
+      "loss": 1.2092,
+      "num_input_tokens_seen": 14141952,
+      "step": 36,
+      "train_runtime": 3085.8763,
+      "train_tokens_per_second": 4582.799
+    },
+    {
+      "epoch": 0.7219512195121951,
+      "grad_norm": 0.24323454189307991,
+      "learning_rate": 9.534371804252728e-05,
+      "loss": 1.1789,
+      "num_input_tokens_seen": 14534784,
+      "step": 37,
+      "train_runtime": 3171.7531,
+      "train_tokens_per_second": 4582.571
+    },
+    {
+      "epoch": 0.7414634146341463,
+      "grad_norm": 0.34801979161039454,
+      "learning_rate": 9.508582368020897e-05,
+      "loss": 1.1495,
+      "num_input_tokens_seen": 14927616,
+      "step": 38,
+      "train_runtime": 3257.3777,
+      "train_tokens_per_second": 4582.71
+    },
+    {
+      "epoch": 0.7609756097560976,
+      "grad_norm": 0.6127611336291061,
+      "learning_rate": 9.482134686478519e-05,
+      "loss": 1.141,
+      "num_input_tokens_seen": 15320448,
+      "step": 39,
+      "train_runtime": 3342.782,
+      "train_tokens_per_second": 4583.143
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.6420115225722821,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 1.1236,
+      "num_input_tokens_seen": 15713280,
+      "step": 40,
+      "train_runtime": 3428.2665,
+      "train_tokens_per_second": 4583.448
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.28502804596451176,
+      "learning_rate": 9.42728012826605e-05,
+      "loss": 1.1034,
+      "num_input_tokens_seen": 16106112,
+      "step": 41,
+      "train_runtime": 3513.7978,
+      "train_tokens_per_second": 4583.676
+    },
+    {
+      "epoch": 0.8195121951219512,
+      "grad_norm": 0.716313084661846,
+      "learning_rate": 9.398881260267589e-05,
+      "loss": 1.1052,
+      "num_input_tokens_seen": 16498944,
+      "step": 42,
+      "train_runtime": 3599.2462,
+      "train_tokens_per_second": 4584.0
+    },
+    {
+      "epoch": 0.8390243902439024,
+      "grad_norm": 0.3220303313208368,
+      "learning_rate": 9.36984016313259e-05,
+      "loss": 1.0595,
+      "num_input_tokens_seen": 16891776,
+      "step": 43,
+      "train_runtime": 3684.6336,
+      "train_tokens_per_second": 4584.384
+    },
+    {
+      "epoch": 0.8585365853658536,
+      "grad_norm": 0.46297801425335283,
+      "learning_rate": 9.340161076811537e-05,
+      "loss": 1.0507,
+      "num_input_tokens_seen": 17284608,
+      "step": 44,
+      "train_runtime": 3770.0588,
+      "train_tokens_per_second": 4584.705
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.3229025177696428,
+      "learning_rate": 9.309848334400246e-05,
+      "loss": 1.0204,
+      "num_input_tokens_seen": 17677440,
+      "step": 45,
+      "train_runtime": 3855.5127,
+      "train_tokens_per_second": 4584.978
+    },
+    {
+      "epoch": 0.8975609756097561,
+      "grad_norm": 0.4974629296010873,
+      "learning_rate": 9.278906361507238e-05,
+      "loss": 1.0275,
+      "num_input_tokens_seen": 18070272,
+      "step": 46,
+      "train_runtime": 3940.8899,
+      "train_tokens_per_second": 4585.328
+    },
+    {
+      "epoch": 0.9170731707317074,
+      "grad_norm": 0.3252828591259486,
+      "learning_rate": 9.247339675607605e-05,
+      "loss": 0.9942,
+      "num_input_tokens_seen": 18463104,
+      "step": 47,
+      "train_runtime": 4026.4826,
+      "train_tokens_per_second": 4585.418
+    },
+    {
+      "epoch": 0.9365853658536586,
+      "grad_norm": 0.4096451495593207,
+      "learning_rate": 9.215152885383474e-05,
+      "loss": 0.9636,
+      "num_input_tokens_seen": 18855936,
+      "step": 48,
+      "train_runtime": 4111.9693,
+      "train_tokens_per_second": 4585.622
+    },
+    {
+      "epoch": 0.9560975609756097,
+      "grad_norm": 0.34175853473817397,
+      "learning_rate": 9.182350690051133e-05,
+      "loss": 0.9595,
+      "num_input_tokens_seen": 19248768,
+      "step": 49,
+      "train_runtime": 4197.3817,
+      "train_tokens_per_second": 4585.899
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.7544878577908084,
+      "learning_rate": 9.148937878674976e-05,
+      "loss": 0.9406,
+      "num_input_tokens_seen": 19641600,
+      "step": 50,
+      "train_runtime": 4282.7892,
+      "train_tokens_per_second": 4586.17
+    },
+    {
+      "epoch": 0.9951219512195122,
+      "grad_norm": 0.45005702668900516,
+      "learning_rate": 9.114919329468282e-05,
+      "loss": 0.9266,
+      "num_input_tokens_seen": 20034432,
+      "step": 51,
+      "train_runtime": 4368.202,
+      "train_tokens_per_second": 4586.425
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5681712533129535,
+      "learning_rate": 9.080300009081024e-05,
+      "loss": 0.9145,
+      "num_input_tokens_seen": 20132640,
+      "step": 52,
+      "train_runtime": 4389.6005,
+      "train_tokens_per_second": 4586.44
+    },
+    {
+      "epoch": 1.0195121951219512,
+      "grad_norm": 0.5035806305267847,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.8835,
+      "num_input_tokens_seen": 20525472,
+      "step": 53,
+      "train_runtime": 4475.0972,
+      "train_tokens_per_second": 4586.598
+    },
+    {
+      "epoch": 1.0390243902439025,
+      "grad_norm": 1.5437125934865135,
+      "learning_rate": 9.009279359184593e-05,
+      "loss": 0.8894,
+      "num_input_tokens_seen": 20918304,
+      "step": 54,
+      "train_runtime": 4560.5362,
+      "train_tokens_per_second": 4586.808
+    },
+    {
+      "epoch": 1.0585365853658537,
+      "grad_norm": 2.5544072695829527,
+      "learning_rate": 8.972888398568772e-05,
+      "loss": 0.8801,
+      "num_input_tokens_seen": 21311136,
+      "step": 55,
+      "train_runtime": 4646.0135,
+      "train_tokens_per_second": 4586.972
+    },
+    {
+      "epoch": 1.078048780487805,
+      "grad_norm": 6.413568180777226,
+      "learning_rate": 8.935917403045251e-05,
+      "loss": 0.8761,
+      "num_input_tokens_seen": 21703968,
+      "step": 56,
+      "train_runtime": 4731.4435,
+      "train_tokens_per_second": 4587.177
+    },
+    {
+      "epoch": 1.0975609756097562,
+      "grad_norm": 3.6652053687664377,
+      "learning_rate": 8.898371770316111e-05,
+      "loss": 0.8785,
+      "num_input_tokens_seen": 22096800,
+      "step": 57,
+      "train_runtime": 4816.8429,
+      "train_tokens_per_second": 4587.403
+    },
+    {
+      "epoch": 1.1170731707317074,
+      "grad_norm": 2.350713418610044,
+      "learning_rate": 8.860256981979484e-05,
+      "loss": 0.8964,
+      "num_input_tokens_seen": 22489632,
+      "step": 58,
+      "train_runtime": 4902.2866,
+      "train_tokens_per_second": 4587.58
+    },
+    {
+      "epoch": 1.1365853658536587,
+      "grad_norm": 1.458077107848317,
+      "learning_rate": 8.821578602729242e-05,
+      "loss": 0.8833,
+      "num_input_tokens_seen": 22882464,
+      "step": 59,
+      "train_runtime": 4987.6858,
+      "train_tokens_per_second": 4587.792
+    },
+    {
+      "epoch": 1.1560975609756097,
+      "grad_norm": 2.3627094246816553,
+      "learning_rate": 8.782342279542568e-05,
+      "loss": 0.8698,
+      "num_input_tokens_seen": 23275296,
+      "step": 60,
+      "train_runtime": 5073.0959,
+      "train_tokens_per_second": 4587.987
+    },
+    {
+      "epoch": 1.175609756097561,
+      "grad_norm": 1.3869190096740975,
+      "learning_rate": 8.742553740855506e-05,
+      "loss": 0.864,
+      "num_input_tokens_seen": 23668128,
+      "step": 61,
+      "train_runtime": 5158.4893,
+      "train_tokens_per_second": 4588.19
+    },
+    {
+      "epoch": 1.1951219512195121,
+      "grad_norm": 1.1437940013985328,
+      "learning_rate": 8.702218795726617e-05,
+      "loss": 0.8551,
+      "num_input_tokens_seen": 24060960,
+      "step": 62,
+      "train_runtime": 5243.865,
+      "train_tokens_per_second": 4588.402
+    },
+    {
+      "epoch": 1.2146341463414634,
+      "grad_norm": 2.801137587074987,
+      "learning_rate": 8.661343332988869e-05,
+      "loss": 0.8327,
+      "num_input_tokens_seen": 24453792,
+      "step": 63,
+      "train_runtime": 5329.3228,
+      "train_tokens_per_second": 4588.536
+    },
+    {
+      "epoch": 1.2341463414634146,
+      "grad_norm": 1.1087446235917915,
+      "learning_rate": 8.619933320389872e-05,
+      "loss": 0.8003,
+      "num_input_tokens_seen": 24846624,
+      "step": 64,
+      "train_runtime": 5414.7776,
+      "train_tokens_per_second": 4588.669
+    },
+    {
+      "epoch": 1.2536585365853659,
+      "grad_norm": 1.1639583727147402,
+      "learning_rate": 8.577994803720606e-05,
+      "loss": 0.8078,
+      "num_input_tokens_seen": 25239456,
+      "step": 65,
+      "train_runtime": 5500.2413,
+      "train_tokens_per_second": 4588.791
+    },
+    {
+      "epoch": 1.273170731707317,
+      "grad_norm": 0.8450850350334035,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8033,
+      "num_input_tokens_seen": 25632288,
+      "step": 66,
+      "train_runtime": 5585.6797,
+      "train_tokens_per_second": 4588.929
+    },
+    {
+      "epoch": 1.2926829268292683,
+      "grad_norm": 4.138498725123297,
+      "learning_rate": 8.492556826244687e-05,
+      "loss": 0.7751,
+      "num_input_tokens_seen": 26025120,
+      "step": 67,
+      "train_runtime": 5671.0727,
+      "train_tokens_per_second": 4589.1
+    },
+    {
+      "epoch": 1.3121951219512196,
+      "grad_norm": 1.2519271390201068,
+      "learning_rate": 8.449069839236538e-05,
+      "loss": 0.7998,
+      "num_input_tokens_seen": 26417952,
+      "step": 68,
+      "train_runtime": 5756.4201,
+      "train_tokens_per_second": 4589.302
+    },
+    {
+      "epoch": 1.3317073170731708,
+      "grad_norm": 2.0612640489651586,
+      "learning_rate": 8.405079293933986e-05,
+      "loss": 0.7949,
+      "num_input_tokens_seen": 26810784,
+      "step": 69,
+      "train_runtime": 5841.8015,
+      "train_tokens_per_second": 4589.472
+    },
+    {
+      "epoch": 1.3512195121951218,
+      "grad_norm": 1.6632187783624717,
+      "learning_rate": 8.360591612881364e-05,
+      "loss": 0.7718,
+      "num_input_tokens_seen": 27203616,
+      "step": 70,
+      "train_runtime": 5927.224,
+      "train_tokens_per_second": 4589.605
+    },
+    {
+      "epoch": 1.370731707317073,
+      "grad_norm": 0.8557124244577246,
+      "learning_rate": 8.315613291203976e-05,
+      "loss": 0.7827,
+      "num_input_tokens_seen": 27596448,
+      "step": 71,
+      "train_runtime": 6012.6847,
+      "train_tokens_per_second": 4589.705
+    },
+    {
+      "epoch": 1.3902439024390243,
+      "grad_norm": 1.0542485300201978,
+      "learning_rate": 8.270150895659823e-05,
+      "loss": 0.7595,
+      "num_input_tokens_seen": 27989280,
+      "step": 72,
+      "train_runtime": 6098.1854,
+      "train_tokens_per_second": 4589.772
+    },
+    {
+      "epoch": 1.4097560975609755,
+      "grad_norm": 1.7657947939512917,
+      "learning_rate": 8.224211063680853e-05,
+      "loss": 0.7416,
+      "num_input_tokens_seen": 28382112,
+      "step": 73,
+      "train_runtime": 6183.6199,
+      "train_tokens_per_second": 4589.886
+    },
+    {
+      "epoch": 1.4292682926829268,
+      "grad_norm": 1.8137027126017153,
+      "learning_rate": 8.177800502403928e-05,
+      "loss": 0.749,
+      "num_input_tokens_seen": 28774944,
+      "step": 74,
+      "train_runtime": 6269.1266,
+      "train_tokens_per_second": 4589.945
+    },
+    {
+      "epoch": 1.448780487804878,
+      "grad_norm": 1.3646726182984732,
+      "learning_rate": 8.130925987691569e-05,
+      "loss": 0.72,
+      "num_input_tokens_seen": 29167776,
+      "step": 75,
+      "train_runtime": 6354.5877,
+      "train_tokens_per_second": 4590.034
+    },
+    {
+      "epoch": 1.4682926829268292,
+      "grad_norm": 2.817948027228682,
+      "learning_rate": 8.083594363142717e-05,
+      "loss": 0.7192,
+      "num_input_tokens_seen": 29560608,
+      "step": 76,
+      "train_runtime": 6440.0829,
+      "train_tokens_per_second": 4590.097
+    },
+    {
+      "epoch": 1.4878048780487805,
+      "grad_norm": 2.8685745350018976,
+      "learning_rate": 8.035812539093557e-05,
+      "loss": 0.7221,
+      "num_input_tokens_seen": 29953440,
+      "step": 77,
+      "train_runtime": 6525.6763,
+      "train_tokens_per_second": 4590.09
+    },
+    {
+      "epoch": 1.5073170731707317,
+      "grad_norm": 0.806171095791916,
+      "learning_rate": 7.987587491608637e-05,
+      "loss": 0.7031,
+      "num_input_tokens_seen": 30346272,
+      "step": 78,
+      "train_runtime": 6611.3229,
+      "train_tokens_per_second": 4590.045
+    },
+    {
+      "epoch": 1.526829268292683,
+      "grad_norm": 3.0602847716922237,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7118,
+      "num_input_tokens_seen": 30739104,
+      "step": 79,
+      "train_runtime": 6696.8792,
+      "train_tokens_per_second": 4590.064
+    },
+    {
+      "epoch": 1.5463414634146342,
+      "grad_norm": 1.0137101758685187,
+      "learning_rate": 7.889835953111075e-05,
+      "loss": 0.6952,
+      "num_input_tokens_seen": 31131936,
+      "step": 80,
+      "train_runtime": 6782.7752,
+      "train_tokens_per_second": 4589.852
+    },
+    {
+      "epoch": 1.5658536585365854,
+      "grad_norm": 1.4320523827445433,
+      "learning_rate": 7.840323733655778e-05,
+      "loss": 0.6693,
+      "num_input_tokens_seen": 31524768,
+      "step": 81,
+      "train_runtime": 6868.9208,
+      "train_tokens_per_second": 4589.479
+    },
+    {
+      "epoch": 1.5853658536585367,
+      "grad_norm": 3.2012899077086177,
+      "learning_rate": 7.790396831795792e-05,
+      "loss": 0.6718,
+      "num_input_tokens_seen": 31917600,
+      "step": 82,
+      "train_runtime": 6954.5194,
+      "train_tokens_per_second": 4589.476
+    },
+    {
+      "epoch": 1.604878048780488,
+      "grad_norm": 0.7553296877905612,
+      "learning_rate": 7.740062536773352e-05,
+      "loss": 0.67,
+      "num_input_tokens_seen": 32310432,
+      "step": 83,
+      "train_runtime": 7040.0533,
+      "train_tokens_per_second": 4589.515
+    },
+    {
+      "epoch": 1.6243902439024391,
+      "grad_norm": 1.069764102117734,
+      "learning_rate": 7.689328197309393e-05,
+      "loss": 0.6688,
+      "num_input_tokens_seen": 32703264,
+      "step": 84,
+      "train_runtime": 7125.6152,
+      "train_tokens_per_second": 4589.536
+    },
+    {
+      "epoch": 1.6439024390243904,
+      "grad_norm": 2.635419412507475,
+      "learning_rate": 7.638201220530665e-05,
+      "loss": 0.6672,
+      "num_input_tokens_seen": 33096096,
+      "step": 85,
+      "train_runtime": 7211.09,
+      "train_tokens_per_second": 4589.611
+    },
+    {
+      "epoch": 1.6634146341463416,
+      "grad_norm": 0.7024644501267906,
+      "learning_rate": 7.586689070888284e-05,
+      "loss": 0.6573,
+      "num_input_tokens_seen": 33488928,
+      "step": 86,
+      "train_runtime": 7296.5933,
+      "train_tokens_per_second": 4589.666
+    },
+    {
+      "epoch": 1.6829268292682928,
+      "grad_norm": 0.44428213007263,
+      "learning_rate": 7.534799269067953e-05,
+      "loss": 0.6422,
+      "num_input_tokens_seen": 33881760,
+      "step": 87,
+      "train_runtime": 7382.0301,
+      "train_tokens_per_second": 4589.762
+    },
+    {
+      "epoch": 1.7024390243902439,
+      "grad_norm": 0.5416450836446436,
+      "learning_rate": 7.48253939089194e-05,
+      "loss": 0.6269,
+      "num_input_tokens_seen": 34274592,
+      "step": 88,
+      "train_runtime": 7467.4502,
+      "train_tokens_per_second": 4589.865
+    },
+    {
+      "epoch": 1.721951219512195,
+      "grad_norm": 0.5642965602823063,
+      "learning_rate": 7.42991706621303e-05,
+      "loss": 0.6357,
+      "num_input_tokens_seen": 34667424,
+      "step": 89,
+      "train_runtime": 7553.0173,
+      "train_tokens_per_second": 4589.878
+    },
+    {
+      "epoch": 1.7414634146341463,
+      "grad_norm": 0.5097755585636675,
+      "learning_rate": 7.376939977800582e-05,
+      "loss": 0.6299,
+      "num_input_tokens_seen": 35060256,
+      "step": 90,
+      "train_runtime": 7638.6282,
+      "train_tokens_per_second": 4589.863
+    },
+    {
+      "epoch": 1.7609756097560976,
+      "grad_norm": 0.45556407265977034,
+      "learning_rate": 7.323615860218843e-05,
+      "loss": 0.634,
+      "num_input_tokens_seen": 35453088,
+      "step": 91,
+      "train_runtime": 7724.1622,
+      "train_tokens_per_second": 4589.894
+    },
+    {
+      "epoch": 1.7804878048780488,
+      "grad_norm": 0.4536282771598066,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.6251,
+      "num_input_tokens_seen": 35845920,
+      "step": 92,
+      "train_runtime": 7809.6142,
+      "train_tokens_per_second": 4589.973
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.43350812308828435,
+      "learning_rate": 7.215957727996207e-05,
+      "loss": 0.62,
+      "num_input_tokens_seen": 36238752,
+      "step": 93,
+      "train_runtime": 7895.006,
+      "train_tokens_per_second": 4590.085
+    },
+    {
+      "epoch": 1.819512195121951,
+      "grad_norm": 0.40833077692944497,
+      "learning_rate": 7.161639431258387e-05,
+      "loss": 0.6073,
+      "num_input_tokens_seen": 36631584,
+      "step": 94,
+      "train_runtime": 7980.4652,
+      "train_tokens_per_second": 4590.156
+    },
+    {
+      "epoch": 1.8390243902439023,
+      "grad_norm": 0.4235068021237779,
+      "learning_rate": 7.107005538862646e-05,
+      "loss": 0.6074,
+      "num_input_tokens_seen": 37024416,
+      "step": 95,
+      "train_runtime": 8065.9658,
+      "train_tokens_per_second": 4590.202
+    },
+    {
+      "epoch": 1.8585365853658535,
+      "grad_norm": 0.4132415083645228,
+      "learning_rate": 7.052064027263786e-05,
+      "loss": 0.6064,
+      "num_input_tokens_seen": 37417248,
+      "step": 96,
+      "train_runtime": 8151.397,
+      "train_tokens_per_second": 4590.287
+    },
+    {
+      "epoch": 1.8780487804878048,
+      "grad_norm": 0.4322861748139327,
+      "learning_rate": 6.996822917828477e-05,
+      "loss": 0.5922,
+      "num_input_tokens_seen": 37810080,
+      "step": 97,
+      "train_runtime": 8236.8862,
+      "train_tokens_per_second": 4590.337
+    },
+    {
+      "epoch": 1.897560975609756,
+      "grad_norm": 0.38942999050451615,
+      "learning_rate": 6.941290275664174e-05,
+      "loss": 0.5939,
+      "num_input_tokens_seen": 38202912,
+      "step": 98,
+      "train_runtime": 8322.3209,
+      "train_tokens_per_second": 4590.416
+    },
+    {
+      "epoch": 1.9170731707317072,
+      "grad_norm": 0.3753721554361611,
+      "learning_rate": 6.885474208441603e-05,
+      "loss": 0.5913,
+      "num_input_tokens_seen": 38595744,
+      "step": 99,
+      "train_runtime": 8407.7641,
+      "train_tokens_per_second": 4590.488
+    },
+    {
+      "epoch": 1.9365853658536585,
+      "grad_norm": 0.35005150318450906,
+      "learning_rate": 6.829382865211063e-05,
+      "loss": 0.5863,
+      "num_input_tokens_seen": 38988576,
+      "step": 100,
+      "train_runtime": 8493.2736,
+      "train_tokens_per_second": 4590.524
+    },
+    {
+      "epoch": 1.9560975609756097,
+      "grad_norm": 0.37808190956380233,
+      "learning_rate": 6.773024435212678e-05,
+      "loss": 0.5822,
+      "num_input_tokens_seen": 39381408,
+      "step": 101,
+      "train_runtime": 8578.7547,
+      "train_tokens_per_second": 4590.574
+    },
+    {
+      "epoch": 1.975609756097561,
+      "grad_norm": 0.3580568006066326,
+      "learning_rate": 6.716407146680792e-05,
+      "loss": 0.5666,
+      "num_input_tokens_seen": 39774240,
+      "step": 102,
+      "train_runtime": 8664.2328,
+      "train_tokens_per_second": 4590.625
+    },
+    {
+      "epoch": 1.9951219512195122,
+      "grad_norm": 0.39572577046735974,
+      "learning_rate": 6.659539265642643e-05,
+      "loss": 0.5806,
+      "num_input_tokens_seen": 40167072,
+      "step": 103,
+      "train_runtime": 8749.6718,
+      "train_tokens_per_second": 4590.695
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5994329532374332,
+      "learning_rate": 6.602429094711548e-05,
+      "loss": 0.5605,
+      "num_input_tokens_seen": 40265280,
+      "step": 104,
+      "train_runtime": 8771.0021,
+      "train_tokens_per_second": 4590.727
+    },
+    {
+      "epoch": 2.0195121951219512,
+      "grad_norm": 0.3746452769053094,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5462,
+      "num_input_tokens_seen": 40658112,
+      "step": 105,
+      "train_runtime": 8856.5287,
+      "train_tokens_per_second": 4590.75
+    },
+    {
+      "epoch": 2.0390243902439025,
+      "grad_norm": 0.453029236937953,
+      "learning_rate": 6.487515269276016e-05,
+      "loss": 0.5447,
+      "num_input_tokens_seen": 41050944,
+      "step": 106,
+      "train_runtime": 8942.0292,
+      "train_tokens_per_second": 4590.786
+    },
+    {
+      "epoch": 2.0585365853658537,
+      "grad_norm": 0.39272552581140363,
+      "learning_rate": 6.429728391993446e-05,
+      "loss": 0.5405,
+      "num_input_tokens_seen": 41443776,
+      "step": 107,
+      "train_runtime": 9027.5293,
+      "train_tokens_per_second": 4590.822
+    },
+    {
+      "epoch": 2.078048780487805,
+      "grad_norm": 0.35801484704748626,
+      "learning_rate": 6.37173277681223e-05,
+      "loss": 0.5433,
+      "num_input_tokens_seen": 41836608,
+      "step": 108,
+      "train_runtime": 9113.0265,
+      "train_tokens_per_second": 4590.858
+    },
+    {
+      "epoch": 2.097560975609756,
+      "grad_norm": 0.3703575056088343,
+      "learning_rate": 6.313536890992935e-05,
+      "loss": 0.5335,
+      "num_input_tokens_seen": 42229440,
+      "step": 109,
+      "train_runtime": 9198.6667,
+      "train_tokens_per_second": 4590.822
+    },
+    {
+      "epoch": 2.1170731707317074,
+      "grad_norm": 0.3456947105084525,
+      "learning_rate": 6.255149231035309e-05,
+      "loss": 0.5416,
+      "num_input_tokens_seen": 42622272,
+      "step": 110,
+      "train_runtime": 9284.269,
+      "train_tokens_per_second": 4590.805
+    },
+    {
+      "epoch": 2.1365853658536587,
+      "grad_norm": 0.33745389931809666,
+      "learning_rate": 6.19657832143779e-05,
+      "loss": 0.5322,
+      "num_input_tokens_seen": 43015104,
+      "step": 111,
+      "train_runtime": 9369.843,
+      "train_tokens_per_second": 4590.803
+    },
+    {
+      "epoch": 2.15609756097561,
+      "grad_norm": 0.33453831659901945,
+      "learning_rate": 6.13783271345295e-05,
+      "loss": 0.5301,
+      "num_input_tokens_seen": 43407936,
+      "step": 112,
+      "train_runtime": 9455.4833,
+      "train_tokens_per_second": 4590.769
+    },
+    {
+      "epoch": 2.175609756097561,
+      "grad_norm": 0.3355284079398747,
+      "learning_rate": 6.078920983839031e-05,
+      "loss": 0.5422,
+      "num_input_tokens_seen": 43800768,
+      "step": 113,
+      "train_runtime": 9541.0542,
+      "train_tokens_per_second": 4590.768
+    },
+    {
+      "epoch": 2.1951219512195124,
+      "grad_norm": 0.3257056473237624,
+      "learning_rate": 6.019851733607744e-05,
+      "loss": 0.5352,
+      "num_input_tokens_seen": 44193600,
+      "step": 114,
+      "train_runtime": 9626.532,
+      "train_tokens_per_second": 4590.812
+    },
+    {
+      "epoch": 2.2146341463414636,
+      "grad_norm": 0.32389003819610007,
+      "learning_rate": 5.960633586768543e-05,
+      "loss": 0.5112,
+      "num_input_tokens_seen": 44586432,
+      "step": 115,
+      "train_runtime": 9712.1322,
+      "train_tokens_per_second": 4590.797
+    },
+    {
+      "epoch": 2.234146341463415,
+      "grad_norm": 0.34317758929799447,
+      "learning_rate": 5.90127518906953e-05,
+      "loss": 0.5171,
+      "num_input_tokens_seen": 44979264,
+      "step": 116,
+      "train_runtime": 9797.6269,
+      "train_tokens_per_second": 4590.833
+    },
+    {
+      "epoch": 2.253658536585366,
+      "grad_norm": 0.31740577502228223,
+      "learning_rate": 5.841785206735192e-05,
+      "loss": 0.5027,
+      "num_input_tokens_seen": 45372096,
+      "step": 117,
+      "train_runtime": 9883.3105,
+      "train_tokens_per_second": 4590.779
+    },
+    {
+      "epoch": 2.2731707317073173,
+      "grad_norm": 0.3705124747857168,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.5151,
+      "num_input_tokens_seen": 45764928,
+      "step": 118,
+      "train_runtime": 9968.9083,
+      "train_tokens_per_second": 4590.766
+    },
+    {
+      "epoch": 2.292682926829268,
+      "grad_norm": 0.36613629503091577,
+      "learning_rate": 5.7224452478461064e-05,
+      "loss": 0.5152,
+      "num_input_tokens_seen": 46157760,
+      "step": 119,
+      "train_runtime": 10054.434,
+      "train_tokens_per_second": 4590.787
+    },
+    {
+      "epoch": 2.3121951219512193,
+      "grad_norm": 0.3314221690877754,
+      "learning_rate": 5.6626126947211386e-05,
+      "loss": 0.5303,
+      "num_input_tokens_seen": 46550592,
+      "step": 120,
+      "train_runtime": 10139.9414,
+      "train_tokens_per_second": 4590.815
+    },
+    {
+      "epoch": 2.3317073170731706,
+      "grad_norm": 0.3470857883762708,
+      "learning_rate": 5.602683401276615e-05,
+      "loss": 0.5032,
+      "num_input_tokens_seen": 46943424,
+      "step": 121,
+      "train_runtime": 10225.7135,
+      "train_tokens_per_second": 4590.724
+    },
+    {
+      "epoch": 2.351219512195122,
+      "grad_norm": 0.3136083377085674,
+      "learning_rate": 5.542666117086832e-05,
+      "loss": 0.5119,
+      "num_input_tokens_seen": 47336256,
+      "step": 122,
+      "train_runtime": 10311.2617,
+      "train_tokens_per_second": 4590.734
+    },
+    {
+      "epoch": 2.370731707317073,
+      "grad_norm": 0.4227118641608833,
+      "learning_rate": 5.482569604572576e-05,
+      "loss": 0.5045,
+      "num_input_tokens_seen": 47729088,
+      "step": 123,
+      "train_runtime": 10396.9552,
+      "train_tokens_per_second": 4590.679
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 0.32585539704348276,
+      "learning_rate": 5.422402637721836e-05,
+      "loss": 0.505,
+      "num_input_tokens_seen": 48121920,
+      "step": 124,
+      "train_runtime": 10482.7724,
+      "train_tokens_per_second": 4590.572
+    },
+    {
+      "epoch": 2.4097560975609755,
+      "grad_norm": 0.3224554976871665,
+      "learning_rate": 5.3621740008088126e-05,
+      "loss": 0.5017,
+      "num_input_tokens_seen": 48514752,
+      "step": 125,
+      "train_runtime": 10568.4335,
+      "train_tokens_per_second": 4590.534
+    },
+    {
+      "epoch": 2.4292682926829268,
+      "grad_norm": 0.33513514879191686,
+      "learning_rate": 5.3018924871114305e-05,
+      "loss": 0.5019,
+      "num_input_tokens_seen": 48907584,
+      "step": 126,
+      "train_runtime": 10653.9397,
+      "train_tokens_per_second": 4590.563
+    },
+    {
+      "epoch": 2.448780487804878,
+      "grad_norm": 0.3333825976504885,
+      "learning_rate": 5.2415668976275355e-05,
+      "loss": 0.4921,
+      "num_input_tokens_seen": 49300416,
+      "step": 127,
+      "train_runtime": 10739.489,
+      "train_tokens_per_second": 4590.574
+    },
+    {
+      "epoch": 2.4682926829268292,
+      "grad_norm": 0.32605283067247587,
+      "learning_rate": 5.181206039789962e-05,
+      "loss": 0.4951,
+      "num_input_tokens_seen": 49693248,
+      "step": 128,
+      "train_runtime": 10825.0018,
+      "train_tokens_per_second": 4590.6
+    },
+    {
+      "epoch": 2.4878048780487805,
+      "grad_norm": 0.345821204685631,
+      "learning_rate": 5.1208187261806615e-05,
+      "loss": 0.5076,
+      "num_input_tokens_seen": 50086080,
+      "step": 129,
+      "train_runtime": 10910.4514,
+      "train_tokens_per_second": 4590.652
+    },
+    {
+      "epoch": 2.5073170731707317,
+      "grad_norm": 0.32182997237639754,
+      "learning_rate": 5.060413773244087e-05,
+      "loss": 0.4974,
+      "num_input_tokens_seen": 50478912,
+      "step": 130,
+      "train_runtime": 10996.0971,
+      "train_tokens_per_second": 4590.621
+    },
+    {
+      "epoch": 2.526829268292683,
+      "grad_norm": 0.3424390071269269,
+      "learning_rate": 5e-05,
+      "loss": 0.5063,
+      "num_input_tokens_seen": 50871744,
+      "step": 131,
+      "train_runtime": 11081.5772,
+      "train_tokens_per_second": 4590.659
+    },
+    {
+      "epoch": 2.546341463414634,
+      "grad_norm": 0.32151933822675133,
+      "learning_rate": 4.9395862267559136e-05,
+      "loss": 0.5093,
+      "num_input_tokens_seen": 51264576,
+      "step": 132,
+      "train_runtime": 11167.132,
+      "train_tokens_per_second": 4590.666
+    },
+    {
+      "epoch": 2.5658536585365854,
+      "grad_norm": 0.33150875749489067,
+      "learning_rate": 4.87918127381934e-05,
+      "loss": 0.5019,
+      "num_input_tokens_seen": 51657408,
+      "step": 133,
+      "train_runtime": 11252.7312,
+      "train_tokens_per_second": 4590.655
+    },
+    {
+      "epoch": 2.5853658536585367,
+      "grad_norm": 0.32260765542480235,
+      "learning_rate": 4.81879396021004e-05,
+      "loss": 0.4836,
+      "num_input_tokens_seen": 52050240,
+      "step": 134,
+      "train_runtime": 11338.3707,
+      "train_tokens_per_second": 4590.628
+    },
+    {
+      "epoch": 2.604878048780488,
+      "grad_norm": 0.3284283947692906,
+      "learning_rate": 4.758433102372466e-05,
+      "loss": 0.4878,
+      "num_input_tokens_seen": 52443072,
+      "step": 135,
+      "train_runtime": 11424.0926,
+      "train_tokens_per_second": 4590.568
+    },
+    {
+      "epoch": 2.624390243902439,
+      "grad_norm": 0.3174202627091527,
+      "learning_rate": 4.6981075128885693e-05,
+      "loss": 0.4895,
+      "num_input_tokens_seen": 52835904,
+      "step": 136,
+      "train_runtime": 11509.8066,
+      "train_tokens_per_second": 4590.512
+    },
+    {
+      "epoch": 2.6439024390243904,
+      "grad_norm": 0.3424879966422641,
+      "learning_rate": 4.6378259991911886e-05,
+      "loss": 0.4987,
+      "num_input_tokens_seen": 53228736,
+      "step": 137,
+      "train_runtime": 11595.5338,
+      "train_tokens_per_second": 4590.452
+    },
+    {
+      "epoch": 2.6634146341463416,
+      "grad_norm": 0.31862495887920006,
+      "learning_rate": 4.5775973622781655e-05,
+      "loss": 0.4952,
+      "num_input_tokens_seen": 53621568,
+      "step": 138,
+      "train_runtime": 11681.2149,
+      "train_tokens_per_second": 4590.41
+    },
+    {
+      "epoch": 2.682926829268293,
+      "grad_norm": 0.32882715869402424,
+      "learning_rate": 4.5174303954274244e-05,
+      "loss": 0.4852,
+      "num_input_tokens_seen": 54014400,
+      "step": 139,
+      "train_runtime": 11766.8708,
+      "train_tokens_per_second": 4590.379
+    },
+    {
+      "epoch": 2.7024390243902436,
+      "grad_norm": 0.35853159941406193,
+      "learning_rate": 4.457333882913169e-05,
+      "loss": 0.4966,
+      "num_input_tokens_seen": 54407232,
+      "step": 140,
+      "train_runtime": 11852.5434,
+      "train_tokens_per_second": 4590.342
+    },
+    {
+      "epoch": 2.721951219512195,
+      "grad_norm": 0.3220506479281512,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 0.4851,
+      "num_input_tokens_seen": 54800064,
+      "step": 141,
+      "train_runtime": 11938.0,
+      "train_tokens_per_second": 4590.389
+    },
+    {
+      "epoch": 2.741463414634146,
+      "grad_norm": 0.338780671076278,
+      "learning_rate": 4.337387305278864e-05,
+      "loss": 0.4897,
+      "num_input_tokens_seen": 55192896,
+      "step": 142,
+      "train_runtime": 12023.5136,
+      "train_tokens_per_second": 4590.413
+    },
+    {
+      "epoch": 2.7609756097560973,
+      "grad_norm": 0.3467288544912658,
+      "learning_rate": 4.277554752153895e-05,
+      "loss": 0.4992,
+      "num_input_tokens_seen": 55585728,
+      "step": 143,
+      "train_runtime": 12109.1196,
+      "train_tokens_per_second": 4590.402
+    },
+    {
+      "epoch": 2.7804878048780486,
+      "grad_norm": 0.3172644652222353,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.4842,
+      "num_input_tokens_seen": 55978560,
+      "step": 144,
+      "train_runtime": 12194.6967,
+      "train_tokens_per_second": 4590.402
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.33792230752401564,
+      "learning_rate": 4.1582147932648074e-05,
+      "loss": 0.4941,
+      "num_input_tokens_seen": 56371392,
+      "step": 145,
+      "train_runtime": 12280.2743,
+      "train_tokens_per_second": 4590.402
+    },
+    {
+      "epoch": 2.819512195121951,
+      "grad_norm": 0.33669423565884143,
+      "learning_rate": 4.0987248109304714e-05,
+      "loss": 0.4933,
+      "num_input_tokens_seen": 56764224,
+      "step": 146,
+      "train_runtime": 12365.7877,
+      "train_tokens_per_second": 4590.425
+    },
+    {
+      "epoch": 2.8390243902439023,
+      "grad_norm": 0.32219243021646965,
+      "learning_rate": 4.039366413231458e-05,
+      "loss": 0.4847,
+      "num_input_tokens_seen": 57157056,
+      "step": 147,
+      "train_runtime": 12451.3235,
+      "train_tokens_per_second": 4590.44
+    },
+    {
+      "epoch": 2.8585365853658535,
+      "grad_norm": 0.32466591195010414,
+      "learning_rate": 3.980148266392258e-05,
+      "loss": 0.492,
+      "num_input_tokens_seen": 57549888,
+      "step": 148,
+      "train_runtime": 12536.8522,
+      "train_tokens_per_second": 4590.458
+    },
+    {
+      "epoch": 2.8780487804878048,
+      "grad_norm": 0.3484362997993096,
+      "learning_rate": 3.92107901616097e-05,
+      "loss": 0.4933,
+      "num_input_tokens_seen": 57942720,
+      "step": 149,
+      "train_runtime": 12622.324,
+      "train_tokens_per_second": 4590.495
+    },
+    {
+      "epoch": 2.897560975609756,
+      "grad_norm": 0.30189538682359085,
+      "learning_rate": 3.86216728654705e-05,
+      "loss": 0.4812,
+      "num_input_tokens_seen": 58335552,
+      "step": 150,
+      "train_runtime": 12707.9974,
+      "train_tokens_per_second": 4590.46
+    },
+    {
+      "epoch": 2.9170731707317072,
+      "grad_norm": 0.3427990142333379,
+      "learning_rate": 3.803421678562213e-05,
+      "loss": 0.4822,
+      "num_input_tokens_seen": 58728384,
+      "step": 151,
+      "train_runtime": 12793.4446,
+      "train_tokens_per_second": 4590.506
+    },
+    {
+      "epoch": 2.9365853658536585,
+      "grad_norm": 0.38332155033085324,
+      "learning_rate": 3.744850768964692e-05,
+      "loss": 0.4814,
+      "num_input_tokens_seen": 59121216,
+      "step": 152,
+      "train_runtime": 12878.9545,
+      "train_tokens_per_second": 4590.529
+    },
+    {
+      "epoch": 2.9560975609756097,
+      "grad_norm": 0.33602591668846876,
+      "learning_rate": 3.6864631090070655e-05,
+      "loss": 0.4921,
+      "num_input_tokens_seen": 59514048,
+      "step": 153,
+      "train_runtime": 12964.4255,
+      "train_tokens_per_second": 4590.566
+    },
+    {
+      "epoch": 2.975609756097561,
+      "grad_norm": 0.5609630326555886,
+      "learning_rate": 3.628267223187771e-05,
+      "loss": 0.4768,
+      "num_input_tokens_seen": 59906880,
+      "step": 154,
+      "train_runtime": 13049.8908,
+      "train_tokens_per_second": 4590.604
+    },
+    {
+      "epoch": 2.995121951219512,
+      "grad_norm": 0.3265623784171003,
+      "learning_rate": 3.570271608006555e-05,
+      "loss": 0.4579,
+      "num_input_tokens_seen": 60299712,
+      "step": 155,
+      "train_runtime": 13135.5526,
+      "train_tokens_per_second": 4590.573
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5314640992941223,
+      "learning_rate": 3.512484730723986e-05,
+      "loss": 0.4418,
+      "num_input_tokens_seen": 60397920,
+      "step": 156,
+      "train_runtime": 13156.9996,
+      "train_tokens_per_second": 4590.554
+    },
+    {
+      "epoch": 3.0195121951219512,
+      "grad_norm": 0.3203324244604146,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.4471,
+      "num_input_tokens_seen": 60790752,
+      "step": 157,
+      "train_runtime": 13242.5524,
+      "train_tokens_per_second": 4590.562
+    },
+    {
+      "epoch": 3.0390243902439025,
+      "grad_norm": 0.32182085188193466,
+      "learning_rate": 3.397570905288453e-05,
+      "loss": 0.4543,
+      "num_input_tokens_seen": 61183584,
+      "step": 158,
+      "train_runtime": 13328.1385,
+      "train_tokens_per_second": 4590.557
+    },
+    {
+      "epoch": 3.0585365853658537,
+      "grad_norm": 0.34726844831899983,
+      "learning_rate": 3.340460734357359e-05,
+      "loss": 0.4561,
+      "num_input_tokens_seen": 61576416,
+      "step": 159,
+      "train_runtime": 13413.7011,
+      "train_tokens_per_second": 4590.561
+    },
+    {
+      "epoch": 3.078048780487805,
+      "grad_norm": 0.32939131628064333,
+      "learning_rate": 3.283592853319209e-05,
+      "loss": 0.4521,
+      "num_input_tokens_seen": 61969248,
+      "step": 160,
+      "train_runtime": 13499.28,
+      "train_tokens_per_second": 4590.56
+    },
+    {
+      "epoch": 3.097560975609756,
+      "grad_norm": 0.325117680484632,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 0.444,
+      "num_input_tokens_seen": 62362080,
+      "step": 161,
+      "train_runtime": 13585.0343,
+      "train_tokens_per_second": 4590.499
+    },
+    {
+      "epoch": 3.1170731707317074,
+      "grad_norm": 0.32737548048736476,
+      "learning_rate": 3.170617134788939e-05,
+      "loss": 0.4541,
+      "num_input_tokens_seen": 62754912,
+      "step": 162,
+      "train_runtime": 13670.9946,
+      "train_tokens_per_second": 4590.369
+    },
+    {
+      "epoch": 3.1365853658536587,
+      "grad_norm": 0.39482140502206775,
+      "learning_rate": 3.114525791558398e-05,
+      "loss": 0.4582,
+      "num_input_tokens_seen": 63147744,
+      "step": 163,
+      "train_runtime": 13756.507,
+      "train_tokens_per_second": 4590.391
+    },
+    {
+      "epoch": 3.15609756097561,
+      "grad_norm": 0.3357742173716643,
+      "learning_rate": 3.0587097243358253e-05,
+      "loss": 0.4429,
+      "num_input_tokens_seen": 63540576,
+      "step": 164,
+      "train_runtime": 13842.0341,
+      "train_tokens_per_second": 4590.407
+    },
+    {
+      "epoch": 3.175609756097561,
+      "grad_norm": 0.3305601057024288,
+      "learning_rate": 3.003177082171523e-05,
+      "loss": 0.4443,
+      "num_input_tokens_seen": 63933408,
+      "step": 165,
+      "train_runtime": 13927.6175,
+      "train_tokens_per_second": 4590.405
+    },
+    {
+      "epoch": 3.1951219512195124,
+      "grad_norm": 0.32083308624205303,
+      "learning_rate": 2.9479359727362173e-05,
+      "loss": 0.4521,
+      "num_input_tokens_seen": 64326240,
+      "step": 166,
+      "train_runtime": 14013.2528,
+      "train_tokens_per_second": 4590.386
+    },
+    {
+      "epoch": 3.2146341463414636,
+      "grad_norm": 0.3335280375327217,
+      "learning_rate": 2.8929944611373554e-05,
+      "loss": 0.4362,
+      "num_input_tokens_seen": 64719072,
+      "step": 167,
+      "train_runtime": 14099.4999,
+      "train_tokens_per_second": 4590.168
+    },
+    {
+      "epoch": 3.234146341463415,
+      "grad_norm": 0.31479589078333686,
+      "learning_rate": 2.8383605687416125e-05,
+      "loss": 0.4503,
+      "num_input_tokens_seen": 65111904,
+      "step": 168,
+      "train_runtime": 14184.9981,
+      "train_tokens_per_second": 4590.195
+    },
+    {
+      "epoch": 3.253658536585366,
+      "grad_norm": 0.3729374255823192,
+      "learning_rate": 2.784042272003794e-05,
+      "loss": 0.448,
+      "num_input_tokens_seen": 65504736,
+      "step": 169,
+      "train_runtime": 14270.519,
+      "train_tokens_per_second": 4590.214
+    },
+    {
+      "epoch": 3.2731707317073173,
+      "grad_norm": 0.32769391044042884,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.4495,
+      "num_input_tokens_seen": 65897568,
+      "step": 170,
+      "train_runtime": 14355.9895,
+      "train_tokens_per_second": 4590.249
+    },
+    {
+      "epoch": 3.292682926829268,
+      "grad_norm": 0.3747118383247798,
+      "learning_rate": 2.6763841397811573e-05,
+      "loss": 0.4512,
+      "num_input_tokens_seen": 66290400,
+      "step": 171,
+      "train_runtime": 14441.5179,
+      "train_tokens_per_second": 4590.265
+    },
+    {
+      "epoch": 3.3121951219512193,
+      "grad_norm": 0.35364574417316713,
+      "learning_rate": 2.6230600221994196e-05,
+      "loss": 0.4342,
+      "num_input_tokens_seen": 66683232,
+      "step": 172,
+      "train_runtime": 14527.0516,
+      "train_tokens_per_second": 4590.28
+    },
+    {
+      "epoch": 3.3317073170731706,
+      "grad_norm": 0.34897968261286955,
+      "learning_rate": 2.57008293378697e-05,
+      "loss": 0.4456,
+      "num_input_tokens_seen": 67076064,
+      "step": 173,
+      "train_runtime": 14612.5638,
+      "train_tokens_per_second": 4590.301
+    },
+    {
+      "epoch": 3.351219512195122,
+      "grad_norm": 0.3526301707012528,
+      "learning_rate": 2.5174606091080627e-05,
+      "loss": 0.4459,
+      "num_input_tokens_seen": 67468896,
+      "step": 174,
+      "train_runtime": 14698.0406,
+      "train_tokens_per_second": 4590.333
+    },
+    {
+      "epoch": 3.370731707317073,
+      "grad_norm": 0.35117048748443935,
+      "learning_rate": 2.4652007309320498e-05,
+      "loss": 0.4383,
+      "num_input_tokens_seen": 67861728,
+      "step": 175,
+      "train_runtime": 14783.5396,
+      "train_tokens_per_second": 4590.357
+    },
+    {
+      "epoch": 3.3902439024390243,
+      "grad_norm": 0.3122289166658474,
+      "learning_rate": 2.4133109291117156e-05,
+      "loss": 0.4447,
+      "num_input_tokens_seen": 68254560,
+      "step": 176,
+      "train_runtime": 14868.9762,
+      "train_tokens_per_second": 4590.401
+    },
+    {
+      "epoch": 3.4097560975609755,
+      "grad_norm": 0.3521930408336,
+      "learning_rate": 2.361798779469336e-05,
+      "loss": 0.442,
+      "num_input_tokens_seen": 68647392,
+      "step": 177,
+      "train_runtime": 14954.4517,
+      "train_tokens_per_second": 4590.432
+    },
+    {
+      "epoch": 3.4292682926829268,
+      "grad_norm": 0.3077364343260739,
+      "learning_rate": 2.3106718026906072e-05,
+      "loss": 0.4418,
+      "num_input_tokens_seen": 69040224,
+      "step": 178,
+      "train_runtime": 15039.9655,
+      "train_tokens_per_second": 4590.451
+    },
+    {
+      "epoch": 3.448780487804878,
+      "grad_norm": 0.33010430660817575,
+      "learning_rate": 2.259937463226651e-05,
+      "loss": 0.4325,
+      "num_input_tokens_seen": 69433056,
+      "step": 179,
+      "train_runtime": 15125.4865,
+      "train_tokens_per_second": 4590.468
+    },
+    {
+      "epoch": 3.4682926829268292,
+      "grad_norm": 0.325795518062987,
+      "learning_rate": 2.209603168204209e-05,
+      "loss": 0.4319,
+      "num_input_tokens_seen": 69825888,
+      "step": 180,
+      "train_runtime": 15211.012,
+      "train_tokens_per_second": 4590.483
+    },
+    {
+      "epoch": 3.4878048780487805,
+      "grad_norm": 0.3179877620527606,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 0.4401,
+      "num_input_tokens_seen": 70218720,
+      "step": 181,
+      "train_runtime": 15296.5238,
+      "train_tokens_per_second": 4590.502
+    },
+    {
+      "epoch": 3.5073170731707317,
+      "grad_norm": 0.3287765696670568,
+      "learning_rate": 2.1101640468889255e-05,
+      "loss": 0.4386,
+      "num_input_tokens_seen": 70611552,
+      "step": 182,
+      "train_runtime": 15382.0311,
+      "train_tokens_per_second": 4590.522
+    },
+    {
+      "epoch": 3.526829268292683,
+      "grad_norm": 0.31971467799401765,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.4202,
+      "num_input_tokens_seen": 71004384,
+      "step": 183,
+      "train_runtime": 15467.521,
+      "train_tokens_per_second": 4590.547
+    },
+    {
+      "epoch": 3.546341463414634,
+      "grad_norm": 0.3239181143254052,
+      "learning_rate": 2.0124125083913637e-05,
+      "loss": 0.4419,
+      "num_input_tokens_seen": 71397216,
+      "step": 184,
+      "train_runtime": 15553.2048,
+      "train_tokens_per_second": 4590.515
+    },
+    {
+      "epoch": 3.5658536585365854,
+      "grad_norm": 0.3040342295851482,
+      "learning_rate": 1.9641874609064443e-05,
+      "loss": 0.4336,
+      "num_input_tokens_seen": 71790048,
+      "step": 185,
+      "train_runtime": 15638.8236,
+      "train_tokens_per_second": 4590.502
+    },
+    {
+      "epoch": 3.5853658536585367,
+      "grad_norm": 0.3144952842609461,
+      "learning_rate": 1.9164056368572846e-05,
+      "loss": 0.4387,
+      "num_input_tokens_seen": 72182880,
+      "step": 186,
+      "train_runtime": 15724.5242,
+      "train_tokens_per_second": 4590.465
+    },
+    {
+      "epoch": 3.604878048780488,
+      "grad_norm": 0.31728573983048836,
+      "learning_rate": 1.8690740123084316e-05,
+      "loss": 0.4297,
+      "num_input_tokens_seen": 72575712,
+      "step": 187,
+      "train_runtime": 15810.1041,
+      "train_tokens_per_second": 4590.464
+    },
+    {
+      "epoch": 3.624390243902439,
+      "grad_norm": 0.35290725632142694,
+      "learning_rate": 1.8221994975960736e-05,
+      "loss": 0.446,
+      "num_input_tokens_seen": 72968544,
+      "step": 188,
+      "train_runtime": 15895.683,
+      "train_tokens_per_second": 4590.463
+    },
+    {
+      "epoch": 3.6439024390243904,
+      "grad_norm": 0.31295107237929615,
+      "learning_rate": 1.7757889363191483e-05,
+      "loss": 0.4318,
+      "num_input_tokens_seen": 73361376,
+      "step": 189,
+      "train_runtime": 15981.3241,
+      "train_tokens_per_second": 4590.444
+    },
+    {
+      "epoch": 3.6634146341463416,
+      "grad_norm": 0.30434189898649333,
+      "learning_rate": 1.7298491043401795e-05,
+      "loss": 0.4393,
+      "num_input_tokens_seen": 73754208,
+      "step": 190,
+      "train_runtime": 16066.87,
+      "train_tokens_per_second": 4590.453
+    },
+    {
+      "epoch": 3.682926829268293,
+      "grad_norm": 0.3000645994101256,
+      "learning_rate": 1.684386708796025e-05,
+      "loss": 0.4437,
+      "num_input_tokens_seen": 74147040,
+      "step": 191,
+      "train_runtime": 16152.3518,
+      "train_tokens_per_second": 4590.48
+    },
+    {
+      "epoch": 3.7024390243902436,
+      "grad_norm": 0.3161645570263139,
+      "learning_rate": 1.6394083871186362e-05,
+      "loss": 0.4378,
+      "num_input_tokens_seen": 74539872,
+      "step": 192,
+      "train_runtime": 16237.7807,
+      "train_tokens_per_second": 4590.521
+    },
+    {
+      "epoch": 3.721951219512195,
+      "grad_norm": 0.3085852095656564,
+      "learning_rate": 1.5949207060660138e-05,
+      "loss": 0.4388,
+      "num_input_tokens_seen": 74932704,
+      "step": 193,
+      "train_runtime": 16323.3128,
+      "train_tokens_per_second": 4590.533
+    },
+    {
+      "epoch": 3.741463414634146,
+      "grad_norm": 0.3214095905441243,
+      "learning_rate": 1.550930160763462e-05,
+      "loss": 0.4483,
+      "num_input_tokens_seen": 75325536,
+      "step": 194,
+      "train_runtime": 16408.7376,
+      "train_tokens_per_second": 4590.575
+    },
+    {
+      "epoch": 3.7609756097560973,
+      "grad_norm": 0.3029571828988472,
+      "learning_rate": 1.5074431737553157e-05,
+      "loss": 0.4336,
+      "num_input_tokens_seen": 75718368,
+      "step": 195,
+      "train_runtime": 16494.1425,
+      "train_tokens_per_second": 4590.622
+    },
+    {
+      "epoch": 3.7804878048780486,
+      "grad_norm": 0.3002722038512263,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4334,
+      "num_input_tokens_seen": 76111200,
+      "step": 196,
+      "train_runtime": 16579.5744,
+      "train_tokens_per_second": 4590.661
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.30486554391008086,
+      "learning_rate": 1.422005196279395e-05,
+      "loss": 0.4352,
+      "num_input_tokens_seen": 76504032,
+      "step": 197,
+      "train_runtime": 16665.0963,
+      "train_tokens_per_second": 4590.674
+    },
+    {
+      "epoch": 3.819512195121951,
+      "grad_norm": 0.3019225596466138,
+      "learning_rate": 1.3800666796101292e-05,
+      "loss": 0.4315,
+      "num_input_tokens_seen": 76896864,
+      "step": 198,
+      "train_runtime": 16750.5821,
+      "train_tokens_per_second": 4590.698
+    },
+    {
+      "epoch": 3.8390243902439023,
+      "grad_norm": 0.29879067901515843,
+      "learning_rate": 1.338656667011134e-05,
+      "loss": 0.4339,
+      "num_input_tokens_seen": 77289696,
+      "step": 199,
+      "train_runtime": 16836.0019,
+      "train_tokens_per_second": 4590.739
+    },
+    {
+      "epoch": 3.8585365853658535,
+      "grad_norm": 0.3064182382633002,
+      "learning_rate": 1.297781204273385e-05,
+      "loss": 0.4374,
+      "num_input_tokens_seen": 77682528,
+      "step": 200,
+      "train_runtime": 16921.5579,
+      "train_tokens_per_second": 4590.743
+    },
+    {
+      "epoch": 3.8780487804878048,
+      "grad_norm": 0.31545962722826715,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 0.4437,
+      "num_input_tokens_seen": 78075360,
+      "step": 201,
+      "train_runtime": 17007.1429,
+      "train_tokens_per_second": 4590.739
+    },
+    {
+      "epoch": 3.897560975609756,
+      "grad_norm": 0.3062038073298703,
+      "learning_rate": 1.2176577204574318e-05,
+      "loss": 0.4319,
+      "num_input_tokens_seen": 78468192,
+      "step": 202,
+      "train_runtime": 17092.564,
+      "train_tokens_per_second": 4590.779
+    },
+    {
+      "epoch": 3.9170731707317072,
+      "grad_norm": 0.4440664308923016,
+      "learning_rate": 1.178421397270758e-05,
+      "loss": 0.4322,
+      "num_input_tokens_seen": 78861024,
+      "step": 203,
+      "train_runtime": 17178.0234,
+      "train_tokens_per_second": 4590.809
+    },
+    {
+      "epoch": 3.9365853658536585,
+      "grad_norm": 0.3017158051173835,
+      "learning_rate": 1.1397430180205171e-05,
+      "loss": 0.4375,
+      "num_input_tokens_seen": 79253856,
+      "step": 204,
+      "train_runtime": 17263.8463,
+      "train_tokens_per_second": 4590.742
+    },
+    {
+      "epoch": 3.9560975609756097,
+      "grad_norm": 0.3075889998265315,
+      "learning_rate": 1.1016282296838887e-05,
+      "loss": 0.4182,
+      "num_input_tokens_seen": 79646688,
+      "step": 205,
+      "train_runtime": 17349.3107,
+      "train_tokens_per_second": 4590.77
+    },
+    {
+      "epoch": 3.975609756097561,
+      "grad_norm": 0.30086206726131764,
+      "learning_rate": 1.0640825969547496e-05,
+      "loss": 0.4382,
+      "num_input_tokens_seen": 80039520,
+      "step": 206,
+      "train_runtime": 17434.78,
+      "train_tokens_per_second": 4590.796
+    },
+    {
+      "epoch": 3.995121951219512,
+      "grad_norm": 0.30615268970962656,
+      "learning_rate": 1.0271116014312293e-05,
+      "loss": 0.4277,
+      "num_input_tokens_seen": 80432352,
+      "step": 207,
+      "train_runtime": 17520.2702,
+      "train_tokens_per_second": 4590.817
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5575452767715656,
+      "learning_rate": 9.90720640815408e-06,
+      "loss": 0.4029,
+      "num_input_tokens_seen": 80530560,
+      "step": 208,
+      "train_runtime": 17541.5926,
+      "train_tokens_per_second": 4590.835
+    },
+    {
+      "epoch": 4.019512195121951,
+      "grad_norm": 0.30272512353274567,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4243,
+      "num_input_tokens_seen": 80923392,
+      "step": 209,
+      "train_runtime": 17627.0549,
+      "train_tokens_per_second": 4590.863
+    },
+    {
+      "epoch": 4.0390243902439025,
+      "grad_norm": 0.30162450457883366,
+      "learning_rate": 9.196999909189762e-06,
+      "loss": 0.4146,
+      "num_input_tokens_seen": 81316224,
+      "step": 210,
+      "train_runtime": 17713.1477,
+      "train_tokens_per_second": 4590.727
+    },
+    {
+      "epoch": 4.058536585365854,
+      "grad_norm": 0.30526033181573403,
+      "learning_rate": 8.850806705317183e-06,
+      "loss": 0.4287,
+      "num_input_tokens_seen": 81709056,
+      "step": 211,
+      "train_runtime": 17798.6213,
+      "train_tokens_per_second": 4590.752
+    },
+    {
+      "epoch": 4.078048780487805,
+      "grad_norm": 0.3107654508084313,
+      "learning_rate": 8.510621213250247e-06,
+      "loss": 0.4221,
+      "num_input_tokens_seen": 82101888,
+      "step": 212,
+      "train_runtime": 17884.1454,
+      "train_tokens_per_second": 4590.764
+    },
+    {
+      "epoch": 4.097560975609756,
+      "grad_norm": 0.325160265062242,
+      "learning_rate": 8.176493099488663e-06,
+      "loss": 0.4232,
+      "num_input_tokens_seen": 82494720,
+      "step": 213,
+      "train_runtime": 17969.6704,
+      "train_tokens_per_second": 4590.775
+    },
+    {
+      "epoch": 4.117073170731707,
+      "grad_norm": 0.3137465946251142,
+      "learning_rate": 7.848471146165288e-06,
+      "loss": 0.416,
+      "num_input_tokens_seen": 82887552,
+      "step": 214,
+      "train_runtime": 18055.2394,
+      "train_tokens_per_second": 4590.776
+    },
+    {
+      "epoch": 4.136585365853659,
+      "grad_norm": 0.31293023871568965,
+      "learning_rate": 7.526603243923957e-06,
+      "loss": 0.4157,
+      "num_input_tokens_seen": 83280384,
+      "step": 215,
+      "train_runtime": 18140.8949,
+      "train_tokens_per_second": 4590.754
+    },
+    {
+      "epoch": 4.15609756097561,
+      "grad_norm": 0.31719664973482375,
+      "learning_rate": 7.21093638492763e-06,
+      "loss": 0.4174,
+      "num_input_tokens_seen": 83673216,
+      "step": 216,
+      "train_runtime": 18226.5244,
+      "train_tokens_per_second": 4590.739
+    },
+    {
+      "epoch": 4.175609756097561,
+      "grad_norm": 0.3958840925349482,
+      "learning_rate": 6.901516655997536e-06,
+      "loss": 0.4041,
+      "num_input_tokens_seen": 84066048,
+      "step": 217,
+      "train_runtime": 18312.181,
+      "train_tokens_per_second": 4590.717
+    },
+    {
+      "epoch": 4.195121951219512,
+      "grad_norm": 0.30791697730474177,
+      "learning_rate": 6.5983892318846275e-06,
+      "loss": 0.4155,
+      "num_input_tokens_seen": 84458880,
+      "step": 218,
+      "train_runtime": 18397.8319,
+      "train_tokens_per_second": 4590.697
+    },
+    {
+      "epoch": 4.214634146341464,
+      "grad_norm": 0.3034741442256561,
+      "learning_rate": 6.301598368674105e-06,
+      "loss": 0.4214,
+      "num_input_tokens_seen": 84851712,
+      "step": 219,
+      "train_runtime": 18483.4309,
+      "train_tokens_per_second": 4590.691
+    },
+    {
+      "epoch": 4.234146341463415,
+      "grad_norm": 0.32535838114327126,
+      "learning_rate": 6.011187397324114e-06,
+      "loss": 0.4193,
+      "num_input_tokens_seen": 85244544,
+      "step": 220,
+      "train_runtime": 18569.0539,
+      "train_tokens_per_second": 4590.678
+    },
+    {
+      "epoch": 4.253658536585366,
+      "grad_norm": 0.3033400736842611,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 0.4137,
+      "num_input_tokens_seen": 85637376,
+      "step": 221,
+      "train_runtime": 18654.7358,
+      "train_tokens_per_second": 4590.651
+    },
+    {
+      "epoch": 4.273170731707317,
+      "grad_norm": 0.3293082877684599,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.4069,
+      "num_input_tokens_seen": 86030208,
+      "step": 222,
+      "train_runtime": 18740.4478,
+      "train_tokens_per_second": 4590.616
+    },
+    {
+      "epoch": 4.2926829268292686,
+      "grad_norm": 0.2994148389025656,
+      "learning_rate": 5.178653135214812e-06,
+      "loss": 0.4188,
+      "num_input_tokens_seen": 86423040,
+      "step": 223,
+      "train_runtime": 18826.1093,
+      "train_tokens_per_second": 4590.595
+    },
+    {
+      "epoch": 4.31219512195122,
+      "grad_norm": 0.3140763914390958,
+      "learning_rate": 4.914176319791036e-06,
+      "loss": 0.4133,
+      "num_input_tokens_seen": 86815872,
+      "step": 224,
+      "train_runtime": 18911.7783,
+      "train_tokens_per_second": 4590.572
+    },
+    {
+      "epoch": 4.331707317073171,
+      "grad_norm": 0.3058594326378288,
+      "learning_rate": 4.65628195747273e-06,
+      "loss": 0.4136,
+      "num_input_tokens_seen": 87208704,
+      "step": 225,
+      "train_runtime": 18997.5405,
+      "train_tokens_per_second": 4590.526
+    },
+    {
+      "epoch": 4.351219512195122,
+      "grad_norm": 0.3036952677463643,
+      "learning_rate": 4.405007700395497e-06,
+      "loss": 0.4066,
+      "num_input_tokens_seen": 87601536,
+      "step": 226,
+      "train_runtime": 19083.2658,
+      "train_tokens_per_second": 4590.49
+    },
+    {
+      "epoch": 4.3707317073170735,
+      "grad_norm": 0.2986697055188429,
+      "learning_rate": 4.16039023417088e-06,
+      "loss": 0.4002,
+      "num_input_tokens_seen": 87994368,
+      "step": 227,
+      "train_runtime": 19168.9792,
+      "train_tokens_per_second": 4590.457
+    },
+    {
+      "epoch": 4.390243902439025,
+      "grad_norm": 0.30912351105330554,
+      "learning_rate": 3.922465272530351e-06,
+      "loss": 0.4213,
+      "num_input_tokens_seen": 88387200,
+      "step": 228,
+      "train_runtime": 19254.8776,
+      "train_tokens_per_second": 4590.38
+    },
+    {
+      "epoch": 4.409756097560976,
+      "grad_norm": 0.31390545996696395,
+      "learning_rate": 3.691267552111183e-06,
+      "loss": 0.4276,
+      "num_input_tokens_seen": 88780032,
+      "step": 229,
+      "train_runtime": 19340.5507,
+      "train_tokens_per_second": 4590.357
+    },
+    {
+      "epoch": 4.429268292682927,
+      "grad_norm": 0.3064931328623729,
+      "learning_rate": 3.4668308273848982e-06,
+      "loss": 0.417,
+      "num_input_tokens_seen": 89172864,
+      "step": 230,
+      "train_runtime": 19426.2001,
+      "train_tokens_per_second": 4590.34
+    },
+    {
+      "epoch": 4.4487804878048784,
+      "grad_norm": 0.2938965818242203,
+      "learning_rate": 3.249187865729264e-06,
+      "loss": 0.4036,
+      "num_input_tokens_seen": 89565696,
+      "step": 231,
+      "train_runtime": 19511.8505,
+      "train_tokens_per_second": 4590.323
+    },
+    {
+      "epoch": 4.46829268292683,
+      "grad_norm": 0.3009741802462199,
+      "learning_rate": 3.0383704426442394e-06,
+      "loss": 0.4109,
+      "num_input_tokens_seen": 89958528,
+      "step": 232,
+      "train_runtime": 19597.5003,
+      "train_tokens_per_second": 4590.306
+    },
+    {
+      "epoch": 4.487804878048781,
+      "grad_norm": 0.30572185629569554,
+      "learning_rate": 2.8344093371128424e-06,
+      "loss": 0.4177,
+      "num_input_tokens_seen": 90351360,
+      "step": 233,
+      "train_runtime": 19683.1546,
+      "train_tokens_per_second": 4590.289
+    },
+    {
+      "epoch": 4.507317073170732,
+      "grad_norm": 0.3060090032156781,
+      "learning_rate": 2.637334327107466e-06,
+      "loss": 0.4167,
+      "num_input_tokens_seen": 90744192,
+      "step": 234,
+      "train_runtime": 19768.7311,
+      "train_tokens_per_second": 4590.289
+    },
+    {
+      "epoch": 4.526829268292683,
+      "grad_norm": 0.30158648786459336,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4214,
+      "num_input_tokens_seen": 91137024,
+      "step": 235,
+      "train_runtime": 19854.2512,
+      "train_tokens_per_second": 4590.303
+    },
+    {
+      "epoch": 4.546341463414635,
+      "grad_norm": 0.30106548477413225,
+      "learning_rate": 2.2639566745727205e-06,
+      "loss": 0.4038,
+      "num_input_tokens_seen": 91529856,
+      "step": 236,
+      "train_runtime": 19939.85,
+      "train_tokens_per_second": 4590.298
+    },
+    {
+      "epoch": 4.565853658536585,
+      "grad_norm": 0.31280608719577163,
+      "learning_rate": 2.087708544541689e-06,
+      "loss": 0.4087,
+      "num_input_tokens_seen": 91922688,
+      "step": 237,
+      "train_runtime": 20025.4609,
+      "train_tokens_per_second": 4590.291
+    },
+    {
+      "epoch": 4.585365853658536,
+      "grad_norm": 0.3151237023853444,
+      "learning_rate": 1.9184555270746194e-06,
+      "loss": 0.4099,
+      "num_input_tokens_seen": 92315520,
+      "step": 238,
+      "train_runtime": 20111.0379,
+      "train_tokens_per_second": 4590.291
+    },
+    {
+      "epoch": 4.6048780487804875,
+      "grad_norm": 0.2979822004749027,
+      "learning_rate": 1.7562223328224325e-06,
+      "loss": 0.4098,
+      "num_input_tokens_seen": 92708352,
+      "step": 239,
+      "train_runtime": 20196.6063,
+      "train_tokens_per_second": 4590.294
+    },
+    {
+      "epoch": 4.624390243902439,
+      "grad_norm": 0.29641279383853864,
+      "learning_rate": 1.601032647553863e-06,
+      "loss": 0.4106,
+      "num_input_tokens_seen": 93101184,
+      "step": 240,
+      "train_runtime": 20282.2193,
+      "train_tokens_per_second": 4590.286
+    },
+    {
+      "epoch": 4.64390243902439,
+      "grad_norm": 0.30405930218468175,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 0.4204,
+      "num_input_tokens_seen": 93494016,
+      "step": 241,
+      "train_runtime": 20367.7887,
+      "train_tokens_per_second": 4590.288
+    },
+    {
+      "epoch": 4.663414634146341,
+      "grad_norm": 0.30816493741451845,
+      "learning_rate": 1.3118734020333256e-06,
+      "loss": 0.4069,
+      "num_input_tokens_seen": 93886848,
+      "step": 242,
+      "train_runtime": 20453.3944,
+      "train_tokens_per_second": 4590.282
+    },
+    {
+      "epoch": 4.682926829268292,
+      "grad_norm": 0.295889585872778,
+      "learning_rate": 1.1779460585363944e-06,
+      "loss": 0.4206,
+      "num_input_tokens_seen": 94279680,
+      "step": 243,
+      "train_runtime": 20538.896,
+      "train_tokens_per_second": 4590.299
+    },
+    {
+      "epoch": 4.702439024390244,
+      "grad_norm": 0.30064754265380783,
+      "learning_rate": 1.0511466513695777e-06,
+      "loss": 0.4216,
+      "num_input_tokens_seen": 94672512,
+      "step": 244,
+      "train_runtime": 20624.455,
+      "train_tokens_per_second": 4590.304
+    },
+    {
+      "epoch": 4.721951219512195,
+      "grad_norm": 0.2956056728342269,
+      "learning_rate": 9.314936930293283e-07,
+      "loss": 0.4067,
+      "num_input_tokens_seen": 95065344,
+      "step": 245,
+      "train_runtime": 20710.4849,
+      "train_tokens_per_second": 4590.204
+    },
+    {
+      "epoch": 4.741463414634146,
+      "grad_norm": 1.2801159100545316,
+      "learning_rate": 8.190046526428242e-07,
+      "loss": 0.4149,
+      "num_input_tokens_seen": 95458176,
+      "step": 246,
+      "train_runtime": 20796.2392,
+      "train_tokens_per_second": 4590.165
+    },
+    {
+      "epoch": 4.760975609756097,
+      "grad_norm": 0.2962901875713787,
+      "learning_rate": 7.136959534174592e-07,
+      "loss": 0.4104,
+      "num_input_tokens_seen": 95851008,
+      "step": 247,
+      "train_runtime": 20881.9173,
+      "train_tokens_per_second": 4590.144
+    },
+    {
+      "epoch": 4.780487804878049,
+      "grad_norm": 0.29775756656133795,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.4275,
+      "num_input_tokens_seen": 96243840,
+      "step": 248,
+      "train_runtime": 20967.6297,
+      "train_tokens_per_second": 4590.115
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.30152743001548155,
+      "learning_rate": 5.246800274474439e-07,
+      "loss": 0.4168,
+      "num_input_tokens_seen": 96636672,
+      "step": 249,
+      "train_runtime": 21053.3487,
+      "train_tokens_per_second": 4590.086
+    },
+    {
+      "epoch": 4.819512195121951,
+      "grad_norm": 0.3006544700138266,
+      "learning_rate": 4.4100039670454395e-07,
+      "loss": 0.4227,
+      "num_input_tokens_seen": 97029504,
+      "step": 250,
+      "train_runtime": 21139.1446,
+      "train_tokens_per_second": 4590.039
+    },
+    {
+      "epoch": 4.839024390243902,
+      "grad_norm": 0.3694815192213994,
+      "learning_rate": 3.6455629509730136e-07,
+      "loss": 0.4224,
+      "num_input_tokens_seen": 97422336,
+      "step": 251,
+      "train_runtime": 21224.947,
+      "train_tokens_per_second": 4589.992
+    },
+    {
+      "epoch": 4.8585365853658535,
+      "grad_norm": 0.29849891867672973,
+      "learning_rate": 2.953588833337406e-07,
+      "loss": 0.409,
+      "num_input_tokens_seen": 97815168,
+      "step": 252,
+      "train_runtime": 21311.0603,
+      "train_tokens_per_second": 4589.878
+    },
+    {
+      "epoch": 4.878048780487805,
+      "grad_norm": 0.29318102693895126,
+      "learning_rate": 2.334182641175686e-07,
+      "loss": 0.4164,
+      "num_input_tokens_seen": 98208000,
+      "step": 253,
+      "train_runtime": 21396.8922,
+      "train_tokens_per_second": 4589.825
+    },
+    {
+      "epoch": 4.897560975609756,
+      "grad_norm": 0.29392220191104595,
+      "learning_rate": 1.7874348067319912e-07,
+      "loss": 0.4048,
+      "num_input_tokens_seen": 98600832,
+      "step": 254,
+      "train_runtime": 21482.6378,
+      "train_tokens_per_second": 4589.792
+    },
+    {
+      "epoch": 4.917073170731707,
+      "grad_norm": 0.29522364415867186,
+      "learning_rate": 1.3134251542544774e-07,
+      "loss": 0.4082,
+      "num_input_tokens_seen": 98993664,
+      "step": 255,
+      "train_runtime": 21568.4139,
+      "train_tokens_per_second": 4589.752
+    },
+    {
+      "epoch": 4.9365853658536585,
+      "grad_norm": 0.29818003556233796,
+      "learning_rate": 9.12222888341252e-08,
+      "loss": 0.4214,
+      "num_input_tokens_seen": 99386496,
+      "step": 256,
+      "train_runtime": 21654.0911,
+      "train_tokens_per_second": 4589.733
+    },
+    {
+      "epoch": 4.95609756097561,
+      "grad_norm": 0.29688566274903394,
+      "learning_rate": 5.838865838366792e-08,
+      "loss": 0.413,
+      "num_input_tokens_seen": 99779328,
+      "step": 257,
+      "train_runtime": 21739.8502,
+      "train_tokens_per_second": 4589.697
+    },
+    {
+      "epoch": 4.975609756097561,
+      "grad_norm": 0.2972951381912236,
+      "learning_rate": 3.284641772793862e-08,
+      "loss": 0.4118,
+      "num_input_tokens_seen": 100172160,
+      "step": 258,
+      "train_runtime": 21825.6482,
+      "train_tokens_per_second": 4589.653
+    },
+    {
+      "epoch": 4.995121951219512,
+      "grad_norm": 0.2934977397098327,
+      "learning_rate": 1.4599295990352924e-08,
+      "loss": 0.4169,
+      "num_input_tokens_seen": 100564992,
+      "step": 259,
+      "train_runtime": 21911.3681,
+      "train_tokens_per_second": 4589.626
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.598332221412963,
+      "learning_rate": 3.6499572194648167e-09,
+      "loss": 0.3937,
+      "num_input_tokens_seen": 100663200,
+      "step": 260,
+      "train_runtime": 21932.7813,
+      "train_tokens_per_second": 4589.623
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 260,
+  "num_input_tokens_seen": 100663200,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2377568804143104.0,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-260/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28367a7f01f97d093d01f03db18770fc51c71f24731638d1414a6bbecdecf30
+size 8081

checkpoint-260/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "num_input_tokens_seen": 100663200,
+    "total_flos": 2377568804143104.0,
+    "train_loss": 0.697018449810835,
+    "train_runtime": 22008.2973,
+    "train_samples_per_second": 4.45,
+    "train_steps_per_second": 0.012
+}

trainer_log.jsonl

@@ -0,0 +1,273 @@
+{"current_steps": 1, "total_steps": 385, "loss": 1.9495, "lr": 0.0001, "epoch": 0.013029315960912053, "percentage": 0.26, "elapsed_time": "0:01:01", "remaining_time": "6:33:13", "throughput": 4262.41, "total_tokens": 261888}
+{"current_steps": 2, "total_steps": 385, "loss": 1.9305, "lr": 9.999833537702192e-05, "epoch": 0.026058631921824105, "percentage": 0.52, "elapsed_time": "0:01:59", "remaining_time": "6:20:29", "throughput": 4393.49, "total_tokens": 523776}
+{"current_steps": 3, "total_steps": 385, "loss": 1.9086, "lr": 9.999334161892648e-05, "epoch": 0.03908794788273615, "percentage": 0.78, "elapsed_time": "0:02:57", "remaining_time": "6:15:46", "throughput": 4437.13, "total_tokens": 785664}
+{"current_steps": 1, "total_steps": 195, "loss": 1.9471, "lr": 0.0001, "epoch": 0.025974025974025976, "percentage": 0.51, "elapsed_time": "0:02:03", "remaining_time": "6:39:29", "throughput": 4239.3, "total_tokens": 523776}
+{"current_steps": 2, "total_steps": 195, "loss": 1.9384, "lr": 9.999351124856874e-05, "epoch": 0.05194805194805195, "percentage": 1.03, "elapsed_time": "0:04:02", "remaining_time": "6:30:22", "throughput": 4315.8, "total_tokens": 1047552}
+{"current_steps": 1, "total_steps": 195, "loss": 1.9471, "lr": 0.0001, "epoch": 0.026058631921824105, "percentage": 0.51, "elapsed_time": "0:01:58", "remaining_time": "6:23:41", "throughput": 4413.77, "total_tokens": 523776}
+{"current_steps": 1, "total_steps": 385, "loss": 1.9495, "lr": 0.0001, "epoch": 0.013029315960912053, "percentage": 0.26, "elapsed_time": "0:01:01", "remaining_time": "6:36:33", "throughput": 4226.57, "total_tokens": 261888}
+{"current_steps": 2, "total_steps": 385, "loss": 1.9304, "lr": 9.999833537702192e-05, "epoch": 0.026058631921824105, "percentage": 0.52, "elapsed_time": "0:01:59", "remaining_time": "6:22:12", "throughput": 4373.84, "total_tokens": 523776}
+{"current_steps": 3, "total_steps": 385, "loss": 1.9078, "lr": 9.999334161892648e-05, "epoch": 0.03908794788273615, "percentage": 0.78, "elapsed_time": "0:02:57", "remaining_time": "6:17:06", "throughput": 4421.44, "total_tokens": 785664}
+{"current_steps": 4, "total_steps": 385, "loss": 1.8593, "lr": 9.998501905822266e-05, "epoch": 0.05211726384364821, "percentage": 1.04, "elapsed_time": "0:03:55", "remaining_time": "6:14:23", "throughput": 4441.89, "total_tokens": 1047552}
+{"current_steps": 5, "total_steps": 385, "loss": 1.8125, "lr": 9.997336824906748e-05, "epoch": 0.06514657980456026, "percentage": 1.3, "elapsed_time": "0:04:54", "remaining_time": "6:12:28", "throughput": 4452.97, "total_tokens": 1309440}
+{"current_steps": 6, "total_steps": 385, "loss": 1.8287, "lr": 9.995838996722914e-05, "epoch": 0.0781758957654723, "percentage": 1.56, "elapsed_time": "0:05:51", "remaining_time": "6:10:32", "throughput": 4464.52, "total_tokens": 1571328}
+{"current_steps": 1, "total_steps": 260, "loss": 1.9481, "lr": 0.0001, "epoch": 0.01951219512195122, "percentage": 0.38, "elapsed_time": "0:01:29", "remaining_time": "6:25:15", "throughput": 4401.53, "total_tokens": 392832}
+{"current_steps": 2, "total_steps": 260, "loss": 1.9426, "lr": 9.999635004278054e-05, "epoch": 0.03902439024390244, "percentage": 0.77, "elapsed_time": "0:02:55", "remaining_time": "6:16:18", "throughput": 4488.88, "total_tokens": 785664}
+{"current_steps": 3, "total_steps": 260, "loss": 1.8808, "lr": 9.998540070400966e-05, "epoch": 0.05853658536585366, "percentage": 1.15, "elapsed_time": "0:04:20", "remaining_time": "6:12:00", "throughput": 4523.17, "total_tokens": 1178496}
+{"current_steps": 4, "total_steps": 260, "loss": 1.8827, "lr": 9.996715358227206e-05, "epoch": 0.07804878048780488, "percentage": 1.54, "elapsed_time": "0:05:45", "remaining_time": "6:09:03", "throughput": 4541.61, "total_tokens": 1571328}
+{"current_steps": 5, "total_steps": 260, "loss": 1.8196, "lr": 9.994161134161634e-05, "epoch": 0.0975609756097561, "percentage": 1.92, "elapsed_time": "0:07:11", "remaining_time": "6:06:46", "throughput": 4551.83, "total_tokens": 1964160}
+{"current_steps": 6, "total_steps": 260, "loss": 1.7928, "lr": 9.990877771116589e-05, "epoch": 0.11707317073170732, "percentage": 2.31, "elapsed_time": "0:08:36", "remaining_time": "6:04:46", "throughput": 4559.0, "total_tokens": 2356992}
+{"current_steps": 7, "total_steps": 260, "loss": 1.7726, "lr": 9.986865748457457e-05, "epoch": 0.13658536585365855, "percentage": 2.69, "elapsed_time": "0:10:02", "remaining_time": "6:02:58", "throughput": 4563.49, "total_tokens": 2749824}
+{"current_steps": 8, "total_steps": 260, "loss": 1.7569, "lr": 9.982125651932681e-05, "epoch": 0.15609756097560976, "percentage": 3.08, "elapsed_time": "0:11:28", "remaining_time": "6:01:18", "throughput": 4566.44, "total_tokens": 3142656}
+{"current_steps": 9, "total_steps": 260, "loss": 1.7263, "lr": 9.976658173588244e-05, "epoch": 0.17560975609756097, "percentage": 3.46, "elapsed_time": "0:12:53", "remaining_time": "5:59:43", "throughput": 4568.25, "total_tokens": 3535488}
+{"current_steps": 10, "total_steps": 260, "loss": 1.7278, "lr": 9.970464111666626e-05, "epoch": 0.1951219512195122, "percentage": 3.85, "elapsed_time": "0:14:19", "remaining_time": "5:58:06", "throughput": 4570.67, "total_tokens": 3928320}
+{"current_steps": 11, "total_steps": 260, "loss": 1.719, "lr": 9.96354437049027e-05, "epoch": 0.2146341463414634, "percentage": 4.23, "elapsed_time": "0:15:45", "remaining_time": "5:56:32", "throughput": 4572.36, "total_tokens": 4321152}
+{"current_steps": 12, "total_steps": 260, "loss": 1.6873, "lr": 9.955899960329547e-05, "epoch": 0.23414634146341465, "percentage": 4.62, "elapsed_time": "0:17:10", "remaining_time": "5:54:59", "throughput": 4573.83, "total_tokens": 4713984}
+{"current_steps": 13, "total_steps": 260, "loss": 1.6583, "lr": 9.947531997255256e-05, "epoch": 0.25365853658536586, "percentage": 5.0, "elapsed_time": "0:18:36", "remaining_time": "5:53:31", "throughput": 4574.38, "total_tokens": 5106816}
+{"current_steps": 14, "total_steps": 260, "loss": 1.6484, "lr": 9.938441702975689e-05, "epoch": 0.2731707317073171, "percentage": 5.38, "elapsed_time": "0:20:02", "remaining_time": "5:52:02", "throughput": 4575.05, "total_tokens": 5499648}
+{"current_steps": 15, "total_steps": 260, "loss": 1.6392, "lr": 9.928630404658255e-05, "epoch": 0.2926829268292683, "percentage": 5.77, "elapsed_time": "0:21:27", "remaining_time": "5:50:32", "throughput": 4576.01, "total_tokens": 5892480}
+{"current_steps": 16, "total_steps": 260, "loss": 1.6079, "lr": 9.918099534735718e-05, "epoch": 0.3121951219512195, "percentage": 6.15, "elapsed_time": "0:22:53", "remaining_time": "5:49:01", "throughput": 4577.02, "total_tokens": 6285312}
+{"current_steps": 17, "total_steps": 260, "loss": 1.614, "lr": 9.906850630697068e-05, "epoch": 0.33170731707317075, "percentage": 6.54, "elapsed_time": "0:24:18", "remaining_time": "5:47:34", "throughput": 4577.27, "total_tokens": 6678144}
+{"current_steps": 18, "total_steps": 260, "loss": 1.5871, "lr": 9.894885334863044e-05, "epoch": 0.35121951219512193, "percentage": 6.92, "elapsed_time": "0:25:44", "remaining_time": "5:46:06", "throughput": 4577.86, "total_tokens": 7070976}
+{"current_steps": 19, "total_steps": 260, "loss": 1.5864, "lr": 9.882205394146361e-05, "epoch": 0.37073170731707317, "percentage": 7.31, "elapsed_time": "0:27:10", "remaining_time": "5:44:37", "throughput": 4578.49, "total_tokens": 7463808}
+{"current_steps": 20, "total_steps": 260, "loss": 1.547, "lr": 9.868812659796668e-05, "epoch": 0.3902439024390244, "percentage": 7.69, "elapsed_time": "0:28:35", "remaining_time": "5:43:09", "throughput": 4578.91, "total_tokens": 7856640}
+{"current_steps": 21, "total_steps": 260, "loss": 1.5349, "lr": 9.85470908713026e-05, "epoch": 0.4097560975609756, "percentage": 8.08, "elapsed_time": "0:30:01", "remaining_time": "5:41:41", "throughput": 4579.45, "total_tokens": 8249472}
+{"current_steps": 22, "total_steps": 260, "loss": 1.5123, "lr": 9.839896735244614e-05, "epoch": 0.4292682926829268, "percentage": 8.46, "elapsed_time": "0:31:26", "remaining_time": "5:40:13", "throughput": 4580.1, "total_tokens": 8642304}
+{"current_steps": 23, "total_steps": 260, "loss": 1.4901, "lr": 9.824377766717759e-05, "epoch": 0.44878048780487806, "percentage": 8.85, "elapsed_time": "0:32:52", "remaining_time": "5:38:44", "throughput": 4580.68, "total_tokens": 9035136}
+{"current_steps": 24, "total_steps": 260, "loss": 1.4924, "lr": 9.808154447292539e-05, "epoch": 0.4682926829268293, "percentage": 9.23, "elapsed_time": "0:34:18", "remaining_time": "5:37:17", "throughput": 4580.98, "total_tokens": 9427968}
+{"current_steps": 25, "total_steps": 260, "loss": 1.4489, "lr": 9.791229145545831e-05, "epoch": 0.4878048780487805, "percentage": 9.62, "elapsed_time": "0:35:43", "remaining_time": "5:35:51", "throughput": 4581.1, "total_tokens": 9820800}
+{"current_steps": 26, "total_steps": 260, "loss": 1.4188, "lr": 9.773604332542729e-05, "epoch": 0.5073170731707317, "percentage": 10.0, "elapsed_time": "0:37:09", "remaining_time": "5:34:24", "throughput": 4581.34, "total_tokens": 10213632}
+{"current_steps": 27, "total_steps": 260, "loss": 1.4272, "lr": 9.755282581475769e-05, "epoch": 0.526829268292683, "percentage": 10.38, "elapsed_time": "0:38:34", "remaining_time": "5:32:56", "throughput": 4581.91, "total_tokens": 10606464}
+{"current_steps": 28, "total_steps": 260, "loss": 1.3815, "lr": 9.736266567289253e-05, "epoch": 0.5463414634146342, "percentage": 10.77, "elapsed_time": "0:40:00", "remaining_time": "5:31:29", "throughput": 4582.24, "total_tokens": 10999296}
+{"current_steps": 29, "total_steps": 260, "loss": 1.3752, "lr": 9.716559066288715e-05, "epoch": 0.5658536585365853, "percentage": 11.15, "elapsed_time": "0:41:26", "remaining_time": "5:30:02", "throughput": 4582.45, "total_tokens": 11392128}
+{"current_steps": 30, "total_steps": 260, "loss": 1.3629, "lr": 9.696162955735577e-05, "epoch": 0.5853658536585366, "percentage": 11.54, "elapsed_time": "0:42:51", "remaining_time": "5:28:36", "throughput": 4582.63, "total_tokens": 11784960}
+{"current_steps": 31, "total_steps": 260, "loss": 1.3163, "lr": 9.675081213427076e-05, "epoch": 0.6048780487804878, "percentage": 11.92, "elapsed_time": "0:44:17", "remaining_time": "5:27:09", "throughput": 4582.94, "total_tokens": 12177792}
+{"current_steps": 32, "total_steps": 260, "loss": 1.3058, "lr": 9.653316917261512e-05, "epoch": 0.624390243902439, "percentage": 12.31, "elapsed_time": "0:45:42", "remaining_time": "5:25:41", "throughput": 4583.34, "total_tokens": 12570624}
+{"current_steps": 33, "total_steps": 260, "loss": 1.2774, "lr": 9.630873244788883e-05, "epoch": 0.6439024390243903, "percentage": 12.69, "elapsed_time": "0:47:08", "remaining_time": "5:24:14", "throughput": 4583.78, "total_tokens": 12963456}
+{"current_steps": 34, "total_steps": 260, "loss": 1.2585, "lr": 9.607753472746966e-05, "epoch": 0.6634146341463415, "percentage": 13.08, "elapsed_time": "0:48:33", "remaining_time": "5:22:46", "throughput": 4584.21, "total_tokens": 13356288}
+{"current_steps": 35, "total_steps": 260, "loss": 1.2429, "lr": 9.583960976582913e-05, "epoch": 0.6829268292682927, "percentage": 13.46, "elapsed_time": "0:49:59", "remaining_time": "5:21:19", "throughput": 4584.55, "total_tokens": 13749120}
+{"current_steps": 36, "total_steps": 260, "loss": 1.2092, "lr": 9.559499229960451e-05, "epoch": 0.7024390243902439, "percentage": 13.85, "elapsed_time": "0:51:24", "remaining_time": "5:19:52", "throughput": 4584.71, "total_tokens": 14141952}
+{"current_steps": 37, "total_steps": 260, "loss": 1.1789, "lr": 9.534371804252728e-05, "epoch": 0.7219512195121951, "percentage": 14.23, "elapsed_time": "0:52:50", "remaining_time": "5:18:28", "throughput": 4584.43, "total_tokens": 14534784}
+{"current_steps": 38, "total_steps": 260, "loss": 1.1495, "lr": 9.508582368020897e-05, "epoch": 0.7414634146341463, "percentage": 14.62, "elapsed_time": "0:54:16", "remaining_time": "5:17:02", "throughput": 4584.52, "total_tokens": 14927616}
+{"current_steps": 39, "total_steps": 260, "loss": 1.141, "lr": 9.482134686478519e-05, "epoch": 0.7609756097560976, "percentage": 15.0, "elapsed_time": "0:55:41", "remaining_time": "5:15:35", "throughput": 4584.91, "total_tokens": 15320448}
+{"current_steps": 40, "total_steps": 260, "loss": 1.1236, "lr": 9.45503262094184e-05, "epoch": 0.7804878048780488, "percentage": 15.38, "elapsed_time": "0:57:06", "remaining_time": "5:14:08", "throughput": 4585.17, "total_tokens": 15713280}
+{"current_steps": 41, "total_steps": 260, "loss": 1.1034, "lr": 9.42728012826605e-05, "epoch": 0.8, "percentage": 15.77, "elapsed_time": "0:58:32", "remaining_time": "5:12:41", "throughput": 4585.36, "total_tokens": 16106112}
+{"current_steps": 42, "total_steps": 260, "loss": 1.1052, "lr": 9.398881260267589e-05, "epoch": 0.8195121951219512, "percentage": 16.15, "elapsed_time": "0:59:57", "remaining_time": "5:11:15", "throughput": 4585.64, "total_tokens": 16498944}
+{"current_steps": 43, "total_steps": 260, "loss": 1.0595, "lr": 9.36984016313259e-05, "epoch": 0.8390243902439024, "percentage": 16.54, "elapsed_time": "1:01:23", "remaining_time": "5:09:48", "throughput": 4585.99, "total_tokens": 16891776}
+{"current_steps": 44, "total_steps": 260, "loss": 1.0507, "lr": 9.340161076811537e-05, "epoch": 0.8585365853658536, "percentage": 16.92, "elapsed_time": "1:02:48", "remaining_time": "5:08:21", "throughput": 4586.27, "total_tokens": 17284608}
+{"current_steps": 45, "total_steps": 260, "loss": 1.0204, "lr": 9.309848334400246e-05, "epoch": 0.8780487804878049, "percentage": 17.31, "elapsed_time": "1:04:14", "remaining_time": "5:06:54", "throughput": 4586.51, "total_tokens": 17677440}
+{"current_steps": 46, "total_steps": 260, "loss": 1.0275, "lr": 9.278906361507238e-05, "epoch": 0.8975609756097561, "percentage": 17.69, "elapsed_time": "1:05:39", "remaining_time": "5:05:27", "throughput": 4586.83, "total_tokens": 18070272}
+{"current_steps": 47, "total_steps": 260, "loss": 0.9942, "lr": 9.247339675607605e-05, "epoch": 0.9170731707317074, "percentage": 18.08, "elapsed_time": "1:07:05", "remaining_time": "5:04:01", "throughput": 4586.88, "total_tokens": 18463104}
+{"current_steps": 48, "total_steps": 260, "loss": 0.9636, "lr": 9.215152885383474e-05, "epoch": 0.9365853658536586, "percentage": 18.46, "elapsed_time": "1:08:30", "remaining_time": "5:02:35", "throughput": 4587.06, "total_tokens": 18855936}
+{"current_steps": 49, "total_steps": 260, "loss": 0.9595, "lr": 9.182350690051133e-05, "epoch": 0.9560975609756097, "percentage": 18.85, "elapsed_time": "1:09:56", "remaining_time": "5:01:08", "throughput": 4587.31, "total_tokens": 19248768}
+{"current_steps": 50, "total_steps": 260, "loss": 0.9406, "lr": 9.148937878674976e-05, "epoch": 0.975609756097561, "percentage": 19.23, "elapsed_time": "1:11:21", "remaining_time": "4:59:42", "throughput": 4587.55, "total_tokens": 19641600}
+{"current_steps": 51, "total_steps": 260, "loss": 0.9266, "lr": 9.114919329468282e-05, "epoch": 0.9951219512195122, "percentage": 19.62, "elapsed_time": "1:12:46", "remaining_time": "4:58:15", "throughput": 4587.78, "total_tokens": 20034432}
+{"current_steps": 52, "total_steps": 260, "loss": 0.9145, "lr": 9.080300009081024e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "1:13:08", "remaining_time": "4:52:33", "throughput": 4587.79, "total_tokens": 20132640}
+{"current_steps": 53, "total_steps": 260, "loss": 0.8835, "lr": 9.045084971874738e-05, "epoch": 1.0195121951219512, "percentage": 20.38, "elapsed_time": "1:14:33", "remaining_time": "4:51:13", "throughput": 4587.92, "total_tokens": 20525472}
+{"current_steps": 54, "total_steps": 260, "loss": 0.8894, "lr": 9.009279359184593e-05, "epoch": 1.0390243902439025, "percentage": 20.77, "elapsed_time": "1:15:59", "remaining_time": "4:49:52", "throughput": 4588.1, "total_tokens": 20918304}
+{"current_steps": 55, "total_steps": 260, "loss": 0.8801, "lr": 8.972888398568772e-05, "epoch": 1.0585365853658537, "percentage": 21.15, "elapsed_time": "1:17:24", "remaining_time": "4:48:32", "throughput": 4588.24, "total_tokens": 21311136}
+{"current_steps": 56, "total_steps": 260, "loss": 0.8761, "lr": 8.935917403045251e-05, "epoch": 1.078048780487805, "percentage": 21.54, "elapsed_time": "1:18:50", "remaining_time": "4:47:11", "throughput": 4588.43, "total_tokens": 21703968}
+{"current_steps": 57, "total_steps": 260, "loss": 0.8785, "lr": 8.898371770316111e-05, "epoch": 1.0975609756097562, "percentage": 21.92, "elapsed_time": "1:20:15", "remaining_time": "4:45:50", "throughput": 4588.63, "total_tokens": 22096800}
+{"current_steps": 58, "total_steps": 260, "loss": 0.8964, "lr": 8.860256981979484e-05, "epoch": 1.1170731707317074, "percentage": 22.31, "elapsed_time": "1:21:40", "remaining_time": "4:44:28", "throughput": 4588.79, "total_tokens": 22489632}
+{"current_steps": 59, "total_steps": 260, "loss": 0.8833, "lr": 8.821578602729242e-05, "epoch": 1.1365853658536587, "percentage": 22.69, "elapsed_time": "1:23:06", "remaining_time": "4:43:07", "throughput": 4588.98, "total_tokens": 22882464}
+{"current_steps": 60, "total_steps": 260, "loss": 0.8698, "lr": 8.782342279542568e-05, "epoch": 1.1560975609756097, "percentage": 23.08, "elapsed_time": "1:24:31", "remaining_time": "4:41:46", "throughput": 4589.15, "total_tokens": 23275296}
+{"current_steps": 61, "total_steps": 260, "loss": 0.864, "lr": 8.742553740855506e-05, "epoch": 1.175609756097561, "percentage": 23.46, "elapsed_time": "1:25:57", "remaining_time": "4:40:24", "throughput": 4589.34, "total_tokens": 23668128}
+{"current_steps": 62, "total_steps": 260, "loss": 0.8551, "lr": 8.702218795726617e-05, "epoch": 1.1951219512195121, "percentage": 23.85, "elapsed_time": "1:27:22", "remaining_time": "4:39:02", "throughput": 4589.53, "total_tokens": 24060960}
+{"current_steps": 63, "total_steps": 260, "loss": 0.8327, "lr": 8.661343332988869e-05, "epoch": 1.2146341463414634, "percentage": 24.23, "elapsed_time": "1:28:48", "remaining_time": "4:37:40", "throughput": 4589.65, "total_tokens": 24453792}
+{"current_steps": 64, "total_steps": 260, "loss": 0.8003, "lr": 8.619933320389872e-05, "epoch": 1.2341463414634146, "percentage": 24.62, "elapsed_time": "1:30:13", "remaining_time": "4:36:18", "throughput": 4589.76, "total_tokens": 24846624}
+{"current_steps": 65, "total_steps": 260, "loss": 0.8078, "lr": 8.577994803720606e-05, "epoch": 1.2536585365853659, "percentage": 25.0, "elapsed_time": "1:31:38", "remaining_time": "4:34:56", "throughput": 4589.87, "total_tokens": 25239456}
+{"current_steps": 66, "total_steps": 260, "loss": 0.8033, "lr": 8.535533905932738e-05, "epoch": 1.273170731707317, "percentage": 25.38, "elapsed_time": "1:33:04", "remaining_time": "4:33:34", "throughput": 4589.99, "total_tokens": 25632288}
+{"current_steps": 67, "total_steps": 260, "loss": 0.7751, "lr": 8.492556826244687e-05, "epoch": 1.2926829268292683, "percentage": 25.77, "elapsed_time": "1:34:29", "remaining_time": "4:32:12", "throughput": 4590.14, "total_tokens": 26025120}
+{"current_steps": 68, "total_steps": 260, "loss": 0.7998, "lr": 8.449069839236538e-05, "epoch": 1.3121951219512196, "percentage": 26.15, "elapsed_time": "1:35:55", "remaining_time": "4:30:49", "throughput": 4590.33, "total_tokens": 26417952}
+{"current_steps": 69, "total_steps": 260, "loss": 0.7949, "lr": 8.405079293933986e-05, "epoch": 1.3317073170731708, "percentage": 26.54, "elapsed_time": "1:37:20", "remaining_time": "4:29:27", "throughput": 4590.48, "total_tokens": 26810784}
+{"current_steps": 70, "total_steps": 260, "loss": 0.7718, "lr": 8.360591612881364e-05, "epoch": 1.3512195121951218, "percentage": 26.92, "elapsed_time": "1:38:45", "remaining_time": "4:28:04", "throughput": 4590.6, "total_tokens": 27203616}
+{"current_steps": 71, "total_steps": 260, "loss": 0.7827, "lr": 8.315613291203976e-05, "epoch": 1.370731707317073, "percentage": 27.31, "elapsed_time": "1:40:11", "remaining_time": "4:26:42", "throughput": 4590.69, "total_tokens": 27596448}
+{"current_steps": 72, "total_steps": 260, "loss": 0.7595, "lr": 8.270150895659823e-05, "epoch": 1.3902439024390243, "percentage": 27.69, "elapsed_time": "1:41:36", "remaining_time": "4:25:19", "throughput": 4590.74, "total_tokens": 27989280}
+{"current_steps": 73, "total_steps": 260, "loss": 0.7416, "lr": 8.224211063680853e-05, "epoch": 1.4097560975609755, "percentage": 28.08, "elapsed_time": "1:43:02", "remaining_time": "4:23:56", "throughput": 4590.84, "total_tokens": 28382112}
+{"current_steps": 74, "total_steps": 260, "loss": 0.749, "lr": 8.177800502403928e-05, "epoch": 1.4292682926829268, "percentage": 28.46, "elapsed_time": "1:44:27", "remaining_time": "4:22:34", "throughput": 4590.89, "total_tokens": 28774944}
+{"current_steps": 75, "total_steps": 260, "loss": 0.72, "lr": 8.130925987691569e-05, "epoch": 1.448780487804878, "percentage": 28.85, "elapsed_time": "1:45:53", "remaining_time": "4:21:11", "throughput": 4590.96, "total_tokens": 29167776}
+{"current_steps": 76, "total_steps": 260, "loss": 0.7192, "lr": 8.083594363142717e-05, "epoch": 1.4682926829268292, "percentage": 29.23, "elapsed_time": "1:47:18", "remaining_time": "4:19:48", "throughput": 4591.02, "total_tokens": 29560608}
+{"current_steps": 77, "total_steps": 260, "loss": 0.7221, "lr": 8.035812539093557e-05, "epoch": 1.4878048780487805, "percentage": 29.62, "elapsed_time": "1:48:44", "remaining_time": "4:18:26", "throughput": 4591.0, "total_tokens": 29953440}
+{"current_steps": 78, "total_steps": 260, "loss": 0.7031, "lr": 7.987587491608637e-05, "epoch": 1.5073170731707317, "percentage": 30.0, "elapsed_time": "1:50:10", "remaining_time": "4:17:03", "throughput": 4590.94, "total_tokens": 30346272}
+{"current_steps": 79, "total_steps": 260, "loss": 0.7118, "lr": 7.938926261462366e-05, "epoch": 1.526829268292683, "percentage": 30.38, "elapsed_time": "1:51:35", "remaining_time": "4:15:40", "throughput": 4590.95, "total_tokens": 30739104}
+{"current_steps": 80, "total_steps": 260, "loss": 0.6952, "lr": 7.889835953111075e-05, "epoch": 1.5463414634146342, "percentage": 30.77, "elapsed_time": "1:53:01", "remaining_time": "4:14:18", "throughput": 4590.72, "total_tokens": 31131936}
+{"current_steps": 81, "total_steps": 260, "loss": 0.6693, "lr": 7.840323733655778e-05, "epoch": 1.5658536585365854, "percentage": 31.15, "elapsed_time": "1:54:27", "remaining_time": "4:12:56", "throughput": 4590.34, "total_tokens": 31524768}
+{"current_steps": 82, "total_steps": 260, "loss": 0.6718, "lr": 7.790396831795792e-05, "epoch": 1.5853658536585367, "percentage": 31.54, "elapsed_time": "1:55:53", "remaining_time": "4:11:33", "throughput": 4590.33, "total_tokens": 31917600}
+{"current_steps": 83, "total_steps": 260, "loss": 0.67, "lr": 7.740062536773352e-05, "epoch": 1.604878048780488, "percentage": 31.92, "elapsed_time": "1:57:18", "remaining_time": "4:10:10", "throughput": 4590.35, "total_tokens": 32310432}
+{"current_steps": 84, "total_steps": 260, "loss": 0.6688, "lr": 7.689328197309393e-05, "epoch": 1.6243902439024391, "percentage": 32.31, "elapsed_time": "1:58:44", "remaining_time": "4:08:47", "throughput": 4590.37, "total_tokens": 32703264}
+{"current_steps": 85, "total_steps": 260, "loss": 0.6672, "lr": 7.638201220530665e-05, "epoch": 1.6439024390243904, "percentage": 32.69, "elapsed_time": "2:00:09", "remaining_time": "4:07:23", "throughput": 4590.43, "total_tokens": 33096096}
+{"current_steps": 86, "total_steps": 260, "loss": 0.6573, "lr": 7.586689070888284e-05, "epoch": 1.6634146341463416, "percentage": 33.08, "elapsed_time": "2:01:35", "remaining_time": "4:06:00", "throughput": 4590.48, "total_tokens": 33488928}
+{"current_steps": 87, "total_steps": 260, "loss": 0.6422, "lr": 7.534799269067953e-05, "epoch": 1.6829268292682928, "percentage": 33.46, "elapsed_time": "2:03:00", "remaining_time": "4:04:36", "throughput": 4590.56, "total_tokens": 33881760}
+{"current_steps": 88, "total_steps": 260, "loss": 0.6269, "lr": 7.48253939089194e-05, "epoch": 1.7024390243902439, "percentage": 33.85, "elapsed_time": "2:04:26", "remaining_time": "4:03:12", "throughput": 4590.66, "total_tokens": 34274592}
+{"current_steps": 89, "total_steps": 260, "loss": 0.6357, "lr": 7.42991706621303e-05, "epoch": 1.721951219512195, "percentage": 34.23, "elapsed_time": "2:05:51", "remaining_time": "4:01:49", "throughput": 4590.66, "total_tokens": 34667424}
+{"current_steps": 90, "total_steps": 260, "loss": 0.6299, "lr": 7.376939977800582e-05, "epoch": 1.7414634146341463, "percentage": 34.62, "elapsed_time": "2:07:17", "remaining_time": "4:00:26", "throughput": 4590.64, "total_tokens": 35060256}
+{"current_steps": 91, "total_steps": 260, "loss": 0.634, "lr": 7.323615860218843e-05, "epoch": 1.7609756097560976, "percentage": 35.0, "elapsed_time": "2:08:42", "remaining_time": "3:59:02", "throughput": 4590.66, "total_tokens": 35453088}
+{"current_steps": 92, "total_steps": 260, "loss": 0.6251, "lr": 7.269952498697734e-05, "epoch": 1.7804878048780488, "percentage": 35.38, "elapsed_time": "2:10:08", "remaining_time": "3:57:38", "throughput": 4590.73, "total_tokens": 35845920}
+{"current_steps": 93, "total_steps": 260, "loss": 0.62, "lr": 7.215957727996207e-05, "epoch": 1.8, "percentage": 35.77, "elapsed_time": "2:11:33", "remaining_time": "3:56:14", "throughput": 4590.83, "total_tokens": 36238752}
+{"current_steps": 94, "total_steps": 260, "loss": 0.6073, "lr": 7.161639431258387e-05, "epoch": 1.819512195121951, "percentage": 36.15, "elapsed_time": "2:12:59", "remaining_time": "3:54:50", "throughput": 4590.9, "total_tokens": 36631584}
+{"current_steps": 95, "total_steps": 260, "loss": 0.6074, "lr": 7.107005538862646e-05, "epoch": 1.8390243902439023, "percentage": 36.54, "elapsed_time": "2:14:24", "remaining_time": "3:53:27", "throughput": 4590.94, "total_tokens": 37024416}
+{"current_steps": 96, "total_steps": 260, "loss": 0.6064, "lr": 7.052064027263786e-05, "epoch": 1.8585365853658535, "percentage": 36.92, "elapsed_time": "2:15:50", "remaining_time": "3:52:03", "throughput": 4591.01, "total_tokens": 37417248}
+{"current_steps": 97, "total_steps": 260, "loss": 0.5922, "lr": 6.996822917828477e-05, "epoch": 1.8780487804878048, "percentage": 37.31, "elapsed_time": "2:17:15", "remaining_time": "3:50:39", "throughput": 4591.05, "total_tokens": 37810080}
+{"current_steps": 98, "total_steps": 260, "loss": 0.5939, "lr": 6.941290275664174e-05, "epoch": 1.897560975609756, "percentage": 37.69, "elapsed_time": "2:18:41", "remaining_time": "3:49:15", "throughput": 4591.13, "total_tokens": 38202912}
+{"current_steps": 99, "total_steps": 260, "loss": 0.5913, "lr": 6.885474208441603e-05, "epoch": 1.9170731707317072, "percentage": 38.08, "elapsed_time": "2:20:06", "remaining_time": "3:47:51", "throughput": 4591.19, "total_tokens": 38595744}
+{"current_steps": 100, "total_steps": 260, "loss": 0.5863, "lr": 6.829382865211063e-05, "epoch": 1.9365853658536585, "percentage": 38.46, "elapsed_time": "2:21:31", "remaining_time": "3:46:27", "throughput": 4591.22, "total_tokens": 38988576}
+{"current_steps": 101, "total_steps": 260, "loss": 0.5822, "lr": 6.773024435212678e-05, "epoch": 1.9560975609756097, "percentage": 38.85, "elapsed_time": "2:22:57", "remaining_time": "3:45:03", "throughput": 4591.26, "total_tokens": 39381408}
+{"current_steps": 102, "total_steps": 260, "loss": 0.5666, "lr": 6.716407146680792e-05, "epoch": 1.975609756097561, "percentage": 39.23, "elapsed_time": "2:24:22", "remaining_time": "3:43:39", "throughput": 4591.31, "total_tokens": 39774240}
+{"current_steps": 103, "total_steps": 260, "loss": 0.5806, "lr": 6.659539265642643e-05, "epoch": 1.9951219512195122, "percentage": 39.62, "elapsed_time": "2:25:48", "remaining_time": "3:42:14", "throughput": 4591.37, "total_tokens": 40167072}
+{"current_steps": 104, "total_steps": 260, "loss": 0.5605, "lr": 6.602429094711548e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "2:26:09", "remaining_time": "3:39:14", "throughput": 4591.4, "total_tokens": 40265280}
+{"current_steps": 105, "total_steps": 260, "loss": 0.5462, "lr": 6.545084971874738e-05, "epoch": 2.0195121951219512, "percentage": 40.38, "elapsed_time": "2:27:35", "remaining_time": "3:37:52", "throughput": 4591.42, "total_tokens": 40658112}
+{"current_steps": 106, "total_steps": 260, "loss": 0.5447, "lr": 6.487515269276016e-05, "epoch": 2.0390243902439025, "percentage": 40.77, "elapsed_time": "2:29:00", "remaining_time": "3:36:29", "throughput": 4591.45, "total_tokens": 41050944}
+{"current_steps": 107, "total_steps": 260, "loss": 0.5405, "lr": 6.429728391993446e-05, "epoch": 2.0585365853658537, "percentage": 41.15, "elapsed_time": "2:30:26", "remaining_time": "3:35:06", "throughput": 4591.48, "total_tokens": 41443776}
+{"current_steps": 108, "total_steps": 260, "loss": 0.5433, "lr": 6.37173277681223e-05, "epoch": 2.078048780487805, "percentage": 41.54, "elapsed_time": "2:31:51", "remaining_time": "3:33:43", "throughput": 4591.51, "total_tokens": 41836608}
+{"current_steps": 109, "total_steps": 260, "loss": 0.5335, "lr": 6.313536890992935e-05, "epoch": 2.097560975609756, "percentage": 41.92, "elapsed_time": "2:33:17", "remaining_time": "3:32:21", "throughput": 4591.46, "total_tokens": 42229440}
+{"current_steps": 110, "total_steps": 260, "loss": 0.5416, "lr": 6.255149231035309e-05, "epoch": 2.1170731707317074, "percentage": 42.31, "elapsed_time": "2:34:42", "remaining_time": "3:30:58", "throughput": 4591.44, "total_tokens": 42622272}
+{"current_steps": 111, "total_steps": 260, "loss": 0.5322, "lr": 6.19657832143779e-05, "epoch": 2.1365853658536587, "percentage": 42.69, "elapsed_time": "2:36:08", "remaining_time": "3:29:35", "throughput": 4591.43, "total_tokens": 43015104}
+{"current_steps": 112, "total_steps": 260, "loss": 0.5301, "lr": 6.13783271345295e-05, "epoch": 2.15609756097561, "percentage": 43.08, "elapsed_time": "2:37:34", "remaining_time": "3:28:13", "throughput": 4591.39, "total_tokens": 43407936}
+{"current_steps": 113, "total_steps": 260, "loss": 0.5422, "lr": 6.078920983839031e-05, "epoch": 2.175609756097561, "percentage": 43.46, "elapsed_time": "2:38:59", "remaining_time": "3:26:50", "throughput": 4591.39, "total_tokens": 43800768}
+{"current_steps": 114, "total_steps": 260, "loss": 0.5352, "lr": 6.019851733607744e-05, "epoch": 2.1951219512195124, "percentage": 43.85, "elapsed_time": "2:40:25", "remaining_time": "3:25:27", "throughput": 4591.43, "total_tokens": 44193600}
+{"current_steps": 115, "total_steps": 260, "loss": 0.5112, "lr": 5.960633586768543e-05, "epoch": 2.2146341463414636, "percentage": 44.23, "elapsed_time": "2:41:50", "remaining_time": "3:24:04", "throughput": 4591.41, "total_tokens": 44586432}
+{"current_steps": 116, "total_steps": 260, "loss": 0.5171, "lr": 5.90127518906953e-05, "epoch": 2.234146341463415, "percentage": 44.62, "elapsed_time": "2:43:16", "remaining_time": "3:22:40", "throughput": 4591.44, "total_tokens": 44979264}
+{"current_steps": 117, "total_steps": 260, "loss": 0.5027, "lr": 5.841785206735192e-05, "epoch": 2.253658536585366, "percentage": 45.0, "elapsed_time": "2:44:42", "remaining_time": "3:21:18", "throughput": 4591.38, "total_tokens": 45372096}
+{"current_steps": 118, "total_steps": 260, "loss": 0.5151, "lr": 5.782172325201155e-05, "epoch": 2.2731707317073173, "percentage": 45.38, "elapsed_time": "2:46:07", "remaining_time": "3:19:54", "throughput": 4591.36, "total_tokens": 45764928}
+{"current_steps": 119, "total_steps": 260, "loss": 0.5152, "lr": 5.7224452478461064e-05, "epoch": 2.292682926829268, "percentage": 45.77, "elapsed_time": "2:47:33", "remaining_time": "3:18:31", "throughput": 4591.37, "total_tokens": 46157760}
+{"current_steps": 120, "total_steps": 260, "loss": 0.5303, "lr": 5.6626126947211386e-05, "epoch": 2.3121951219512193, "percentage": 46.15, "elapsed_time": "2:48:58", "remaining_time": "3:17:08", "throughput": 4591.4, "total_tokens": 46550592}
+{"current_steps": 121, "total_steps": 260, "loss": 0.5032, "lr": 5.602683401276615e-05, "epoch": 2.3317073170731706, "percentage": 46.54, "elapsed_time": "2:50:24", "remaining_time": "3:15:45", "throughput": 4591.3, "total_tokens": 46943424}
+{"current_steps": 122, "total_steps": 260, "loss": 0.5119, "lr": 5.542666117086832e-05, "epoch": 2.351219512195122, "percentage": 46.92, "elapsed_time": "2:51:49", "remaining_time": "3:14:22", "throughput": 4591.31, "total_tokens": 47336256}
+{"current_steps": 123, "total_steps": 260, "loss": 0.5045, "lr": 5.482569604572576e-05, "epoch": 2.370731707317073, "percentage": 47.31, "elapsed_time": "2:53:15", "remaining_time": "3:12:58", "throughput": 4591.25, "total_tokens": 47729088}
+{"current_steps": 124, "total_steps": 260, "loss": 0.505, "lr": 5.422402637721836e-05, "epoch": 2.3902439024390243, "percentage": 47.69, "elapsed_time": "2:54:41", "remaining_time": "3:11:35", "throughput": 4591.14, "total_tokens": 48121920}
+{"current_steps": 125, "total_steps": 260, "loss": 0.5017, "lr": 5.3621740008088126e-05, "epoch": 2.4097560975609755, "percentage": 48.08, "elapsed_time": "2:56:07", "remaining_time": "3:10:12", "throughput": 4591.09, "total_tokens": 48514752}
+{"current_steps": 126, "total_steps": 260, "loss": 0.5019, "lr": 5.3018924871114305e-05, "epoch": 2.4292682926829268, "percentage": 48.46, "elapsed_time": "2:57:32", "remaining_time": "3:08:49", "throughput": 4591.12, "total_tokens": 48907584}
+{"current_steps": 127, "total_steps": 260, "loss": 0.4921, "lr": 5.2415668976275355e-05, "epoch": 2.448780487804878, "percentage": 48.85, "elapsed_time": "2:58:58", "remaining_time": "3:07:25", "throughput": 4591.12, "total_tokens": 49300416}
+{"current_steps": 128, "total_steps": 260, "loss": 0.4951, "lr": 5.181206039789962e-05, "epoch": 2.4682926829268292, "percentage": 49.23, "elapsed_time": "3:00:23", "remaining_time": "3:06:01", "throughput": 4591.15, "total_tokens": 49693248}
+{"current_steps": 129, "total_steps": 260, "loss": 0.5076, "lr": 5.1208187261806615e-05, "epoch": 2.4878048780487805, "percentage": 49.62, "elapsed_time": "3:01:49", "remaining_time": "3:04:38", "throughput": 4591.19, "total_tokens": 50086080}
+{"current_steps": 130, "total_steps": 260, "loss": 0.4974, "lr": 5.060413773244087e-05, "epoch": 2.5073170731707317, "percentage": 50.0, "elapsed_time": "3:03:14", "remaining_time": "3:03:14", "throughput": 4591.16, "total_tokens": 50478912}
+{"current_steps": 131, "total_steps": 260, "loss": 0.5063, "lr": 5e-05, "epoch": 2.526829268292683, "percentage": 50.38, "elapsed_time": "3:04:40", "remaining_time": "3:01:51", "throughput": 4591.19, "total_tokens": 50871744}
+{"current_steps": 132, "total_steps": 260, "loss": 0.5093, "lr": 4.9395862267559136e-05, "epoch": 2.546341463414634, "percentage": 50.77, "elapsed_time": "3:06:05", "remaining_time": "3:00:27", "throughput": 4591.2, "total_tokens": 51264576}
+{"current_steps": 133, "total_steps": 260, "loss": 0.5019, "lr": 4.87918127381934e-05, "epoch": 2.5658536585365854, "percentage": 51.15, "elapsed_time": "3:07:31", "remaining_time": "2:59:03", "throughput": 4591.18, "total_tokens": 51657408}
+{"current_steps": 134, "total_steps": 260, "loss": 0.4836, "lr": 4.81879396021004e-05, "epoch": 2.5853658536585367, "percentage": 51.54, "elapsed_time": "3:08:57", "remaining_time": "2:57:40", "throughput": 4591.15, "total_tokens": 52050240}
+{"current_steps": 135, "total_steps": 260, "loss": 0.4878, "lr": 4.758433102372466e-05, "epoch": 2.604878048780488, "percentage": 51.92, "elapsed_time": "3:10:22", "remaining_time": "2:56:16", "throughput": 4591.09, "total_tokens": 52443072}
+{"current_steps": 136, "total_steps": 260, "loss": 0.4895, "lr": 4.6981075128885693e-05, "epoch": 2.624390243902439, "percentage": 52.31, "elapsed_time": "3:11:48", "remaining_time": "2:54:53", "throughput": 4591.03, "total_tokens": 52835904}
+{"current_steps": 137, "total_steps": 260, "loss": 0.4987, "lr": 4.6378259991911886e-05, "epoch": 2.6439024390243904, "percentage": 52.69, "elapsed_time": "3:13:14", "remaining_time": "2:53:29", "throughput": 4590.96, "total_tokens": 53228736}
+{"current_steps": 138, "total_steps": 260, "loss": 0.4952, "lr": 4.5775973622781655e-05, "epoch": 2.6634146341463416, "percentage": 53.08, "elapsed_time": "3:14:39", "remaining_time": "2:52:05", "throughput": 4590.92, "total_tokens": 53621568}
+{"current_steps": 139, "total_steps": 260, "loss": 0.4852, "lr": 4.5174303954274244e-05, "epoch": 2.682926829268293, "percentage": 53.46, "elapsed_time": "3:16:05", "remaining_time": "2:50:41", "throughput": 4590.88, "total_tokens": 54014400}
+{"current_steps": 140, "total_steps": 260, "loss": 0.4966, "lr": 4.457333882913169e-05, "epoch": 2.7024390243902436, "percentage": 53.85, "elapsed_time": "3:17:31", "remaining_time": "2:49:18", "throughput": 4590.84, "total_tokens": 54407232}
+{"current_steps": 141, "total_steps": 260, "loss": 0.4851, "lr": 4.397316598723385e-05, "epoch": 2.721951219512195, "percentage": 54.23, "elapsed_time": "3:18:56", "remaining_time": "2:47:54", "throughput": 4590.88, "total_tokens": 54800064}
+{"current_steps": 142, "total_steps": 260, "loss": 0.4897, "lr": 4.337387305278864e-05, "epoch": 2.741463414634146, "percentage": 54.62, "elapsed_time": "3:20:22", "remaining_time": "2:46:30", "throughput": 4590.9, "total_tokens": 55192896}
+{"current_steps": 143, "total_steps": 260, "loss": 0.4992, "lr": 4.277554752153895e-05, "epoch": 2.7609756097560973, "percentage": 55.0, "elapsed_time": "3:21:47", "remaining_time": "2:45:06", "throughput": 4590.89, "total_tokens": 55585728}
+{"current_steps": 144, "total_steps": 260, "loss": 0.4842, "lr": 4.2178276747988446e-05, "epoch": 2.7804878048780486, "percentage": 55.38, "elapsed_time": "3:23:13", "remaining_time": "2:43:42", "throughput": 4590.89, "total_tokens": 55978560}
+{"current_steps": 145, "total_steps": 260, "loss": 0.4941, "lr": 4.1582147932648074e-05, "epoch": 2.8, "percentage": 55.77, "elapsed_time": "3:24:38", "remaining_time": "2:42:18", "throughput": 4590.88, "total_tokens": 56371392}
+{"current_steps": 146, "total_steps": 260, "loss": 0.4933, "lr": 4.0987248109304714e-05, "epoch": 2.819512195121951, "percentage": 56.15, "elapsed_time": "3:26:04", "remaining_time": "2:40:54", "throughput": 4590.9, "total_tokens": 56764224}
+{"current_steps": 147, "total_steps": 260, "loss": 0.4847, "lr": 4.039366413231458e-05, "epoch": 2.8390243902439023, "percentage": 56.54, "elapsed_time": "3:27:30", "remaining_time": "2:39:30", "throughput": 4590.91, "total_tokens": 57157056}
+{"current_steps": 148, "total_steps": 260, "loss": 0.492, "lr": 3.980148266392258e-05, "epoch": 2.8585365853658535, "percentage": 56.92, "elapsed_time": "3:28:55", "remaining_time": "2:38:06", "throughput": 4590.93, "total_tokens": 57549888}
+{"current_steps": 149, "total_steps": 260, "loss": 0.4933, "lr": 3.92107901616097e-05, "epoch": 2.8780487804878048, "percentage": 57.31, "elapsed_time": "3:30:21", "remaining_time": "2:36:42", "throughput": 4590.96, "total_tokens": 57942720}
+{"current_steps": 150, "total_steps": 260, "loss": 0.4812, "lr": 3.86216728654705e-05, "epoch": 2.897560975609756, "percentage": 57.69, "elapsed_time": "3:31:46", "remaining_time": "2:35:18", "throughput": 4590.93, "total_tokens": 58335552}
+{"current_steps": 151, "total_steps": 260, "loss": 0.4822, "lr": 3.803421678562213e-05, "epoch": 2.9170731707317072, "percentage": 58.08, "elapsed_time": "3:33:12", "remaining_time": "2:33:54", "throughput": 4590.97, "total_tokens": 58728384}
+{"current_steps": 152, "total_steps": 260, "loss": 0.4814, "lr": 3.744850768964692e-05, "epoch": 2.9365853658536585, "percentage": 58.46, "elapsed_time": "3:34:37", "remaining_time": "2:32:29", "throughput": 4590.99, "total_tokens": 59121216}
+{"current_steps": 153, "total_steps": 260, "loss": 0.4921, "lr": 3.6864631090070655e-05, "epoch": 2.9560975609756097, "percentage": 58.85, "elapsed_time": "3:36:03", "remaining_time": "2:31:05", "throughput": 4591.02, "total_tokens": 59514048}
+{"current_steps": 154, "total_steps": 260, "loss": 0.4768, "lr": 3.628267223187771e-05, "epoch": 2.975609756097561, "percentage": 59.23, "elapsed_time": "3:37:28", "remaining_time": "2:29:41", "throughput": 4591.06, "total_tokens": 59906880}
+{"current_steps": 155, "total_steps": 260, "loss": 0.4579, "lr": 3.570271608006555e-05, "epoch": 2.995121951219512, "percentage": 59.62, "elapsed_time": "3:38:54", "remaining_time": "2:28:17", "throughput": 4591.02, "total_tokens": 60299712}
+{"current_steps": 156, "total_steps": 260, "loss": 0.4418, "lr": 3.512484730723986e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "3:39:15", "remaining_time": "2:26:10", "throughput": 4591.0, "total_tokens": 60397920}
+{"current_steps": 157, "total_steps": 260, "loss": 0.4471, "lr": 3.4549150281252636e-05, "epoch": 3.0195121951219512, "percentage": 60.38, "elapsed_time": "3:40:41", "remaining_time": "2:24:46", "throughput": 4591.01, "total_tokens": 60790752}
+{"current_steps": 158, "total_steps": 260, "loss": 0.4543, "lr": 3.397570905288453e-05, "epoch": 3.0390243902439025, "percentage": 60.77, "elapsed_time": "3:42:06", "remaining_time": "2:23:23", "throughput": 4591.0, "total_tokens": 61183584}
+{"current_steps": 159, "total_steps": 260, "loss": 0.4561, "lr": 3.340460734357359e-05, "epoch": 3.0585365853658537, "percentage": 61.15, "elapsed_time": "3:43:32", "remaining_time": "2:21:59", "throughput": 4591.0, "total_tokens": 61576416}
+{"current_steps": 160, "total_steps": 260, "loss": 0.4521, "lr": 3.283592853319209e-05, "epoch": 3.078048780487805, "percentage": 61.54, "elapsed_time": "3:44:57", "remaining_time": "2:20:36", "throughput": 4591.0, "total_tokens": 61969248}
+{"current_steps": 161, "total_steps": 260, "loss": 0.444, "lr": 3.226975564787322e-05, "epoch": 3.097560975609756, "percentage": 61.92, "elapsed_time": "3:46:23", "remaining_time": "2:19:12", "throughput": 4590.93, "total_tokens": 62362080}
+{"current_steps": 162, "total_steps": 260, "loss": 0.4541, "lr": 3.170617134788939e-05, "epoch": 3.1170731707317074, "percentage": 62.31, "elapsed_time": "3:47:49", "remaining_time": "2:17:49", "throughput": 4590.8, "total_tokens": 62754912}
+{"current_steps": 163, "total_steps": 260, "loss": 0.4582, "lr": 3.114525791558398e-05, "epoch": 3.1365853658536587, "percentage": 62.69, "elapsed_time": "3:49:15", "remaining_time": "2:16:25", "throughput": 4590.82, "total_tokens": 63147744}
+{"current_steps": 164, "total_steps": 260, "loss": 0.4429, "lr": 3.0587097243358253e-05, "epoch": 3.15609756097561, "percentage": 63.08, "elapsed_time": "3:50:40", "remaining_time": "2:15:01", "throughput": 4590.83, "total_tokens": 63540576}
+{"current_steps": 165, "total_steps": 260, "loss": 0.4443, "lr": 3.003177082171523e-05, "epoch": 3.175609756097561, "percentage": 63.46, "elapsed_time": "3:52:06", "remaining_time": "2:13:38", "throughput": 4590.83, "total_tokens": 63933408}
+{"current_steps": 166, "total_steps": 260, "loss": 0.4521, "lr": 2.9479359727362173e-05, "epoch": 3.1951219512195124, "percentage": 63.85, "elapsed_time": "3:53:31", "remaining_time": "2:12:14", "throughput": 4590.81, "total_tokens": 64326240}
+{"current_steps": 167, "total_steps": 260, "loss": 0.4362, "lr": 2.8929944611373554e-05, "epoch": 3.2146341463414636, "percentage": 64.23, "elapsed_time": "3:54:58", "remaining_time": "2:10:51", "throughput": 4590.59, "total_tokens": 64719072}
+{"current_steps": 168, "total_steps": 260, "loss": 0.4503, "lr": 2.8383605687416125e-05, "epoch": 3.234146341463415, "percentage": 64.62, "elapsed_time": "3:56:23", "remaining_time": "2:09:27", "throughput": 4590.61, "total_tokens": 65111904}
+{"current_steps": 169, "total_steps": 260, "loss": 0.448, "lr": 2.784042272003794e-05, "epoch": 3.253658536585366, "percentage": 65.0, "elapsed_time": "3:57:49", "remaining_time": "2:08:03", "throughput": 4590.63, "total_tokens": 65504736}
+{"current_steps": 170, "total_steps": 260, "loss": 0.4495, "lr": 2.7300475013022663e-05, "epoch": 3.2731707317073173, "percentage": 65.38, "elapsed_time": "3:59:14", "remaining_time": "2:06:39", "throughput": 4590.66, "total_tokens": 65897568}
+{"current_steps": 171, "total_steps": 260, "loss": 0.4512, "lr": 2.6763841397811573e-05, "epoch": 3.292682926829268, "percentage": 65.77, "elapsed_time": "4:00:40", "remaining_time": "2:05:15", "throughput": 4590.67, "total_tokens": 66290400}
+{"current_steps": 172, "total_steps": 260, "loss": 0.4342, "lr": 2.6230600221994196e-05, "epoch": 3.3121951219512193, "percentage": 66.15, "elapsed_time": "4:02:05", "remaining_time": "2:03:51", "throughput": 4590.69, "total_tokens": 66683232}
+{"current_steps": 173, "total_steps": 260, "loss": 0.4456, "lr": 2.57008293378697e-05, "epoch": 3.3317073170731706, "percentage": 66.54, "elapsed_time": "4:03:31", "remaining_time": "2:02:27", "throughput": 4590.71, "total_tokens": 67076064}
+{"current_steps": 174, "total_steps": 260, "loss": 0.4459, "lr": 2.5174606091080627e-05, "epoch": 3.351219512195122, "percentage": 66.92, "elapsed_time": "4:04:56", "remaining_time": "2:01:03", "throughput": 4590.73, "total_tokens": 67468896}
+{"current_steps": 175, "total_steps": 260, "loss": 0.4383, "lr": 2.4652007309320498e-05, "epoch": 3.370731707317073, "percentage": 67.31, "elapsed_time": "4:06:22", "remaining_time": "1:59:39", "throughput": 4590.76, "total_tokens": 67861728}
+{"current_steps": 176, "total_steps": 260, "loss": 0.4447, "lr": 2.4133109291117156e-05, "epoch": 3.3902439024390243, "percentage": 67.69, "elapsed_time": "4:07:47", "remaining_time": "1:58:15", "throughput": 4590.8, "total_tokens": 68254560}
+{"current_steps": 177, "total_steps": 260, "loss": 0.442, "lr": 2.361798779469336e-05, "epoch": 3.4097560975609755, "percentage": 68.08, "elapsed_time": "4:09:13", "remaining_time": "1:56:51", "throughput": 4590.83, "total_tokens": 68647392}
+{"current_steps": 178, "total_steps": 260, "loss": 0.4418, "lr": 2.3106718026906072e-05, "epoch": 3.4292682926829268, "percentage": 68.46, "elapsed_time": "4:10:38", "remaining_time": "1:55:27", "throughput": 4590.84, "total_tokens": 69040224}
+{"current_steps": 179, "total_steps": 260, "loss": 0.4325, "lr": 2.259937463226651e-05, "epoch": 3.448780487804878, "percentage": 68.85, "elapsed_time": "4:12:04", "remaining_time": "1:54:03", "throughput": 4590.86, "total_tokens": 69433056}
+{"current_steps": 180, "total_steps": 260, "loss": 0.4319, "lr": 2.209603168204209e-05, "epoch": 3.4682926829268292, "percentage": 69.23, "elapsed_time": "4:13:29", "remaining_time": "1:52:39", "throughput": 4590.87, "total_tokens": 69825888}
+{"current_steps": 181, "total_steps": 260, "loss": 0.4401, "lr": 2.1596762663442218e-05, "epoch": 3.4878048780487805, "percentage": 69.62, "elapsed_time": "4:14:55", "remaining_time": "1:51:15", "throughput": 4590.89, "total_tokens": 70218720}
+{"current_steps": 182, "total_steps": 260, "loss": 0.4386, "lr": 2.1101640468889255e-05, "epoch": 3.5073170731707317, "percentage": 70.0, "elapsed_time": "4:16:20", "remaining_time": "1:49:51", "throughput": 4590.91, "total_tokens": 70611552}
+{"current_steps": 183, "total_steps": 260, "loss": 0.4202, "lr": 2.061073738537635e-05, "epoch": 3.526829268292683, "percentage": 70.38, "elapsed_time": "4:17:46", "remaining_time": "1:48:27", "throughput": 4590.93, "total_tokens": 71004384}
+{"current_steps": 184, "total_steps": 260, "loss": 0.4419, "lr": 2.0124125083913637e-05, "epoch": 3.546341463414634, "percentage": 70.77, "elapsed_time": "4:19:11", "remaining_time": "1:47:03", "throughput": 4590.89, "total_tokens": 71397216}
+{"current_steps": 185, "total_steps": 260, "loss": 0.4336, "lr": 1.9641874609064443e-05, "epoch": 3.5658536585365854, "percentage": 71.15, "elapsed_time": "4:20:37", "remaining_time": "1:45:39", "throughput": 4590.88, "total_tokens": 71790048}
+{"current_steps": 186, "total_steps": 260, "loss": 0.4387, "lr": 1.9164056368572846e-05, "epoch": 3.5853658536585367, "percentage": 71.54, "elapsed_time": "4:22:03", "remaining_time": "1:44:15", "throughput": 4590.84, "total_tokens": 72182880}
+{"current_steps": 187, "total_steps": 260, "loss": 0.4297, "lr": 1.8690740123084316e-05, "epoch": 3.604878048780488, "percentage": 71.92, "elapsed_time": "4:23:28", "remaining_time": "1:42:51", "throughput": 4590.84, "total_tokens": 72575712}
+{"current_steps": 188, "total_steps": 260, "loss": 0.446, "lr": 1.8221994975960736e-05, "epoch": 3.624390243902439, "percentage": 72.31, "elapsed_time": "4:24:54", "remaining_time": "1:41:27", "throughput": 4590.83, "total_tokens": 72968544}
+{"current_steps": 189, "total_steps": 260, "loss": 0.4318, "lr": 1.7757889363191483e-05, "epoch": 3.6439024390243904, "percentage": 72.69, "elapsed_time": "4:26:20", "remaining_time": "1:40:03", "throughput": 4590.81, "total_tokens": 73361376}
+{"current_steps": 190, "total_steps": 260, "loss": 0.4393, "lr": 1.7298491043401795e-05, "epoch": 3.6634146341463416, "percentage": 73.08, "elapsed_time": "4:27:45", "remaining_time": "1:38:38", "throughput": 4590.82, "total_tokens": 73754208}
+{"current_steps": 191, "total_steps": 260, "loss": 0.4437, "lr": 1.684386708796025e-05, "epoch": 3.682926829268293, "percentage": 73.46, "elapsed_time": "4:29:11", "remaining_time": "1:37:14", "throughput": 4590.85, "total_tokens": 74147040}
+{"current_steps": 192, "total_steps": 260, "loss": 0.4378, "lr": 1.6394083871186362e-05, "epoch": 3.7024390243902436, "percentage": 73.85, "elapsed_time": "4:30:36", "remaining_time": "1:35:50", "throughput": 4590.88, "total_tokens": 74539872}
+{"current_steps": 193, "total_steps": 260, "loss": 0.4388, "lr": 1.5949207060660138e-05, "epoch": 3.721951219512195, "percentage": 74.23, "elapsed_time": "4:32:02", "remaining_time": "1:34:26", "throughput": 4590.9, "total_tokens": 74932704}
+{"current_steps": 194, "total_steps": 260, "loss": 0.4483, "lr": 1.550930160763462e-05, "epoch": 3.741463414634146, "percentage": 74.62, "elapsed_time": "4:33:27", "remaining_time": "1:33:01", "throughput": 4590.93, "total_tokens": 75325536}
+{"current_steps": 195, "total_steps": 260, "loss": 0.4336, "lr": 1.5074431737553157e-05, "epoch": 3.7609756097560973, "percentage": 75.0, "elapsed_time": "4:34:52", "remaining_time": "1:31:37", "throughput": 4590.98, "total_tokens": 75718368}
+{"current_steps": 196, "total_steps": 260, "loss": 0.4334, "lr": 1.4644660940672627e-05, "epoch": 3.7804878048780486, "percentage": 75.38, "elapsed_time": "4:36:18", "remaining_time": "1:30:13", "throughput": 4591.02, "total_tokens": 76111200}
+{"current_steps": 197, "total_steps": 260, "loss": 0.4352, "lr": 1.422005196279395e-05, "epoch": 3.8, "percentage": 75.77, "elapsed_time": "4:37:43", "remaining_time": "1:28:49", "throughput": 4591.03, "total_tokens": 76504032}
+{"current_steps": 198, "total_steps": 260, "loss": 0.4315, "lr": 1.3800666796101292e-05, "epoch": 3.819512195121951, "percentage": 76.15, "elapsed_time": "4:39:09", "remaining_time": "1:27:24", "throughput": 4591.05, "total_tokens": 76896864}
+{"current_steps": 199, "total_steps": 260, "loss": 0.4339, "lr": 1.338656667011134e-05, "epoch": 3.8390243902439023, "percentage": 76.54, "elapsed_time": "4:40:34", "remaining_time": "1:26:00", "throughput": 4591.09, "total_tokens": 77289696}
+{"current_steps": 200, "total_steps": 260, "loss": 0.4374, "lr": 1.297781204273385e-05, "epoch": 3.8585365853658535, "percentage": 76.92, "elapsed_time": "4:42:00", "remaining_time": "1:24:36", "throughput": 4591.09, "total_tokens": 77682528}
+{"current_steps": 201, "total_steps": 260, "loss": 0.4437, "lr": 1.257446259144494e-05, "epoch": 3.8780487804878048, "percentage": 77.31, "elapsed_time": "4:43:25", "remaining_time": "1:23:11", "throughput": 4591.09, "total_tokens": 78075360}
+{"current_steps": 202, "total_steps": 260, "loss": 0.4319, "lr": 1.2176577204574318e-05, "epoch": 3.897560975609756, "percentage": 77.69, "elapsed_time": "4:44:51", "remaining_time": "1:21:47", "throughput": 4591.13, "total_tokens": 78468192}
+{"current_steps": 203, "total_steps": 260, "loss": 0.4322, "lr": 1.178421397270758e-05, "epoch": 3.9170731707317072, "percentage": 78.08, "elapsed_time": "4:46:16", "remaining_time": "1:20:23", "throughput": 4591.15, "total_tokens": 78861024}
+{"current_steps": 204, "total_steps": 260, "loss": 0.4375, "lr": 1.1397430180205171e-05, "epoch": 3.9365853658536585, "percentage": 78.46, "elapsed_time": "4:47:42", "remaining_time": "1:18:58", "throughput": 4591.08, "total_tokens": 79253856}
+{"current_steps": 205, "total_steps": 260, "loss": 0.4182, "lr": 1.1016282296838887e-05, "epoch": 3.9560975609756097, "percentage": 78.85, "elapsed_time": "4:49:08", "remaining_time": "1:17:34", "throughput": 4591.11, "total_tokens": 79646688}
+{"current_steps": 206, "total_steps": 260, "loss": 0.4382, "lr": 1.0640825969547496e-05, "epoch": 3.975609756097561, "percentage": 79.23, "elapsed_time": "4:50:33", "remaining_time": "1:16:09", "throughput": 4591.14, "total_tokens": 80039520}
+{"current_steps": 207, "total_steps": 260, "loss": 0.4277, "lr": 1.0271116014312293e-05, "epoch": 3.995121951219512, "percentage": 79.62, "elapsed_time": "4:51:58", "remaining_time": "1:14:45", "throughput": 4591.15, "total_tokens": 80432352}
+{"current_steps": 208, "total_steps": 260, "loss": 0.4029, "lr": 9.90720640815408e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "4:52:20", "remaining_time": "1:13:05", "throughput": 4591.17, "total_tokens": 80530560}
+{"current_steps": 209, "total_steps": 260, "loss": 0.4243, "lr": 9.549150281252633e-06, "epoch": 4.019512195121951, "percentage": 80.38, "elapsed_time": "4:53:45", "remaining_time": "1:11:41", "throughput": 4591.2, "total_tokens": 80923392}
+{"current_steps": 210, "total_steps": 260, "loss": 0.4146, "lr": 9.196999909189762e-06, "epoch": 4.0390243902439025, "percentage": 80.77, "elapsed_time": "4:55:11", "remaining_time": "1:10:17", "throughput": 4591.06, "total_tokens": 81316224}
+{"current_steps": 211, "total_steps": 260, "loss": 0.4287, "lr": 8.850806705317183e-06, "epoch": 4.058536585365854, "percentage": 81.15, "elapsed_time": "4:56:37", "remaining_time": "1:08:53", "throughput": 4591.08, "total_tokens": 81709056}
+{"current_steps": 212, "total_steps": 260, "loss": 0.4221, "lr": 8.510621213250247e-06, "epoch": 4.078048780487805, "percentage": 81.54, "elapsed_time": "4:58:02", "remaining_time": "1:07:28", "throughput": 4591.09, "total_tokens": 82101888}
+{"current_steps": 213, "total_steps": 260, "loss": 0.4232, "lr": 8.176493099488663e-06, "epoch": 4.097560975609756, "percentage": 81.92, "elapsed_time": "4:59:28", "remaining_time": "1:06:04", "throughput": 4591.1, "total_tokens": 82494720}
+{"current_steps": 214, "total_steps": 260, "loss": 0.416, "lr": 7.848471146165288e-06, "epoch": 4.117073170731707, "percentage": 82.31, "elapsed_time": "5:00:53", "remaining_time": "1:04:40", "throughput": 4591.1, "total_tokens": 82887552}
+{"current_steps": 215, "total_steps": 260, "loss": 0.4157, "lr": 7.526603243923957e-06, "epoch": 4.136585365853659, "percentage": 82.69, "elapsed_time": "5:02:19", "remaining_time": "1:03:16", "throughput": 4591.08, "total_tokens": 83280384}
+{"current_steps": 216, "total_steps": 260, "loss": 0.4174, "lr": 7.21093638492763e-06, "epoch": 4.15609756097561, "percentage": 83.08, "elapsed_time": "5:03:45", "remaining_time": "1:01:52", "throughput": 4591.06, "total_tokens": 83673216}
+{"current_steps": 217, "total_steps": 260, "loss": 0.4041, "lr": 6.901516655997536e-06, "epoch": 4.175609756097561, "percentage": 83.46, "elapsed_time": "5:05:10", "remaining_time": "1:00:28", "throughput": 4591.04, "total_tokens": 84066048}
+{"current_steps": 218, "total_steps": 260, "loss": 0.4155, "lr": 6.5983892318846275e-06, "epoch": 4.195121951219512, "percentage": 83.85, "elapsed_time": "5:06:36", "remaining_time": "0:59:04", "throughput": 4591.02, "total_tokens": 84458880}
+{"current_steps": 219, "total_steps": 260, "loss": 0.4214, "lr": 6.301598368674105e-06, "epoch": 4.214634146341464, "percentage": 84.23, "elapsed_time": "5:08:02", "remaining_time": "0:57:40", "throughput": 4591.01, "total_tokens": 84851712}
+{"current_steps": 220, "total_steps": 260, "loss": 0.4193, "lr": 6.011187397324114e-06, "epoch": 4.234146341463415, "percentage": 84.62, "elapsed_time": "5:09:27", "remaining_time": "0:56:15", "throughput": 4591.0, "total_tokens": 85244544}
+{"current_steps": 221, "total_steps": 260, "loss": 0.4137, "lr": 5.727198717339511e-06, "epoch": 4.253658536585366, "percentage": 85.0, "elapsed_time": "5:10:53", "remaining_time": "0:54:51", "throughput": 4590.97, "total_tokens": 85637376}
+{"current_steps": 222, "total_steps": 260, "loss": 0.4069, "lr": 5.449673790581611e-06, "epoch": 4.273170731707317, "percentage": 85.38, "elapsed_time": "5:12:19", "remaining_time": "0:53:27", "throughput": 4590.93, "total_tokens": 86030208}
+{"current_steps": 223, "total_steps": 260, "loss": 0.4188, "lr": 5.178653135214812e-06, "epoch": 4.2926829268292686, "percentage": 85.77, "elapsed_time": "5:13:44", "remaining_time": "0:52:03", "throughput": 4590.91, "total_tokens": 86423040}
+{"current_steps": 224, "total_steps": 260, "loss": 0.4133, "lr": 4.914176319791036e-06, "epoch": 4.31219512195122, "percentage": 86.15, "elapsed_time": "5:15:10", "remaining_time": "0:50:39", "throughput": 4590.88, "total_tokens": 86815872}
+{"current_steps": 225, "total_steps": 260, "loss": 0.4136, "lr": 4.65628195747273e-06, "epoch": 4.331707317073171, "percentage": 86.54, "elapsed_time": "5:16:36", "remaining_time": "0:49:14", "throughput": 4590.84, "total_tokens": 87208704}
+{"current_steps": 226, "total_steps": 260, "loss": 0.4066, "lr": 4.405007700395497e-06, "epoch": 4.351219512195122, "percentage": 86.92, "elapsed_time": "5:18:01", "remaining_time": "0:47:50", "throughput": 4590.8, "total_tokens": 87601536}
+{"current_steps": 227, "total_steps": 260, "loss": 0.4002, "lr": 4.16039023417088e-06, "epoch": 4.3707317073170735, "percentage": 87.31, "elapsed_time": "5:19:27", "remaining_time": "0:46:26", "throughput": 4590.77, "total_tokens": 87994368}
+{"current_steps": 228, "total_steps": 260, "loss": 0.4213, "lr": 3.922465272530351e-06, "epoch": 4.390243902439025, "percentage": 87.69, "elapsed_time": "5:20:53", "remaining_time": "0:45:02", "throughput": 4590.69, "total_tokens": 88387200}
+{"current_steps": 229, "total_steps": 260, "loss": 0.4276, "lr": 3.691267552111183e-06, "epoch": 4.409756097560976, "percentage": 88.08, "elapsed_time": "5:22:19", "remaining_time": "0:43:37", "throughput": 4590.66, "total_tokens": 88780032}
+{"current_steps": 230, "total_steps": 260, "loss": 0.417, "lr": 3.4668308273848982e-06, "epoch": 4.429268292682927, "percentage": 88.46, "elapsed_time": "5:23:44", "remaining_time": "0:42:13", "throughput": 4590.64, "total_tokens": 89172864}
+{"current_steps": 231, "total_steps": 260, "loss": 0.4036, "lr": 3.249187865729264e-06, "epoch": 4.4487804878048784, "percentage": 88.85, "elapsed_time": "5:25:10", "remaining_time": "0:40:49", "throughput": 4590.63, "total_tokens": 89565696}
+{"current_steps": 232, "total_steps": 260, "loss": 0.4109, "lr": 3.0383704426442394e-06, "epoch": 4.46829268292683, "percentage": 89.23, "elapsed_time": "5:26:36", "remaining_time": "0:39:25", "throughput": 4590.61, "total_tokens": 89958528}
+{"current_steps": 233, "total_steps": 260, "loss": 0.4177, "lr": 2.8344093371128424e-06, "epoch": 4.487804878048781, "percentage": 89.62, "elapsed_time": "5:28:01", "remaining_time": "0:38:00", "throughput": 4590.59, "total_tokens": 90351360}
+{"current_steps": 234, "total_steps": 260, "loss": 0.4167, "lr": 2.637334327107466e-06, "epoch": 4.507317073170732, "percentage": 90.0, "elapsed_time": "5:29:27", "remaining_time": "0:36:36", "throughput": 4590.59, "total_tokens": 90744192}
+{"current_steps": 235, "total_steps": 260, "loss": 0.4214, "lr": 2.4471741852423237e-06, "epoch": 4.526829268292683, "percentage": 90.38, "elapsed_time": "5:30:52", "remaining_time": "0:35:12", "throughput": 4590.6, "total_tokens": 91137024}
+{"current_steps": 236, "total_steps": 260, "loss": 0.4038, "lr": 2.2639566745727205e-06, "epoch": 4.546341463414635, "percentage": 90.77, "elapsed_time": "5:32:18", "remaining_time": "0:33:47", "throughput": 4590.59, "total_tokens": 91529856}
+{"current_steps": 237, "total_steps": 260, "loss": 0.4087, "lr": 2.087708544541689e-06, "epoch": 4.565853658536585, "percentage": 91.15, "elapsed_time": "5:33:44", "remaining_time": "0:32:23", "throughput": 4590.59, "total_tokens": 91922688}
+{"current_steps": 238, "total_steps": 260, "loss": 0.4099, "lr": 1.9184555270746194e-06, "epoch": 4.585365853658536, "percentage": 91.54, "elapsed_time": "5:35:09", "remaining_time": "0:30:58", "throughput": 4590.59, "total_tokens": 92315520}
+{"current_steps": 239, "total_steps": 260, "loss": 0.4098, "lr": 1.7562223328224325e-06, "epoch": 4.6048780487804875, "percentage": 91.92, "elapsed_time": "5:36:35", "remaining_time": "0:29:34", "throughput": 4590.59, "total_tokens": 92708352}
+{"current_steps": 240, "total_steps": 260, "loss": 0.4106, "lr": 1.601032647553863e-06, "epoch": 4.624390243902439, "percentage": 92.31, "elapsed_time": "5:38:00", "remaining_time": "0:28:10", "throughput": 4590.58, "total_tokens": 93101184}
+{"current_steps": 241, "total_steps": 260, "loss": 0.4204, "lr": 1.4529091286973995e-06, "epoch": 4.64390243902439, "percentage": 92.69, "elapsed_time": "5:39:26", "remaining_time": "0:26:45", "throughput": 4590.58, "total_tokens": 93494016}
+{"current_steps": 242, "total_steps": 260, "loss": 0.4069, "lr": 1.3118734020333256e-06, "epoch": 4.663414634146341, "percentage": 93.08, "elapsed_time": "5:40:52", "remaining_time": "0:25:21", "throughput": 4590.57, "total_tokens": 93886848}
+{"current_steps": 243, "total_steps": 260, "loss": 0.4206, "lr": 1.1779460585363944e-06, "epoch": 4.682926829268292, "percentage": 93.46, "elapsed_time": "5:42:17", "remaining_time": "0:23:56", "throughput": 4590.59, "total_tokens": 94279680}
+{"current_steps": 244, "total_steps": 260, "loss": 0.4216, "lr": 1.0511466513695777e-06, "epoch": 4.702439024390244, "percentage": 93.85, "elapsed_time": "5:43:43", "remaining_time": "0:22:32", "throughput": 4590.59, "total_tokens": 94672512}
+{"current_steps": 245, "total_steps": 260, "loss": 0.4067, "lr": 9.314936930293283e-07, "epoch": 4.721951219512195, "percentage": 94.23, "elapsed_time": "5:45:09", "remaining_time": "0:21:07", "throughput": 4590.49, "total_tokens": 95065344}
+{"current_steps": 246, "total_steps": 260, "loss": 0.4149, "lr": 8.190046526428242e-07, "epoch": 4.741463414634146, "percentage": 94.62, "elapsed_time": "5:46:34", "remaining_time": "0:19:43", "throughput": 4590.45, "total_tokens": 95458176}
+{"current_steps": 247, "total_steps": 260, "loss": 0.4104, "lr": 7.136959534174592e-07, "epoch": 4.760975609756097, "percentage": 95.0, "elapsed_time": "5:48:00", "remaining_time": "0:18:18", "throughput": 4590.43, "total_tokens": 95851008}
+{"current_steps": 248, "total_steps": 260, "loss": 0.4275, "lr": 6.15582970243117e-07, "epoch": 4.780487804878049, "percentage": 95.38, "elapsed_time": "5:49:26", "remaining_time": "0:16:54", "throughput": 4590.4, "total_tokens": 96243840}
+{"current_steps": 249, "total_steps": 260, "loss": 0.4168, "lr": 5.246800274474439e-07, "epoch": 4.8, "percentage": 95.77, "elapsed_time": "5:50:52", "remaining_time": "0:15:30", "throughput": 4590.37, "total_tokens": 96636672}
+{"current_steps": 250, "total_steps": 260, "loss": 0.4227, "lr": 4.4100039670454395e-07, "epoch": 4.819512195121951, "percentage": 96.15, "elapsed_time": "5:52:17", "remaining_time": "0:14:05", "throughput": 4590.32, "total_tokens": 97029504}
+{"current_steps": 251, "total_steps": 260, "loss": 0.4224, "lr": 3.6455629509730136e-07, "epoch": 4.839024390243902, "percentage": 96.54, "elapsed_time": "5:53:43", "remaining_time": "0:12:41", "throughput": 4590.27, "total_tokens": 97422336}
+{"current_steps": 252, "total_steps": 260, "loss": 0.409, "lr": 2.953588833337406e-07, "epoch": 4.8585365853658535, "percentage": 96.92, "elapsed_time": "5:55:09", "remaining_time": "0:11:16", "throughput": 4590.16, "total_tokens": 97815168}
+{"current_steps": 253, "total_steps": 260, "loss": 0.4164, "lr": 2.334182641175686e-07, "epoch": 4.878048780487805, "percentage": 97.31, "elapsed_time": "5:56:35", "remaining_time": "0:09:51", "throughput": 4590.1, "total_tokens": 98208000}
+{"current_steps": 254, "total_steps": 260, "loss": 0.4048, "lr": 1.7874348067319912e-07, "epoch": 4.897560975609756, "percentage": 97.69, "elapsed_time": "5:58:01", "remaining_time": "0:08:27", "throughput": 4590.07, "total_tokens": 98600832}
+{"current_steps": 255, "total_steps": 260, "loss": 0.4082, "lr": 1.3134251542544774e-07, "epoch": 4.917073170731707, "percentage": 98.08, "elapsed_time": "5:59:27", "remaining_time": "0:07:02", "throughput": 4590.03, "total_tokens": 98993664}
+{"current_steps": 256, "total_steps": 260, "loss": 0.4214, "lr": 9.12222888341252e-08, "epoch": 4.9365853658536585, "percentage": 98.46, "elapsed_time": "6:00:52", "remaining_time": "0:05:38", "throughput": 4590.01, "total_tokens": 99386496}
+{"current_steps": 257, "total_steps": 260, "loss": 0.413, "lr": 5.838865838366792e-08, "epoch": 4.95609756097561, "percentage": 98.85, "elapsed_time": "6:02:18", "remaining_time": "0:04:13", "throughput": 4589.97, "total_tokens": 99779328}
+{"current_steps": 258, "total_steps": 260, "loss": 0.4118, "lr": 3.284641772793862e-08, "epoch": 4.975609756097561, "percentage": 99.23, "elapsed_time": "6:03:44", "remaining_time": "0:02:49", "throughput": 4589.92, "total_tokens": 100172160}
+{"current_steps": 259, "total_steps": 260, "loss": 0.4169, "lr": 1.4599295990352924e-08, "epoch": 4.995121951219512, "percentage": 99.62, "elapsed_time": "6:05:10", "remaining_time": "0:01:24", "throughput": 4589.9, "total_tokens": 100564992}
+{"current_steps": 260, "total_steps": 260, "loss": 0.3937, "lr": 3.6499572194648167e-09, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "6:05:31", "remaining_time": "0:00:00", "throughput": 4589.89, "total_tokens": 100663200}
+{"current_steps": 260, "total_steps": 260, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "6:06:47", "remaining_time": "0:00:00", "throughput": 4574.14, "total_tokens": 100663200}

trainer_state.json

@@ -0,0 +1,2644 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01951219512195122,
+      "grad_norm": 0.15858030701789594,
+      "learning_rate": 0.0001,
+      "loss": 1.9481,
+      "num_input_tokens_seen": 392832,
+      "step": 1,
+      "train_runtime": 90.5356,
+      "train_tokens_per_second": 4338.977
+    },
+    {
+      "epoch": 0.03902439024390244,
+      "grad_norm": 0.20614269950817926,
+      "learning_rate": 9.999635004278054e-05,
+      "loss": 1.9426,
+      "num_input_tokens_seen": 785664,
+      "step": 2,
+      "train_runtime": 176.3121,
+      "train_tokens_per_second": 4456.097
+    },
+    {
+      "epoch": 0.05853658536585366,
+      "grad_norm": 0.11931287845406353,
+      "learning_rate": 9.998540070400966e-05,
+      "loss": 1.8808,
+      "num_input_tokens_seen": 1178496,
+      "step": 3,
+      "train_runtime": 261.8343,
+      "train_tokens_per_second": 4500.924
+    },
+    {
+      "epoch": 0.07804878048780488,
+      "grad_norm": 0.1061877717922271,
+      "learning_rate": 9.996715358227206e-05,
+      "loss": 1.8827,
+      "num_input_tokens_seen": 1571328,
+      "step": 4,
+      "train_runtime": 347.2723,
+      "train_tokens_per_second": 4524.772
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.2303512070226615,
+      "learning_rate": 9.994161134161634e-05,
+      "loss": 1.8196,
+      "num_input_tokens_seen": 1964160,
+      "step": 5,
+      "train_runtime": 432.7972,
+      "train_tokens_per_second": 4538.292
+    },
+    {
+      "epoch": 0.11707317073170732,
+      "grad_norm": 0.10282606368495031,
+      "learning_rate": 9.990877771116589e-05,
+      "loss": 1.7928,
+      "num_input_tokens_seen": 2356992,
+      "step": 6,
+      "train_runtime": 518.285,
+      "train_tokens_per_second": 4547.676
+    },
+    {
+      "epoch": 0.13658536585365855,
+      "grad_norm": 0.09334879403165187,
+      "learning_rate": 9.986865748457457e-05,
+      "loss": 1.7726,
+      "num_input_tokens_seen": 2749824,
+      "step": 7,
+      "train_runtime": 603.8579,
+      "train_tokens_per_second": 4553.76
+    },
+    {
+      "epoch": 0.15609756097560976,
+      "grad_norm": 0.08922352642855319,
+      "learning_rate": 9.982125651932681e-05,
+      "loss": 1.7569,
+      "num_input_tokens_seen": 3142656,
+      "step": 8,
+      "train_runtime": 689.4943,
+      "train_tokens_per_second": 4557.915
+    },
+    {
+      "epoch": 0.17560975609756097,
+      "grad_norm": 0.08017329983520603,
+      "learning_rate": 9.976658173588244e-05,
+      "loss": 1.7263,
+      "num_input_tokens_seen": 3535488,
+      "step": 9,
+      "train_runtime": 775.2129,
+      "train_tokens_per_second": 4560.667
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.09081767257053708,
+      "learning_rate": 9.970464111666626e-05,
+      "loss": 1.7278,
+      "num_input_tokens_seen": 3928320,
+      "step": 10,
+      "train_runtime": 860.7493,
+      "train_tokens_per_second": 4563.837
+    },
+    {
+      "epoch": 0.2146341463414634,
+      "grad_norm": 0.09473566656122094,
+      "learning_rate": 9.96354437049027e-05,
+      "loss": 1.719,
+      "num_input_tokens_seen": 4321152,
+      "step": 11,
+      "train_runtime": 946.3458,
+      "train_tokens_per_second": 4566.145
+    },
+    {
+      "epoch": 0.23414634146341465,
+      "grad_norm": 0.09855985009583386,
+      "learning_rate": 9.955899960329547e-05,
+      "loss": 1.6873,
+      "num_input_tokens_seen": 4713984,
+      "step": 12,
+      "train_runtime": 1031.9306,
+      "train_tokens_per_second": 4568.121
+    },
+    {
+      "epoch": 0.25365853658536586,
+      "grad_norm": 0.08976785941545291,
+      "learning_rate": 9.947531997255256e-05,
+      "loss": 1.6583,
+      "num_input_tokens_seen": 5106816,
+      "step": 13,
+      "train_runtime": 1117.6812,
+      "train_tokens_per_second": 4569.117
+    },
+    {
+      "epoch": 0.2731707317073171,
+      "grad_norm": 0.13069965458083008,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 1.6484,
+      "num_input_tokens_seen": 5499648,
+      "step": 14,
+      "train_runtime": 1203.3824,
+      "train_tokens_per_second": 4570.158
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.09614160184332628,
+      "learning_rate": 9.928630404658255e-05,
+      "loss": 1.6392,
+      "num_input_tokens_seen": 5892480,
+      "step": 15,
+      "train_runtime": 1288.9765,
+      "train_tokens_per_second": 4571.441
+    },
+    {
+      "epoch": 0.3121951219512195,
+      "grad_norm": 0.11451137531983133,
+      "learning_rate": 9.918099534735718e-05,
+      "loss": 1.6079,
+      "num_input_tokens_seen": 6285312,
+      "step": 16,
+      "train_runtime": 1374.5203,
+      "train_tokens_per_second": 4572.731
+    },
+    {
+      "epoch": 0.33170731707317075,
+      "grad_norm": 0.1000369686921647,
+      "learning_rate": 9.906850630697068e-05,
+      "loss": 1.614,
+      "num_input_tokens_seen": 6678144,
+      "step": 17,
+      "train_runtime": 1460.267,
+      "train_tokens_per_second": 4573.235
+    },
+    {
+      "epoch": 0.35121951219512193,
+      "grad_norm": 0.11186890632545277,
+      "learning_rate": 9.894885334863044e-05,
+      "loss": 1.5871,
+      "num_input_tokens_seen": 7070976,
+      "step": 18,
+      "train_runtime": 1545.8916,
+      "train_tokens_per_second": 4574.044
+    },
+    {
+      "epoch": 0.37073170731707317,
+      "grad_norm": 0.12930001237850156,
+      "learning_rate": 9.882205394146361e-05,
+      "loss": 1.5864,
+      "num_input_tokens_seen": 7463808,
+      "step": 19,
+      "train_runtime": 1631.4769,
+      "train_tokens_per_second": 4574.878
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.11111621443548497,
+      "learning_rate": 9.868812659796668e-05,
+      "loss": 1.547,
+      "num_input_tokens_seen": 7856640,
+      "step": 20,
+      "train_runtime": 1717.1186,
+      "train_tokens_per_second": 4575.479
+    },
+    {
+      "epoch": 0.4097560975609756,
+      "grad_norm": 0.10197780896100014,
+      "learning_rate": 9.85470908713026e-05,
+      "loss": 1.5349,
+      "num_input_tokens_seen": 8249472,
+      "step": 21,
+      "train_runtime": 1802.6996,
+      "train_tokens_per_second": 4576.177
+    },
+    {
+      "epoch": 0.4292682926829268,
+      "grad_norm": 0.11362815005489417,
+      "learning_rate": 9.839896735244614e-05,
+      "loss": 1.5123,
+      "num_input_tokens_seen": 8642304,
+      "step": 22,
+      "train_runtime": 1888.2112,
+      "train_tokens_per_second": 4576.98
+    },
+    {
+      "epoch": 0.44878048780487806,
+      "grad_norm": 0.5028658075504846,
+      "learning_rate": 9.824377766717759e-05,
+      "loss": 1.4901,
+      "num_input_tokens_seen": 9035136,
+      "step": 23,
+      "train_runtime": 1973.7336,
+      "train_tokens_per_second": 4577.688
+    },
+    {
+      "epoch": 0.4682926829268293,
+      "grad_norm": 0.12820339687555396,
+      "learning_rate": 9.808154447292539e-05,
+      "loss": 1.4924,
+      "num_input_tokens_seen": 9427968,
+      "step": 24,
+      "train_runtime": 2059.3532,
+      "train_tokens_per_second": 4578.121
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.13588084054069685,
+      "learning_rate": 9.791229145545831e-05,
+      "loss": 1.4489,
+      "num_input_tokens_seen": 9820800,
+      "step": 25,
+      "train_runtime": 2145.0524,
+      "train_tokens_per_second": 4578.35
+    },
+    {
+      "epoch": 0.5073170731707317,
+      "grad_norm": 0.13132153795044452,
+      "learning_rate": 9.773604332542729e-05,
+      "loss": 1.4188,
+      "num_input_tokens_seen": 10213632,
+      "step": 26,
+      "train_runtime": 2230.6879,
+      "train_tokens_per_second": 4578.692
+    },
+    {
+      "epoch": 0.526829268292683,
+      "grad_norm": 0.13496880260647526,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.4272,
+      "num_input_tokens_seen": 10606464,
+      "step": 27,
+      "train_runtime": 2316.1437,
+      "train_tokens_per_second": 4579.364
+    },
+    {
+      "epoch": 0.5463414634146342,
+      "grad_norm": 0.14799450429263764,
+      "learning_rate": 9.736266567289253e-05,
+      "loss": 1.3815,
+      "num_input_tokens_seen": 10999296,
+      "step": 28,
+      "train_runtime": 2401.7043,
+      "train_tokens_per_second": 4579.788
+    },
+    {
+      "epoch": 0.5658536585365853,
+      "grad_norm": 0.32782733922481533,
+      "learning_rate": 9.716559066288715e-05,
+      "loss": 1.3752,
+      "num_input_tokens_seen": 11392128,
+      "step": 29,
+      "train_runtime": 2487.3215,
+      "train_tokens_per_second": 4580.079
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.1534924395682076,
+      "learning_rate": 9.696162955735577e-05,
+      "loss": 1.3629,
+      "num_input_tokens_seen": 11784960,
+      "step": 30,
+      "train_runtime": 2572.9464,
+      "train_tokens_per_second": 4580.336
+    },
+    {
+      "epoch": 0.6048780487804878,
+      "grad_norm": 0.23747387980155885,
+      "learning_rate": 9.675081213427076e-05,
+      "loss": 1.3163,
+      "num_input_tokens_seen": 12177792,
+      "step": 31,
+      "train_runtime": 2658.4902,
+      "train_tokens_per_second": 4580.717
+    },
+    {
+      "epoch": 0.624390243902439,
+      "grad_norm": 0.1724017252468989,
+      "learning_rate": 9.653316917261512e-05,
+      "loss": 1.3058,
+      "num_input_tokens_seen": 12570624,
+      "step": 32,
+      "train_runtime": 2743.9643,
+      "train_tokens_per_second": 4581.191
+    },
+    {
+      "epoch": 0.6439024390243903,
+      "grad_norm": 0.1619965153711787,
+      "learning_rate": 9.630873244788883e-05,
+      "loss": 1.2774,
+      "num_input_tokens_seen": 12963456,
+      "step": 33,
+      "train_runtime": 2829.4055,
+      "train_tokens_per_second": 4581.689
+    },
+    {
+      "epoch": 0.6634146341463415,
+      "grad_norm": 0.18133620259351485,
+      "learning_rate": 9.607753472746966e-05,
+      "loss": 1.2585,
+      "num_input_tokens_seen": 13356288,
+      "step": 34,
+      "train_runtime": 2914.8292,
+      "train_tokens_per_second": 4582.185
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 0.20121493987838818,
+      "learning_rate": 9.583960976582913e-05,
+      "loss": 1.2429,
+      "num_input_tokens_seen": 13749120,
+      "step": 35,
+      "train_runtime": 3000.3011,
+      "train_tokens_per_second": 4582.58
+    },
+    {
+      "epoch": 0.7024390243902439,
+      "grad_norm": 0.2485985257238104,
+      "learning_rate": 9.559499229960451e-05,
+      "loss": 1.2092,
+      "num_input_tokens_seen": 14141952,
+      "step": 36,
+      "train_runtime": 3085.8763,
+      "train_tokens_per_second": 4582.799
+    },
+    {
+      "epoch": 0.7219512195121951,
+      "grad_norm": 0.24323454189307991,
+      "learning_rate": 9.534371804252728e-05,
+      "loss": 1.1789,
+      "num_input_tokens_seen": 14534784,
+      "step": 37,
+      "train_runtime": 3171.7531,
+      "train_tokens_per_second": 4582.571
+    },
+    {
+      "epoch": 0.7414634146341463,
+      "grad_norm": 0.34801979161039454,
+      "learning_rate": 9.508582368020897e-05,
+      "loss": 1.1495,
+      "num_input_tokens_seen": 14927616,
+      "step": 38,
+      "train_runtime": 3257.3777,
+      "train_tokens_per_second": 4582.71
+    },
+    {
+      "epoch": 0.7609756097560976,
+      "grad_norm": 0.6127611336291061,
+      "learning_rate": 9.482134686478519e-05,
+      "loss": 1.141,
+      "num_input_tokens_seen": 15320448,
+      "step": 39,
+      "train_runtime": 3342.782,
+      "train_tokens_per_second": 4583.143
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.6420115225722821,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 1.1236,
+      "num_input_tokens_seen": 15713280,
+      "step": 40,
+      "train_runtime": 3428.2665,
+      "train_tokens_per_second": 4583.448
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.28502804596451176,
+      "learning_rate": 9.42728012826605e-05,
+      "loss": 1.1034,
+      "num_input_tokens_seen": 16106112,
+      "step": 41,
+      "train_runtime": 3513.7978,
+      "train_tokens_per_second": 4583.676
+    },
+    {
+      "epoch": 0.8195121951219512,
+      "grad_norm": 0.716313084661846,
+      "learning_rate": 9.398881260267589e-05,
+      "loss": 1.1052,
+      "num_input_tokens_seen": 16498944,
+      "step": 42,
+      "train_runtime": 3599.2462,
+      "train_tokens_per_second": 4584.0
+    },
+    {
+      "epoch": 0.8390243902439024,
+      "grad_norm": 0.3220303313208368,
+      "learning_rate": 9.36984016313259e-05,
+      "loss": 1.0595,
+      "num_input_tokens_seen": 16891776,
+      "step": 43,
+      "train_runtime": 3684.6336,
+      "train_tokens_per_second": 4584.384
+    },
+    {
+      "epoch": 0.8585365853658536,
+      "grad_norm": 0.46297801425335283,
+      "learning_rate": 9.340161076811537e-05,
+      "loss": 1.0507,
+      "num_input_tokens_seen": 17284608,
+      "step": 44,
+      "train_runtime": 3770.0588,
+      "train_tokens_per_second": 4584.705
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.3229025177696428,
+      "learning_rate": 9.309848334400246e-05,
+      "loss": 1.0204,
+      "num_input_tokens_seen": 17677440,
+      "step": 45,
+      "train_runtime": 3855.5127,
+      "train_tokens_per_second": 4584.978
+    },
+    {
+      "epoch": 0.8975609756097561,
+      "grad_norm": 0.4974629296010873,
+      "learning_rate": 9.278906361507238e-05,
+      "loss": 1.0275,
+      "num_input_tokens_seen": 18070272,
+      "step": 46,
+      "train_runtime": 3940.8899,
+      "train_tokens_per_second": 4585.328
+    },
+    {
+      "epoch": 0.9170731707317074,
+      "grad_norm": 0.3252828591259486,
+      "learning_rate": 9.247339675607605e-05,
+      "loss": 0.9942,
+      "num_input_tokens_seen": 18463104,
+      "step": 47,
+      "train_runtime": 4026.4826,
+      "train_tokens_per_second": 4585.418
+    },
+    {
+      "epoch": 0.9365853658536586,
+      "grad_norm": 0.4096451495593207,
+      "learning_rate": 9.215152885383474e-05,
+      "loss": 0.9636,
+      "num_input_tokens_seen": 18855936,
+      "step": 48,
+      "train_runtime": 4111.9693,
+      "train_tokens_per_second": 4585.622
+    },
+    {
+      "epoch": 0.9560975609756097,
+      "grad_norm": 0.34175853473817397,
+      "learning_rate": 9.182350690051133e-05,
+      "loss": 0.9595,
+      "num_input_tokens_seen": 19248768,
+      "step": 49,
+      "train_runtime": 4197.3817,
+      "train_tokens_per_second": 4585.899
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.7544878577908084,
+      "learning_rate": 9.148937878674976e-05,
+      "loss": 0.9406,
+      "num_input_tokens_seen": 19641600,
+      "step": 50,
+      "train_runtime": 4282.7892,
+      "train_tokens_per_second": 4586.17
+    },
+    {
+      "epoch": 0.9951219512195122,
+      "grad_norm": 0.45005702668900516,
+      "learning_rate": 9.114919329468282e-05,
+      "loss": 0.9266,
+      "num_input_tokens_seen": 20034432,
+      "step": 51,
+      "train_runtime": 4368.202,
+      "train_tokens_per_second": 4586.425
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5681712533129535,
+      "learning_rate": 9.080300009081024e-05,
+      "loss": 0.9145,
+      "num_input_tokens_seen": 20132640,
+      "step": 52,
+      "train_runtime": 4389.6005,
+      "train_tokens_per_second": 4586.44
+    },
+    {
+      "epoch": 1.0195121951219512,
+      "grad_norm": 0.5035806305267847,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.8835,
+      "num_input_tokens_seen": 20525472,
+      "step": 53,
+      "train_runtime": 4475.0972,
+      "train_tokens_per_second": 4586.598
+    },
+    {
+      "epoch": 1.0390243902439025,
+      "grad_norm": 1.5437125934865135,
+      "learning_rate": 9.009279359184593e-05,
+      "loss": 0.8894,
+      "num_input_tokens_seen": 20918304,
+      "step": 54,
+      "train_runtime": 4560.5362,
+      "train_tokens_per_second": 4586.808
+    },
+    {
+      "epoch": 1.0585365853658537,
+      "grad_norm": 2.5544072695829527,
+      "learning_rate": 8.972888398568772e-05,
+      "loss": 0.8801,
+      "num_input_tokens_seen": 21311136,
+      "step": 55,
+      "train_runtime": 4646.0135,
+      "train_tokens_per_second": 4586.972
+    },
+    {
+      "epoch": 1.078048780487805,
+      "grad_norm": 6.413568180777226,
+      "learning_rate": 8.935917403045251e-05,
+      "loss": 0.8761,
+      "num_input_tokens_seen": 21703968,
+      "step": 56,
+      "train_runtime": 4731.4435,
+      "train_tokens_per_second": 4587.177
+    },
+    {
+      "epoch": 1.0975609756097562,
+      "grad_norm": 3.6652053687664377,
+      "learning_rate": 8.898371770316111e-05,
+      "loss": 0.8785,
+      "num_input_tokens_seen": 22096800,
+      "step": 57,
+      "train_runtime": 4816.8429,
+      "train_tokens_per_second": 4587.403
+    },
+    {
+      "epoch": 1.1170731707317074,
+      "grad_norm": 2.350713418610044,
+      "learning_rate": 8.860256981979484e-05,
+      "loss": 0.8964,
+      "num_input_tokens_seen": 22489632,
+      "step": 58,
+      "train_runtime": 4902.2866,
+      "train_tokens_per_second": 4587.58
+    },
+    {
+      "epoch": 1.1365853658536587,
+      "grad_norm": 1.458077107848317,
+      "learning_rate": 8.821578602729242e-05,
+      "loss": 0.8833,
+      "num_input_tokens_seen": 22882464,
+      "step": 59,
+      "train_runtime": 4987.6858,
+      "train_tokens_per_second": 4587.792
+    },
+    {
+      "epoch": 1.1560975609756097,
+      "grad_norm": 2.3627094246816553,
+      "learning_rate": 8.782342279542568e-05,
+      "loss": 0.8698,
+      "num_input_tokens_seen": 23275296,
+      "step": 60,
+      "train_runtime": 5073.0959,
+      "train_tokens_per_second": 4587.987
+    },
+    {
+      "epoch": 1.175609756097561,
+      "grad_norm": 1.3869190096740975,
+      "learning_rate": 8.742553740855506e-05,
+      "loss": 0.864,
+      "num_input_tokens_seen": 23668128,
+      "step": 61,
+      "train_runtime": 5158.4893,
+      "train_tokens_per_second": 4588.19
+    },
+    {
+      "epoch": 1.1951219512195121,
+      "grad_norm": 1.1437940013985328,
+      "learning_rate": 8.702218795726617e-05,
+      "loss": 0.8551,
+      "num_input_tokens_seen": 24060960,
+      "step": 62,
+      "train_runtime": 5243.865,
+      "train_tokens_per_second": 4588.402
+    },
+    {
+      "epoch": 1.2146341463414634,
+      "grad_norm": 2.801137587074987,
+      "learning_rate": 8.661343332988869e-05,
+      "loss": 0.8327,
+      "num_input_tokens_seen": 24453792,
+      "step": 63,
+      "train_runtime": 5329.3228,
+      "train_tokens_per_second": 4588.536
+    },
+    {
+      "epoch": 1.2341463414634146,
+      "grad_norm": 1.1087446235917915,
+      "learning_rate": 8.619933320389872e-05,
+      "loss": 0.8003,
+      "num_input_tokens_seen": 24846624,
+      "step": 64,
+      "train_runtime": 5414.7776,
+      "train_tokens_per_second": 4588.669
+    },
+    {
+      "epoch": 1.2536585365853659,
+      "grad_norm": 1.1639583727147402,
+      "learning_rate": 8.577994803720606e-05,
+      "loss": 0.8078,
+      "num_input_tokens_seen": 25239456,
+      "step": 65,
+      "train_runtime": 5500.2413,
+      "train_tokens_per_second": 4588.791
+    },
+    {
+      "epoch": 1.273170731707317,
+      "grad_norm": 0.8450850350334035,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8033,
+      "num_input_tokens_seen": 25632288,
+      "step": 66,
+      "train_runtime": 5585.6797,
+      "train_tokens_per_second": 4588.929
+    },
+    {
+      "epoch": 1.2926829268292683,
+      "grad_norm": 4.138498725123297,
+      "learning_rate": 8.492556826244687e-05,
+      "loss": 0.7751,
+      "num_input_tokens_seen": 26025120,
+      "step": 67,
+      "train_runtime": 5671.0727,
+      "train_tokens_per_second": 4589.1
+    },
+    {
+      "epoch": 1.3121951219512196,
+      "grad_norm": 1.2519271390201068,
+      "learning_rate": 8.449069839236538e-05,
+      "loss": 0.7998,
+      "num_input_tokens_seen": 26417952,
+      "step": 68,
+      "train_runtime": 5756.4201,
+      "train_tokens_per_second": 4589.302
+    },
+    {
+      "epoch": 1.3317073170731708,
+      "grad_norm": 2.0612640489651586,
+      "learning_rate": 8.405079293933986e-05,
+      "loss": 0.7949,
+      "num_input_tokens_seen": 26810784,
+      "step": 69,
+      "train_runtime": 5841.8015,
+      "train_tokens_per_second": 4589.472
+    },
+    {
+      "epoch": 1.3512195121951218,
+      "grad_norm": 1.6632187783624717,
+      "learning_rate": 8.360591612881364e-05,
+      "loss": 0.7718,
+      "num_input_tokens_seen": 27203616,
+      "step": 70,
+      "train_runtime": 5927.224,
+      "train_tokens_per_second": 4589.605
+    },
+    {
+      "epoch": 1.370731707317073,
+      "grad_norm": 0.8557124244577246,
+      "learning_rate": 8.315613291203976e-05,
+      "loss": 0.7827,
+      "num_input_tokens_seen": 27596448,
+      "step": 71,
+      "train_runtime": 6012.6847,
+      "train_tokens_per_second": 4589.705
+    },
+    {
+      "epoch": 1.3902439024390243,
+      "grad_norm": 1.0542485300201978,
+      "learning_rate": 8.270150895659823e-05,
+      "loss": 0.7595,
+      "num_input_tokens_seen": 27989280,
+      "step": 72,
+      "train_runtime": 6098.1854,
+      "train_tokens_per_second": 4589.772
+    },
+    {
+      "epoch": 1.4097560975609755,
+      "grad_norm": 1.7657947939512917,
+      "learning_rate": 8.224211063680853e-05,
+      "loss": 0.7416,
+      "num_input_tokens_seen": 28382112,
+      "step": 73,
+      "train_runtime": 6183.6199,
+      "train_tokens_per_second": 4589.886
+    },
+    {
+      "epoch": 1.4292682926829268,
+      "grad_norm": 1.8137027126017153,
+      "learning_rate": 8.177800502403928e-05,
+      "loss": 0.749,
+      "num_input_tokens_seen": 28774944,
+      "step": 74,
+      "train_runtime": 6269.1266,
+      "train_tokens_per_second": 4589.945
+    },
+    {
+      "epoch": 1.448780487804878,
+      "grad_norm": 1.3646726182984732,
+      "learning_rate": 8.130925987691569e-05,
+      "loss": 0.72,
+      "num_input_tokens_seen": 29167776,
+      "step": 75,
+      "train_runtime": 6354.5877,
+      "train_tokens_per_second": 4590.034
+    },
+    {
+      "epoch": 1.4682926829268292,
+      "grad_norm": 2.817948027228682,
+      "learning_rate": 8.083594363142717e-05,
+      "loss": 0.7192,
+      "num_input_tokens_seen": 29560608,
+      "step": 76,
+      "train_runtime": 6440.0829,
+      "train_tokens_per_second": 4590.097
+    },
+    {
+      "epoch": 1.4878048780487805,
+      "grad_norm": 2.8685745350018976,
+      "learning_rate": 8.035812539093557e-05,
+      "loss": 0.7221,
+      "num_input_tokens_seen": 29953440,
+      "step": 77,
+      "train_runtime": 6525.6763,
+      "train_tokens_per_second": 4590.09
+    },
+    {
+      "epoch": 1.5073170731707317,
+      "grad_norm": 0.806171095791916,
+      "learning_rate": 7.987587491608637e-05,
+      "loss": 0.7031,
+      "num_input_tokens_seen": 30346272,
+      "step": 78,
+      "train_runtime": 6611.3229,
+      "train_tokens_per_second": 4590.045
+    },
+    {
+      "epoch": 1.526829268292683,
+      "grad_norm": 3.0602847716922237,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7118,
+      "num_input_tokens_seen": 30739104,
+      "step": 79,
+      "train_runtime": 6696.8792,
+      "train_tokens_per_second": 4590.064
+    },
+    {
+      "epoch": 1.5463414634146342,
+      "grad_norm": 1.0137101758685187,
+      "learning_rate": 7.889835953111075e-05,
+      "loss": 0.6952,
+      "num_input_tokens_seen": 31131936,
+      "step": 80,
+      "train_runtime": 6782.7752,
+      "train_tokens_per_second": 4589.852
+    },
+    {
+      "epoch": 1.5658536585365854,
+      "grad_norm": 1.4320523827445433,
+      "learning_rate": 7.840323733655778e-05,
+      "loss": 0.6693,
+      "num_input_tokens_seen": 31524768,
+      "step": 81,
+      "train_runtime": 6868.9208,
+      "train_tokens_per_second": 4589.479
+    },
+    {
+      "epoch": 1.5853658536585367,
+      "grad_norm": 3.2012899077086177,
+      "learning_rate": 7.790396831795792e-05,
+      "loss": 0.6718,
+      "num_input_tokens_seen": 31917600,
+      "step": 82,
+      "train_runtime": 6954.5194,
+      "train_tokens_per_second": 4589.476
+    },
+    {
+      "epoch": 1.604878048780488,
+      "grad_norm": 0.7553296877905612,
+      "learning_rate": 7.740062536773352e-05,
+      "loss": 0.67,
+      "num_input_tokens_seen": 32310432,
+      "step": 83,
+      "train_runtime": 7040.0533,
+      "train_tokens_per_second": 4589.515
+    },
+    {
+      "epoch": 1.6243902439024391,
+      "grad_norm": 1.069764102117734,
+      "learning_rate": 7.689328197309393e-05,
+      "loss": 0.6688,
+      "num_input_tokens_seen": 32703264,
+      "step": 84,
+      "train_runtime": 7125.6152,
+      "train_tokens_per_second": 4589.536
+    },
+    {
+      "epoch": 1.6439024390243904,
+      "grad_norm": 2.635419412507475,
+      "learning_rate": 7.638201220530665e-05,
+      "loss": 0.6672,
+      "num_input_tokens_seen": 33096096,
+      "step": 85,
+      "train_runtime": 7211.09,
+      "train_tokens_per_second": 4589.611
+    },
+    {
+      "epoch": 1.6634146341463416,
+      "grad_norm": 0.7024644501267906,
+      "learning_rate": 7.586689070888284e-05,
+      "loss": 0.6573,
+      "num_input_tokens_seen": 33488928,
+      "step": 86,
+      "train_runtime": 7296.5933,
+      "train_tokens_per_second": 4589.666
+    },
+    {
+      "epoch": 1.6829268292682928,
+      "grad_norm": 0.44428213007263,
+      "learning_rate": 7.534799269067953e-05,
+      "loss": 0.6422,
+      "num_input_tokens_seen": 33881760,
+      "step": 87,
+      "train_runtime": 7382.0301,
+      "train_tokens_per_second": 4589.762
+    },
+    {
+      "epoch": 1.7024390243902439,
+      "grad_norm": 0.5416450836446436,
+      "learning_rate": 7.48253939089194e-05,
+      "loss": 0.6269,
+      "num_input_tokens_seen": 34274592,
+      "step": 88,
+      "train_runtime": 7467.4502,
+      "train_tokens_per_second": 4589.865
+    },
+    {
+      "epoch": 1.721951219512195,
+      "grad_norm": 0.5642965602823063,
+      "learning_rate": 7.42991706621303e-05,
+      "loss": 0.6357,
+      "num_input_tokens_seen": 34667424,
+      "step": 89,
+      "train_runtime": 7553.0173,
+      "train_tokens_per_second": 4589.878
+    },
+    {
+      "epoch": 1.7414634146341463,
+      "grad_norm": 0.5097755585636675,
+      "learning_rate": 7.376939977800582e-05,
+      "loss": 0.6299,
+      "num_input_tokens_seen": 35060256,
+      "step": 90,
+      "train_runtime": 7638.6282,
+      "train_tokens_per_second": 4589.863
+    },
+    {
+      "epoch": 1.7609756097560976,
+      "grad_norm": 0.45556407265977034,
+      "learning_rate": 7.323615860218843e-05,
+      "loss": 0.634,
+      "num_input_tokens_seen": 35453088,
+      "step": 91,
+      "train_runtime": 7724.1622,
+      "train_tokens_per_second": 4589.894
+    },
+    {
+      "epoch": 1.7804878048780488,
+      "grad_norm": 0.4536282771598066,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.6251,
+      "num_input_tokens_seen": 35845920,
+      "step": 92,
+      "train_runtime": 7809.6142,
+      "train_tokens_per_second": 4589.973
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.43350812308828435,
+      "learning_rate": 7.215957727996207e-05,
+      "loss": 0.62,
+      "num_input_tokens_seen": 36238752,
+      "step": 93,
+      "train_runtime": 7895.006,
+      "train_tokens_per_second": 4590.085
+    },
+    {
+      "epoch": 1.819512195121951,
+      "grad_norm": 0.40833077692944497,
+      "learning_rate": 7.161639431258387e-05,
+      "loss": 0.6073,
+      "num_input_tokens_seen": 36631584,
+      "step": 94,
+      "train_runtime": 7980.4652,
+      "train_tokens_per_second": 4590.156
+    },
+    {
+      "epoch": 1.8390243902439023,
+      "grad_norm": 0.4235068021237779,
+      "learning_rate": 7.107005538862646e-05,
+      "loss": 0.6074,
+      "num_input_tokens_seen": 37024416,
+      "step": 95,
+      "train_runtime": 8065.9658,
+      "train_tokens_per_second": 4590.202
+    },
+    {
+      "epoch": 1.8585365853658535,
+      "grad_norm": 0.4132415083645228,
+      "learning_rate": 7.052064027263786e-05,
+      "loss": 0.6064,
+      "num_input_tokens_seen": 37417248,
+      "step": 96,
+      "train_runtime": 8151.397,
+      "train_tokens_per_second": 4590.287
+    },
+    {
+      "epoch": 1.8780487804878048,
+      "grad_norm": 0.4322861748139327,
+      "learning_rate": 6.996822917828477e-05,
+      "loss": 0.5922,
+      "num_input_tokens_seen": 37810080,
+      "step": 97,
+      "train_runtime": 8236.8862,
+      "train_tokens_per_second": 4590.337
+    },
+    {
+      "epoch": 1.897560975609756,
+      "grad_norm": 0.38942999050451615,
+      "learning_rate": 6.941290275664174e-05,
+      "loss": 0.5939,
+      "num_input_tokens_seen": 38202912,
+      "step": 98,
+      "train_runtime": 8322.3209,
+      "train_tokens_per_second": 4590.416
+    },
+    {
+      "epoch": 1.9170731707317072,
+      "grad_norm": 0.3753721554361611,
+      "learning_rate": 6.885474208441603e-05,
+      "loss": 0.5913,
+      "num_input_tokens_seen": 38595744,
+      "step": 99,
+      "train_runtime": 8407.7641,
+      "train_tokens_per_second": 4590.488
+    },
+    {
+      "epoch": 1.9365853658536585,
+      "grad_norm": 0.35005150318450906,
+      "learning_rate": 6.829382865211063e-05,
+      "loss": 0.5863,
+      "num_input_tokens_seen": 38988576,
+      "step": 100,
+      "train_runtime": 8493.2736,
+      "train_tokens_per_second": 4590.524
+    },
+    {
+      "epoch": 1.9560975609756097,
+      "grad_norm": 0.37808190956380233,
+      "learning_rate": 6.773024435212678e-05,
+      "loss": 0.5822,
+      "num_input_tokens_seen": 39381408,
+      "step": 101,
+      "train_runtime": 8578.7547,
+      "train_tokens_per_second": 4590.574
+    },
+    {
+      "epoch": 1.975609756097561,
+      "grad_norm": 0.3580568006066326,
+      "learning_rate": 6.716407146680792e-05,
+      "loss": 0.5666,
+      "num_input_tokens_seen": 39774240,
+      "step": 102,
+      "train_runtime": 8664.2328,
+      "train_tokens_per_second": 4590.625
+    },
+    {
+      "epoch": 1.9951219512195122,
+      "grad_norm": 0.39572577046735974,
+      "learning_rate": 6.659539265642643e-05,
+      "loss": 0.5806,
+      "num_input_tokens_seen": 40167072,
+      "step": 103,
+      "train_runtime": 8749.6718,
+      "train_tokens_per_second": 4590.695
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5994329532374332,
+      "learning_rate": 6.602429094711548e-05,
+      "loss": 0.5605,
+      "num_input_tokens_seen": 40265280,
+      "step": 104,
+      "train_runtime": 8771.0021,
+      "train_tokens_per_second": 4590.727
+    },
+    {
+      "epoch": 2.0195121951219512,
+      "grad_norm": 0.3746452769053094,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5462,
+      "num_input_tokens_seen": 40658112,
+      "step": 105,
+      "train_runtime": 8856.5287,
+      "train_tokens_per_second": 4590.75
+    },
+    {
+      "epoch": 2.0390243902439025,
+      "grad_norm": 0.453029236937953,
+      "learning_rate": 6.487515269276016e-05,
+      "loss": 0.5447,
+      "num_input_tokens_seen": 41050944,
+      "step": 106,
+      "train_runtime": 8942.0292,
+      "train_tokens_per_second": 4590.786
+    },
+    {
+      "epoch": 2.0585365853658537,
+      "grad_norm": 0.39272552581140363,
+      "learning_rate": 6.429728391993446e-05,
+      "loss": 0.5405,
+      "num_input_tokens_seen": 41443776,
+      "step": 107,
+      "train_runtime": 9027.5293,
+      "train_tokens_per_second": 4590.822
+    },
+    {
+      "epoch": 2.078048780487805,
+      "grad_norm": 0.35801484704748626,
+      "learning_rate": 6.37173277681223e-05,
+      "loss": 0.5433,
+      "num_input_tokens_seen": 41836608,
+      "step": 108,
+      "train_runtime": 9113.0265,
+      "train_tokens_per_second": 4590.858
+    },
+    {
+      "epoch": 2.097560975609756,
+      "grad_norm": 0.3703575056088343,
+      "learning_rate": 6.313536890992935e-05,
+      "loss": 0.5335,
+      "num_input_tokens_seen": 42229440,
+      "step": 109,
+      "train_runtime": 9198.6667,
+      "train_tokens_per_second": 4590.822
+    },
+    {
+      "epoch": 2.1170731707317074,
+      "grad_norm": 0.3456947105084525,
+      "learning_rate": 6.255149231035309e-05,
+      "loss": 0.5416,
+      "num_input_tokens_seen": 42622272,
+      "step": 110,
+      "train_runtime": 9284.269,
+      "train_tokens_per_second": 4590.805
+    },
+    {
+      "epoch": 2.1365853658536587,
+      "grad_norm": 0.33745389931809666,
+      "learning_rate": 6.19657832143779e-05,
+      "loss": 0.5322,
+      "num_input_tokens_seen": 43015104,
+      "step": 111,
+      "train_runtime": 9369.843,
+      "train_tokens_per_second": 4590.803
+    },
+    {
+      "epoch": 2.15609756097561,
+      "grad_norm": 0.33453831659901945,
+      "learning_rate": 6.13783271345295e-05,
+      "loss": 0.5301,
+      "num_input_tokens_seen": 43407936,
+      "step": 112,
+      "train_runtime": 9455.4833,
+      "train_tokens_per_second": 4590.769
+    },
+    {
+      "epoch": 2.175609756097561,
+      "grad_norm": 0.3355284079398747,
+      "learning_rate": 6.078920983839031e-05,
+      "loss": 0.5422,
+      "num_input_tokens_seen": 43800768,
+      "step": 113,
+      "train_runtime": 9541.0542,
+      "train_tokens_per_second": 4590.768
+    },
+    {
+      "epoch": 2.1951219512195124,
+      "grad_norm": 0.3257056473237624,
+      "learning_rate": 6.019851733607744e-05,
+      "loss": 0.5352,
+      "num_input_tokens_seen": 44193600,
+      "step": 114,
+      "train_runtime": 9626.532,
+      "train_tokens_per_second": 4590.812
+    },
+    {
+      "epoch": 2.2146341463414636,
+      "grad_norm": 0.32389003819610007,
+      "learning_rate": 5.960633586768543e-05,
+      "loss": 0.5112,
+      "num_input_tokens_seen": 44586432,
+      "step": 115,
+      "train_runtime": 9712.1322,
+      "train_tokens_per_second": 4590.797
+    },
+    {
+      "epoch": 2.234146341463415,
+      "grad_norm": 0.34317758929799447,
+      "learning_rate": 5.90127518906953e-05,
+      "loss": 0.5171,
+      "num_input_tokens_seen": 44979264,
+      "step": 116,
+      "train_runtime": 9797.6269,
+      "train_tokens_per_second": 4590.833
+    },
+    {
+      "epoch": 2.253658536585366,
+      "grad_norm": 0.31740577502228223,
+      "learning_rate": 5.841785206735192e-05,
+      "loss": 0.5027,
+      "num_input_tokens_seen": 45372096,
+      "step": 117,
+      "train_runtime": 9883.3105,
+      "train_tokens_per_second": 4590.779
+    },
+    {
+      "epoch": 2.2731707317073173,
+      "grad_norm": 0.3705124747857168,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.5151,
+      "num_input_tokens_seen": 45764928,
+      "step": 118,
+      "train_runtime": 9968.9083,
+      "train_tokens_per_second": 4590.766
+    },
+    {
+      "epoch": 2.292682926829268,
+      "grad_norm": 0.36613629503091577,
+      "learning_rate": 5.7224452478461064e-05,
+      "loss": 0.5152,
+      "num_input_tokens_seen": 46157760,
+      "step": 119,
+      "train_runtime": 10054.434,
+      "train_tokens_per_second": 4590.787
+    },
+    {
+      "epoch": 2.3121951219512193,
+      "grad_norm": 0.3314221690877754,
+      "learning_rate": 5.6626126947211386e-05,
+      "loss": 0.5303,
+      "num_input_tokens_seen": 46550592,
+      "step": 120,
+      "train_runtime": 10139.9414,
+      "train_tokens_per_second": 4590.815
+    },
+    {
+      "epoch": 2.3317073170731706,
+      "grad_norm": 0.3470857883762708,
+      "learning_rate": 5.602683401276615e-05,
+      "loss": 0.5032,
+      "num_input_tokens_seen": 46943424,
+      "step": 121,
+      "train_runtime": 10225.7135,
+      "train_tokens_per_second": 4590.724
+    },
+    {
+      "epoch": 2.351219512195122,
+      "grad_norm": 0.3136083377085674,
+      "learning_rate": 5.542666117086832e-05,
+      "loss": 0.5119,
+      "num_input_tokens_seen": 47336256,
+      "step": 122,
+      "train_runtime": 10311.2617,
+      "train_tokens_per_second": 4590.734
+    },
+    {
+      "epoch": 2.370731707317073,
+      "grad_norm": 0.4227118641608833,
+      "learning_rate": 5.482569604572576e-05,
+      "loss": 0.5045,
+      "num_input_tokens_seen": 47729088,
+      "step": 123,
+      "train_runtime": 10396.9552,
+      "train_tokens_per_second": 4590.679
+    },
+    {
+      "epoch": 2.3902439024390243,
+      "grad_norm": 0.32585539704348276,
+      "learning_rate": 5.422402637721836e-05,
+      "loss": 0.505,
+      "num_input_tokens_seen": 48121920,
+      "step": 124,
+      "train_runtime": 10482.7724,
+      "train_tokens_per_second": 4590.572
+    },
+    {
+      "epoch": 2.4097560975609755,
+      "grad_norm": 0.3224554976871665,
+      "learning_rate": 5.3621740008088126e-05,
+      "loss": 0.5017,
+      "num_input_tokens_seen": 48514752,
+      "step": 125,
+      "train_runtime": 10568.4335,
+      "train_tokens_per_second": 4590.534
+    },
+    {
+      "epoch": 2.4292682926829268,
+      "grad_norm": 0.33513514879191686,
+      "learning_rate": 5.3018924871114305e-05,
+      "loss": 0.5019,
+      "num_input_tokens_seen": 48907584,
+      "step": 126,
+      "train_runtime": 10653.9397,
+      "train_tokens_per_second": 4590.563
+    },
+    {
+      "epoch": 2.448780487804878,
+      "grad_norm": 0.3333825976504885,
+      "learning_rate": 5.2415668976275355e-05,
+      "loss": 0.4921,
+      "num_input_tokens_seen": 49300416,
+      "step": 127,
+      "train_runtime": 10739.489,
+      "train_tokens_per_second": 4590.574
+    },
+    {
+      "epoch": 2.4682926829268292,
+      "grad_norm": 0.32605283067247587,
+      "learning_rate": 5.181206039789962e-05,
+      "loss": 0.4951,
+      "num_input_tokens_seen": 49693248,
+      "step": 128,
+      "train_runtime": 10825.0018,
+      "train_tokens_per_second": 4590.6
+    },
+    {
+      "epoch": 2.4878048780487805,
+      "grad_norm": 0.345821204685631,
+      "learning_rate": 5.1208187261806615e-05,
+      "loss": 0.5076,
+      "num_input_tokens_seen": 50086080,
+      "step": 129,
+      "train_runtime": 10910.4514,
+      "train_tokens_per_second": 4590.652
+    },
+    {
+      "epoch": 2.5073170731707317,
+      "grad_norm": 0.32182997237639754,
+      "learning_rate": 5.060413773244087e-05,
+      "loss": 0.4974,
+      "num_input_tokens_seen": 50478912,
+      "step": 130,
+      "train_runtime": 10996.0971,
+      "train_tokens_per_second": 4590.621
+    },
+    {
+      "epoch": 2.526829268292683,
+      "grad_norm": 0.3424390071269269,
+      "learning_rate": 5e-05,
+      "loss": 0.5063,
+      "num_input_tokens_seen": 50871744,
+      "step": 131,
+      "train_runtime": 11081.5772,
+      "train_tokens_per_second": 4590.659
+    },
+    {
+      "epoch": 2.546341463414634,
+      "grad_norm": 0.32151933822675133,
+      "learning_rate": 4.9395862267559136e-05,
+      "loss": 0.5093,
+      "num_input_tokens_seen": 51264576,
+      "step": 132,
+      "train_runtime": 11167.132,
+      "train_tokens_per_second": 4590.666
+    },
+    {
+      "epoch": 2.5658536585365854,
+      "grad_norm": 0.33150875749489067,
+      "learning_rate": 4.87918127381934e-05,
+      "loss": 0.5019,
+      "num_input_tokens_seen": 51657408,
+      "step": 133,
+      "train_runtime": 11252.7312,
+      "train_tokens_per_second": 4590.655
+    },
+    {
+      "epoch": 2.5853658536585367,
+      "grad_norm": 0.32260765542480235,
+      "learning_rate": 4.81879396021004e-05,
+      "loss": 0.4836,
+      "num_input_tokens_seen": 52050240,
+      "step": 134,
+      "train_runtime": 11338.3707,
+      "train_tokens_per_second": 4590.628
+    },
+    {
+      "epoch": 2.604878048780488,
+      "grad_norm": 0.3284283947692906,
+      "learning_rate": 4.758433102372466e-05,
+      "loss": 0.4878,
+      "num_input_tokens_seen": 52443072,
+      "step": 135,
+      "train_runtime": 11424.0926,
+      "train_tokens_per_second": 4590.568
+    },
+    {
+      "epoch": 2.624390243902439,
+      "grad_norm": 0.3174202627091527,
+      "learning_rate": 4.6981075128885693e-05,
+      "loss": 0.4895,
+      "num_input_tokens_seen": 52835904,
+      "step": 136,
+      "train_runtime": 11509.8066,
+      "train_tokens_per_second": 4590.512
+    },
+    {
+      "epoch": 2.6439024390243904,
+      "grad_norm": 0.3424879966422641,
+      "learning_rate": 4.6378259991911886e-05,
+      "loss": 0.4987,
+      "num_input_tokens_seen": 53228736,
+      "step": 137,
+      "train_runtime": 11595.5338,
+      "train_tokens_per_second": 4590.452
+    },
+    {
+      "epoch": 2.6634146341463416,
+      "grad_norm": 0.31862495887920006,
+      "learning_rate": 4.5775973622781655e-05,
+      "loss": 0.4952,
+      "num_input_tokens_seen": 53621568,
+      "step": 138,
+      "train_runtime": 11681.2149,
+      "train_tokens_per_second": 4590.41
+    },
+    {
+      "epoch": 2.682926829268293,
+      "grad_norm": 0.32882715869402424,
+      "learning_rate": 4.5174303954274244e-05,
+      "loss": 0.4852,
+      "num_input_tokens_seen": 54014400,
+      "step": 139,
+      "train_runtime": 11766.8708,
+      "train_tokens_per_second": 4590.379
+    },
+    {
+      "epoch": 2.7024390243902436,
+      "grad_norm": 0.35853159941406193,
+      "learning_rate": 4.457333882913169e-05,
+      "loss": 0.4966,
+      "num_input_tokens_seen": 54407232,
+      "step": 140,
+      "train_runtime": 11852.5434,
+      "train_tokens_per_second": 4590.342
+    },
+    {
+      "epoch": 2.721951219512195,
+      "grad_norm": 0.3220506479281512,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 0.4851,
+      "num_input_tokens_seen": 54800064,
+      "step": 141,
+      "train_runtime": 11938.0,
+      "train_tokens_per_second": 4590.389
+    },
+    {
+      "epoch": 2.741463414634146,
+      "grad_norm": 0.338780671076278,
+      "learning_rate": 4.337387305278864e-05,
+      "loss": 0.4897,
+      "num_input_tokens_seen": 55192896,
+      "step": 142,
+      "train_runtime": 12023.5136,
+      "train_tokens_per_second": 4590.413
+    },
+    {
+      "epoch": 2.7609756097560973,
+      "grad_norm": 0.3467288544912658,
+      "learning_rate": 4.277554752153895e-05,
+      "loss": 0.4992,
+      "num_input_tokens_seen": 55585728,
+      "step": 143,
+      "train_runtime": 12109.1196,
+      "train_tokens_per_second": 4590.402
+    },
+    {
+      "epoch": 2.7804878048780486,
+      "grad_norm": 0.3172644652222353,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.4842,
+      "num_input_tokens_seen": 55978560,
+      "step": 144,
+      "train_runtime": 12194.6967,
+      "train_tokens_per_second": 4590.402
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.33792230752401564,
+      "learning_rate": 4.1582147932648074e-05,
+      "loss": 0.4941,
+      "num_input_tokens_seen": 56371392,
+      "step": 145,
+      "train_runtime": 12280.2743,
+      "train_tokens_per_second": 4590.402
+    },
+    {
+      "epoch": 2.819512195121951,
+      "grad_norm": 0.33669423565884143,
+      "learning_rate": 4.0987248109304714e-05,
+      "loss": 0.4933,
+      "num_input_tokens_seen": 56764224,
+      "step": 146,
+      "train_runtime": 12365.7877,
+      "train_tokens_per_second": 4590.425
+    },
+    {
+      "epoch": 2.8390243902439023,
+      "grad_norm": 0.32219243021646965,
+      "learning_rate": 4.039366413231458e-05,
+      "loss": 0.4847,
+      "num_input_tokens_seen": 57157056,
+      "step": 147,
+      "train_runtime": 12451.3235,
+      "train_tokens_per_second": 4590.44
+    },
+    {
+      "epoch": 2.8585365853658535,
+      "grad_norm": 0.32466591195010414,
+      "learning_rate": 3.980148266392258e-05,
+      "loss": 0.492,
+      "num_input_tokens_seen": 57549888,
+      "step": 148,
+      "train_runtime": 12536.8522,
+      "train_tokens_per_second": 4590.458
+    },
+    {
+      "epoch": 2.8780487804878048,
+      "grad_norm": 0.3484362997993096,
+      "learning_rate": 3.92107901616097e-05,
+      "loss": 0.4933,
+      "num_input_tokens_seen": 57942720,
+      "step": 149,
+      "train_runtime": 12622.324,
+      "train_tokens_per_second": 4590.495
+    },
+    {
+      "epoch": 2.897560975609756,
+      "grad_norm": 0.30189538682359085,
+      "learning_rate": 3.86216728654705e-05,
+      "loss": 0.4812,
+      "num_input_tokens_seen": 58335552,
+      "step": 150,
+      "train_runtime": 12707.9974,
+      "train_tokens_per_second": 4590.46
+    },
+    {
+      "epoch": 2.9170731707317072,
+      "grad_norm": 0.3427990142333379,
+      "learning_rate": 3.803421678562213e-05,
+      "loss": 0.4822,
+      "num_input_tokens_seen": 58728384,
+      "step": 151,
+      "train_runtime": 12793.4446,
+      "train_tokens_per_second": 4590.506
+    },
+    {
+      "epoch": 2.9365853658536585,
+      "grad_norm": 0.38332155033085324,
+      "learning_rate": 3.744850768964692e-05,
+      "loss": 0.4814,
+      "num_input_tokens_seen": 59121216,
+      "step": 152,
+      "train_runtime": 12878.9545,
+      "train_tokens_per_second": 4590.529
+    },
+    {
+      "epoch": 2.9560975609756097,
+      "grad_norm": 0.33602591668846876,
+      "learning_rate": 3.6864631090070655e-05,
+      "loss": 0.4921,
+      "num_input_tokens_seen": 59514048,
+      "step": 153,
+      "train_runtime": 12964.4255,
+      "train_tokens_per_second": 4590.566
+    },
+    {
+      "epoch": 2.975609756097561,
+      "grad_norm": 0.5609630326555886,
+      "learning_rate": 3.628267223187771e-05,
+      "loss": 0.4768,
+      "num_input_tokens_seen": 59906880,
+      "step": 154,
+      "train_runtime": 13049.8908,
+      "train_tokens_per_second": 4590.604
+    },
+    {
+      "epoch": 2.995121951219512,
+      "grad_norm": 0.3265623784171003,
+      "learning_rate": 3.570271608006555e-05,
+      "loss": 0.4579,
+      "num_input_tokens_seen": 60299712,
+      "step": 155,
+      "train_runtime": 13135.5526,
+      "train_tokens_per_second": 4590.573
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5314640992941223,
+      "learning_rate": 3.512484730723986e-05,
+      "loss": 0.4418,
+      "num_input_tokens_seen": 60397920,
+      "step": 156,
+      "train_runtime": 13156.9996,
+      "train_tokens_per_second": 4590.554
+    },
+    {
+      "epoch": 3.0195121951219512,
+      "grad_norm": 0.3203324244604146,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.4471,
+      "num_input_tokens_seen": 60790752,
+      "step": 157,
+      "train_runtime": 13242.5524,
+      "train_tokens_per_second": 4590.562
+    },
+    {
+      "epoch": 3.0390243902439025,
+      "grad_norm": 0.32182085188193466,
+      "learning_rate": 3.397570905288453e-05,
+      "loss": 0.4543,
+      "num_input_tokens_seen": 61183584,
+      "step": 158,
+      "train_runtime": 13328.1385,
+      "train_tokens_per_second": 4590.557
+    },
+    {
+      "epoch": 3.0585365853658537,
+      "grad_norm": 0.34726844831899983,
+      "learning_rate": 3.340460734357359e-05,
+      "loss": 0.4561,
+      "num_input_tokens_seen": 61576416,
+      "step": 159,
+      "train_runtime": 13413.7011,
+      "train_tokens_per_second": 4590.561
+    },
+    {
+      "epoch": 3.078048780487805,
+      "grad_norm": 0.32939131628064333,
+      "learning_rate": 3.283592853319209e-05,
+      "loss": 0.4521,
+      "num_input_tokens_seen": 61969248,
+      "step": 160,
+      "train_runtime": 13499.28,
+      "train_tokens_per_second": 4590.56
+    },
+    {
+      "epoch": 3.097560975609756,
+      "grad_norm": 0.325117680484632,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 0.444,
+      "num_input_tokens_seen": 62362080,
+      "step": 161,
+      "train_runtime": 13585.0343,
+      "train_tokens_per_second": 4590.499
+    },
+    {
+      "epoch": 3.1170731707317074,
+      "grad_norm": 0.32737548048736476,
+      "learning_rate": 3.170617134788939e-05,
+      "loss": 0.4541,
+      "num_input_tokens_seen": 62754912,
+      "step": 162,
+      "train_runtime": 13670.9946,
+      "train_tokens_per_second": 4590.369
+    },
+    {
+      "epoch": 3.1365853658536587,
+      "grad_norm": 0.39482140502206775,
+      "learning_rate": 3.114525791558398e-05,
+      "loss": 0.4582,
+      "num_input_tokens_seen": 63147744,
+      "step": 163,
+      "train_runtime": 13756.507,
+      "train_tokens_per_second": 4590.391
+    },
+    {
+      "epoch": 3.15609756097561,
+      "grad_norm": 0.3357742173716643,
+      "learning_rate": 3.0587097243358253e-05,
+      "loss": 0.4429,
+      "num_input_tokens_seen": 63540576,
+      "step": 164,
+      "train_runtime": 13842.0341,
+      "train_tokens_per_second": 4590.407
+    },
+    {
+      "epoch": 3.175609756097561,
+      "grad_norm": 0.3305601057024288,
+      "learning_rate": 3.003177082171523e-05,
+      "loss": 0.4443,
+      "num_input_tokens_seen": 63933408,
+      "step": 165,
+      "train_runtime": 13927.6175,
+      "train_tokens_per_second": 4590.405
+    },
+    {
+      "epoch": 3.1951219512195124,
+      "grad_norm": 0.32083308624205303,
+      "learning_rate": 2.9479359727362173e-05,
+      "loss": 0.4521,
+      "num_input_tokens_seen": 64326240,
+      "step": 166,
+      "train_runtime": 14013.2528,
+      "train_tokens_per_second": 4590.386
+    },
+    {
+      "epoch": 3.2146341463414636,
+      "grad_norm": 0.3335280375327217,
+      "learning_rate": 2.8929944611373554e-05,
+      "loss": 0.4362,
+      "num_input_tokens_seen": 64719072,
+      "step": 167,
+      "train_runtime": 14099.4999,
+      "train_tokens_per_second": 4590.168
+    },
+    {
+      "epoch": 3.234146341463415,
+      "grad_norm": 0.31479589078333686,
+      "learning_rate": 2.8383605687416125e-05,
+      "loss": 0.4503,
+      "num_input_tokens_seen": 65111904,
+      "step": 168,
+      "train_runtime": 14184.9981,
+      "train_tokens_per_second": 4590.195
+    },
+    {
+      "epoch": 3.253658536585366,
+      "grad_norm": 0.3729374255823192,
+      "learning_rate": 2.784042272003794e-05,
+      "loss": 0.448,
+      "num_input_tokens_seen": 65504736,
+      "step": 169,
+      "train_runtime": 14270.519,
+      "train_tokens_per_second": 4590.214
+    },
+    {
+      "epoch": 3.2731707317073173,
+      "grad_norm": 0.32769391044042884,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.4495,
+      "num_input_tokens_seen": 65897568,
+      "step": 170,
+      "train_runtime": 14355.9895,
+      "train_tokens_per_second": 4590.249
+    },
+    {
+      "epoch": 3.292682926829268,
+      "grad_norm": 0.3747118383247798,
+      "learning_rate": 2.6763841397811573e-05,
+      "loss": 0.4512,
+      "num_input_tokens_seen": 66290400,
+      "step": 171,
+      "train_runtime": 14441.5179,
+      "train_tokens_per_second": 4590.265
+    },
+    {
+      "epoch": 3.3121951219512193,
+      "grad_norm": 0.35364574417316713,
+      "learning_rate": 2.6230600221994196e-05,
+      "loss": 0.4342,
+      "num_input_tokens_seen": 66683232,
+      "step": 172,
+      "train_runtime": 14527.0516,
+      "train_tokens_per_second": 4590.28
+    },
+    {
+      "epoch": 3.3317073170731706,
+      "grad_norm": 0.34897968261286955,
+      "learning_rate": 2.57008293378697e-05,
+      "loss": 0.4456,
+      "num_input_tokens_seen": 67076064,
+      "step": 173,
+      "train_runtime": 14612.5638,
+      "train_tokens_per_second": 4590.301
+    },
+    {
+      "epoch": 3.351219512195122,
+      "grad_norm": 0.3526301707012528,
+      "learning_rate": 2.5174606091080627e-05,
+      "loss": 0.4459,
+      "num_input_tokens_seen": 67468896,
+      "step": 174,
+      "train_runtime": 14698.0406,
+      "train_tokens_per_second": 4590.333
+    },
+    {
+      "epoch": 3.370731707317073,
+      "grad_norm": 0.35117048748443935,
+      "learning_rate": 2.4652007309320498e-05,
+      "loss": 0.4383,
+      "num_input_tokens_seen": 67861728,
+      "step": 175,
+      "train_runtime": 14783.5396,
+      "train_tokens_per_second": 4590.357
+    },
+    {
+      "epoch": 3.3902439024390243,
+      "grad_norm": 0.3122289166658474,
+      "learning_rate": 2.4133109291117156e-05,
+      "loss": 0.4447,
+      "num_input_tokens_seen": 68254560,
+      "step": 176,
+      "train_runtime": 14868.9762,
+      "train_tokens_per_second": 4590.401
+    },
+    {
+      "epoch": 3.4097560975609755,
+      "grad_norm": 0.3521930408336,
+      "learning_rate": 2.361798779469336e-05,
+      "loss": 0.442,
+      "num_input_tokens_seen": 68647392,
+      "step": 177,
+      "train_runtime": 14954.4517,
+      "train_tokens_per_second": 4590.432
+    },
+    {
+      "epoch": 3.4292682926829268,
+      "grad_norm": 0.3077364343260739,
+      "learning_rate": 2.3106718026906072e-05,
+      "loss": 0.4418,
+      "num_input_tokens_seen": 69040224,
+      "step": 178,
+      "train_runtime": 15039.9655,
+      "train_tokens_per_second": 4590.451
+    },
+    {
+      "epoch": 3.448780487804878,
+      "grad_norm": 0.33010430660817575,
+      "learning_rate": 2.259937463226651e-05,
+      "loss": 0.4325,
+      "num_input_tokens_seen": 69433056,
+      "step": 179,
+      "train_runtime": 15125.4865,
+      "train_tokens_per_second": 4590.468
+    },
+    {
+      "epoch": 3.4682926829268292,
+      "grad_norm": 0.325795518062987,
+      "learning_rate": 2.209603168204209e-05,
+      "loss": 0.4319,
+      "num_input_tokens_seen": 69825888,
+      "step": 180,
+      "train_runtime": 15211.012,
+      "train_tokens_per_second": 4590.483
+    },
+    {
+      "epoch": 3.4878048780487805,
+      "grad_norm": 0.3179877620527606,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 0.4401,
+      "num_input_tokens_seen": 70218720,
+      "step": 181,
+      "train_runtime": 15296.5238,
+      "train_tokens_per_second": 4590.502
+    },
+    {
+      "epoch": 3.5073170731707317,
+      "grad_norm": 0.3287765696670568,
+      "learning_rate": 2.1101640468889255e-05,
+      "loss": 0.4386,
+      "num_input_tokens_seen": 70611552,
+      "step": 182,
+      "train_runtime": 15382.0311,
+      "train_tokens_per_second": 4590.522
+    },
+    {
+      "epoch": 3.526829268292683,
+      "grad_norm": 0.31971467799401765,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.4202,
+      "num_input_tokens_seen": 71004384,
+      "step": 183,
+      "train_runtime": 15467.521,
+      "train_tokens_per_second": 4590.547
+    },
+    {
+      "epoch": 3.546341463414634,
+      "grad_norm": 0.3239181143254052,
+      "learning_rate": 2.0124125083913637e-05,
+      "loss": 0.4419,
+      "num_input_tokens_seen": 71397216,
+      "step": 184,
+      "train_runtime": 15553.2048,
+      "train_tokens_per_second": 4590.515
+    },
+    {
+      "epoch": 3.5658536585365854,
+      "grad_norm": 0.3040342295851482,
+      "learning_rate": 1.9641874609064443e-05,
+      "loss": 0.4336,
+      "num_input_tokens_seen": 71790048,
+      "step": 185,
+      "train_runtime": 15638.8236,
+      "train_tokens_per_second": 4590.502
+    },
+    {
+      "epoch": 3.5853658536585367,
+      "grad_norm": 0.3144952842609461,
+      "learning_rate": 1.9164056368572846e-05,
+      "loss": 0.4387,
+      "num_input_tokens_seen": 72182880,
+      "step": 186,
+      "train_runtime": 15724.5242,
+      "train_tokens_per_second": 4590.465
+    },
+    {
+      "epoch": 3.604878048780488,
+      "grad_norm": 0.31728573983048836,
+      "learning_rate": 1.8690740123084316e-05,
+      "loss": 0.4297,
+      "num_input_tokens_seen": 72575712,
+      "step": 187,
+      "train_runtime": 15810.1041,
+      "train_tokens_per_second": 4590.464
+    },
+    {
+      "epoch": 3.624390243902439,
+      "grad_norm": 0.35290725632142694,
+      "learning_rate": 1.8221994975960736e-05,
+      "loss": 0.446,
+      "num_input_tokens_seen": 72968544,
+      "step": 188,
+      "train_runtime": 15895.683,
+      "train_tokens_per_second": 4590.463
+    },
+    {
+      "epoch": 3.6439024390243904,
+      "grad_norm": 0.31295107237929615,
+      "learning_rate": 1.7757889363191483e-05,
+      "loss": 0.4318,
+      "num_input_tokens_seen": 73361376,
+      "step": 189,
+      "train_runtime": 15981.3241,
+      "train_tokens_per_second": 4590.444
+    },
+    {
+      "epoch": 3.6634146341463416,
+      "grad_norm": 0.30434189898649333,
+      "learning_rate": 1.7298491043401795e-05,
+      "loss": 0.4393,
+      "num_input_tokens_seen": 73754208,
+      "step": 190,
+      "train_runtime": 16066.87,
+      "train_tokens_per_second": 4590.453
+    },
+    {
+      "epoch": 3.682926829268293,
+      "grad_norm": 0.3000645994101256,
+      "learning_rate": 1.684386708796025e-05,
+      "loss": 0.4437,
+      "num_input_tokens_seen": 74147040,
+      "step": 191,
+      "train_runtime": 16152.3518,
+      "train_tokens_per_second": 4590.48
+    },
+    {
+      "epoch": 3.7024390243902436,
+      "grad_norm": 0.3161645570263139,
+      "learning_rate": 1.6394083871186362e-05,
+      "loss": 0.4378,
+      "num_input_tokens_seen": 74539872,
+      "step": 192,
+      "train_runtime": 16237.7807,
+      "train_tokens_per_second": 4590.521
+    },
+    {
+      "epoch": 3.721951219512195,
+      "grad_norm": 0.3085852095656564,
+      "learning_rate": 1.5949207060660138e-05,
+      "loss": 0.4388,
+      "num_input_tokens_seen": 74932704,
+      "step": 193,
+      "train_runtime": 16323.3128,
+      "train_tokens_per_second": 4590.533
+    },
+    {
+      "epoch": 3.741463414634146,
+      "grad_norm": 0.3214095905441243,
+      "learning_rate": 1.550930160763462e-05,
+      "loss": 0.4483,
+      "num_input_tokens_seen": 75325536,
+      "step": 194,
+      "train_runtime": 16408.7376,
+      "train_tokens_per_second": 4590.575
+    },
+    {
+      "epoch": 3.7609756097560973,
+      "grad_norm": 0.3029571828988472,
+      "learning_rate": 1.5074431737553157e-05,
+      "loss": 0.4336,
+      "num_input_tokens_seen": 75718368,
+      "step": 195,
+      "train_runtime": 16494.1425,
+      "train_tokens_per_second": 4590.622
+    },
+    {
+      "epoch": 3.7804878048780486,
+      "grad_norm": 0.3002722038512263,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4334,
+      "num_input_tokens_seen": 76111200,
+      "step": 196,
+      "train_runtime": 16579.5744,
+      "train_tokens_per_second": 4590.661
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.30486554391008086,
+      "learning_rate": 1.422005196279395e-05,
+      "loss": 0.4352,
+      "num_input_tokens_seen": 76504032,
+      "step": 197,
+      "train_runtime": 16665.0963,
+      "train_tokens_per_second": 4590.674
+    },
+    {
+      "epoch": 3.819512195121951,
+      "grad_norm": 0.3019225596466138,
+      "learning_rate": 1.3800666796101292e-05,
+      "loss": 0.4315,
+      "num_input_tokens_seen": 76896864,
+      "step": 198,
+      "train_runtime": 16750.5821,
+      "train_tokens_per_second": 4590.698
+    },
+    {
+      "epoch": 3.8390243902439023,
+      "grad_norm": 0.29879067901515843,
+      "learning_rate": 1.338656667011134e-05,
+      "loss": 0.4339,
+      "num_input_tokens_seen": 77289696,
+      "step": 199,
+      "train_runtime": 16836.0019,
+      "train_tokens_per_second": 4590.739
+    },
+    {
+      "epoch": 3.8585365853658535,
+      "grad_norm": 0.3064182382633002,
+      "learning_rate": 1.297781204273385e-05,
+      "loss": 0.4374,
+      "num_input_tokens_seen": 77682528,
+      "step": 200,
+      "train_runtime": 16921.5579,
+      "train_tokens_per_second": 4590.743
+    },
+    {
+      "epoch": 3.8780487804878048,
+      "grad_norm": 0.31545962722826715,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 0.4437,
+      "num_input_tokens_seen": 78075360,
+      "step": 201,
+      "train_runtime": 17007.1429,
+      "train_tokens_per_second": 4590.739
+    },
+    {
+      "epoch": 3.897560975609756,
+      "grad_norm": 0.3062038073298703,
+      "learning_rate": 1.2176577204574318e-05,
+      "loss": 0.4319,
+      "num_input_tokens_seen": 78468192,
+      "step": 202,
+      "train_runtime": 17092.564,
+      "train_tokens_per_second": 4590.779
+    },
+    {
+      "epoch": 3.9170731707317072,
+      "grad_norm": 0.4440664308923016,
+      "learning_rate": 1.178421397270758e-05,
+      "loss": 0.4322,
+      "num_input_tokens_seen": 78861024,
+      "step": 203,
+      "train_runtime": 17178.0234,
+      "train_tokens_per_second": 4590.809
+    },
+    {
+      "epoch": 3.9365853658536585,
+      "grad_norm": 0.3017158051173835,
+      "learning_rate": 1.1397430180205171e-05,
+      "loss": 0.4375,
+      "num_input_tokens_seen": 79253856,
+      "step": 204,
+      "train_runtime": 17263.8463,
+      "train_tokens_per_second": 4590.742
+    },
+    {
+      "epoch": 3.9560975609756097,
+      "grad_norm": 0.3075889998265315,
+      "learning_rate": 1.1016282296838887e-05,
+      "loss": 0.4182,
+      "num_input_tokens_seen": 79646688,
+      "step": 205,
+      "train_runtime": 17349.3107,
+      "train_tokens_per_second": 4590.77
+    },
+    {
+      "epoch": 3.975609756097561,
+      "grad_norm": 0.30086206726131764,
+      "learning_rate": 1.0640825969547496e-05,
+      "loss": 0.4382,
+      "num_input_tokens_seen": 80039520,
+      "step": 206,
+      "train_runtime": 17434.78,
+      "train_tokens_per_second": 4590.796
+    },
+    {
+      "epoch": 3.995121951219512,
+      "grad_norm": 0.30615268970962656,
+      "learning_rate": 1.0271116014312293e-05,
+      "loss": 0.4277,
+      "num_input_tokens_seen": 80432352,
+      "step": 207,
+      "train_runtime": 17520.2702,
+      "train_tokens_per_second": 4590.817
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5575452767715656,
+      "learning_rate": 9.90720640815408e-06,
+      "loss": 0.4029,
+      "num_input_tokens_seen": 80530560,
+      "step": 208,
+      "train_runtime": 17541.5926,
+      "train_tokens_per_second": 4590.835
+    },
+    {
+      "epoch": 4.019512195121951,
+      "grad_norm": 0.30272512353274567,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4243,
+      "num_input_tokens_seen": 80923392,
+      "step": 209,
+      "train_runtime": 17627.0549,
+      "train_tokens_per_second": 4590.863
+    },
+    {
+      "epoch": 4.0390243902439025,
+      "grad_norm": 0.30162450457883366,
+      "learning_rate": 9.196999909189762e-06,
+      "loss": 0.4146,
+      "num_input_tokens_seen": 81316224,
+      "step": 210,
+      "train_runtime": 17713.1477,
+      "train_tokens_per_second": 4590.727
+    },
+    {
+      "epoch": 4.058536585365854,
+      "grad_norm": 0.30526033181573403,
+      "learning_rate": 8.850806705317183e-06,
+      "loss": 0.4287,
+      "num_input_tokens_seen": 81709056,
+      "step": 211,
+      "train_runtime": 17798.6213,
+      "train_tokens_per_second": 4590.752
+    },
+    {
+      "epoch": 4.078048780487805,
+      "grad_norm": 0.3107654508084313,
+      "learning_rate": 8.510621213250247e-06,
+      "loss": 0.4221,
+      "num_input_tokens_seen": 82101888,
+      "step": 212,
+      "train_runtime": 17884.1454,
+      "train_tokens_per_second": 4590.764
+    },
+    {
+      "epoch": 4.097560975609756,
+      "grad_norm": 0.325160265062242,
+      "learning_rate": 8.176493099488663e-06,
+      "loss": 0.4232,
+      "num_input_tokens_seen": 82494720,
+      "step": 213,
+      "train_runtime": 17969.6704,
+      "train_tokens_per_second": 4590.775
+    },
+    {
+      "epoch": 4.117073170731707,
+      "grad_norm": 0.3137465946251142,
+      "learning_rate": 7.848471146165288e-06,
+      "loss": 0.416,
+      "num_input_tokens_seen": 82887552,
+      "step": 214,
+      "train_runtime": 18055.2394,
+      "train_tokens_per_second": 4590.776
+    },
+    {
+      "epoch": 4.136585365853659,
+      "grad_norm": 0.31293023871568965,
+      "learning_rate": 7.526603243923957e-06,
+      "loss": 0.4157,
+      "num_input_tokens_seen": 83280384,
+      "step": 215,
+      "train_runtime": 18140.8949,
+      "train_tokens_per_second": 4590.754
+    },
+    {
+      "epoch": 4.15609756097561,
+      "grad_norm": 0.31719664973482375,
+      "learning_rate": 7.21093638492763e-06,
+      "loss": 0.4174,
+      "num_input_tokens_seen": 83673216,
+      "step": 216,
+      "train_runtime": 18226.5244,
+      "train_tokens_per_second": 4590.739
+    },
+    {
+      "epoch": 4.175609756097561,
+      "grad_norm": 0.3958840925349482,
+      "learning_rate": 6.901516655997536e-06,
+      "loss": 0.4041,
+      "num_input_tokens_seen": 84066048,
+      "step": 217,
+      "train_runtime": 18312.181,
+      "train_tokens_per_second": 4590.717
+    },
+    {
+      "epoch": 4.195121951219512,
+      "grad_norm": 0.30791697730474177,
+      "learning_rate": 6.5983892318846275e-06,
+      "loss": 0.4155,
+      "num_input_tokens_seen": 84458880,
+      "step": 218,
+      "train_runtime": 18397.8319,
+      "train_tokens_per_second": 4590.697
+    },
+    {
+      "epoch": 4.214634146341464,
+      "grad_norm": 0.3034741442256561,
+      "learning_rate": 6.301598368674105e-06,
+      "loss": 0.4214,
+      "num_input_tokens_seen": 84851712,
+      "step": 219,
+      "train_runtime": 18483.4309,
+      "train_tokens_per_second": 4590.691
+    },
+    {
+      "epoch": 4.234146341463415,
+      "grad_norm": 0.32535838114327126,
+      "learning_rate": 6.011187397324114e-06,
+      "loss": 0.4193,
+      "num_input_tokens_seen": 85244544,
+      "step": 220,
+      "train_runtime": 18569.0539,
+      "train_tokens_per_second": 4590.678
+    },
+    {
+      "epoch": 4.253658536585366,
+      "grad_norm": 0.3033400736842611,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 0.4137,
+      "num_input_tokens_seen": 85637376,
+      "step": 221,
+      "train_runtime": 18654.7358,
+      "train_tokens_per_second": 4590.651
+    },
+    {
+      "epoch": 4.273170731707317,
+      "grad_norm": 0.3293082877684599,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.4069,
+      "num_input_tokens_seen": 86030208,
+      "step": 222,
+      "train_runtime": 18740.4478,
+      "train_tokens_per_second": 4590.616
+    },
+    {
+      "epoch": 4.2926829268292686,
+      "grad_norm": 0.2994148389025656,
+      "learning_rate": 5.178653135214812e-06,
+      "loss": 0.4188,
+      "num_input_tokens_seen": 86423040,
+      "step": 223,
+      "train_runtime": 18826.1093,
+      "train_tokens_per_second": 4590.595
+    },
+    {
+      "epoch": 4.31219512195122,
+      "grad_norm": 0.3140763914390958,
+      "learning_rate": 4.914176319791036e-06,
+      "loss": 0.4133,
+      "num_input_tokens_seen": 86815872,
+      "step": 224,
+      "train_runtime": 18911.7783,
+      "train_tokens_per_second": 4590.572
+    },
+    {
+      "epoch": 4.331707317073171,
+      "grad_norm": 0.3058594326378288,
+      "learning_rate": 4.65628195747273e-06,
+      "loss": 0.4136,
+      "num_input_tokens_seen": 87208704,
+      "step": 225,
+      "train_runtime": 18997.5405,
+      "train_tokens_per_second": 4590.526
+    },
+    {
+      "epoch": 4.351219512195122,
+      "grad_norm": 0.3036952677463643,
+      "learning_rate": 4.405007700395497e-06,
+      "loss": 0.4066,
+      "num_input_tokens_seen": 87601536,
+      "step": 226,
+      "train_runtime": 19083.2658,
+      "train_tokens_per_second": 4590.49
+    },
+    {
+      "epoch": 4.3707317073170735,
+      "grad_norm": 0.2986697055188429,
+      "learning_rate": 4.16039023417088e-06,
+      "loss": 0.4002,
+      "num_input_tokens_seen": 87994368,
+      "step": 227,
+      "train_runtime": 19168.9792,
+      "train_tokens_per_second": 4590.457
+    },
+    {
+      "epoch": 4.390243902439025,
+      "grad_norm": 0.30912351105330554,
+      "learning_rate": 3.922465272530351e-06,
+      "loss": 0.4213,
+      "num_input_tokens_seen": 88387200,
+      "step": 228,
+      "train_runtime": 19254.8776,
+      "train_tokens_per_second": 4590.38
+    },
+    {
+      "epoch": 4.409756097560976,
+      "grad_norm": 0.31390545996696395,
+      "learning_rate": 3.691267552111183e-06,
+      "loss": 0.4276,
+      "num_input_tokens_seen": 88780032,
+      "step": 229,
+      "train_runtime": 19340.5507,
+      "train_tokens_per_second": 4590.357
+    },
+    {
+      "epoch": 4.429268292682927,
+      "grad_norm": 0.3064931328623729,
+      "learning_rate": 3.4668308273848982e-06,
+      "loss": 0.417,
+      "num_input_tokens_seen": 89172864,
+      "step": 230,
+      "train_runtime": 19426.2001,
+      "train_tokens_per_second": 4590.34
+    },
+    {
+      "epoch": 4.4487804878048784,
+      "grad_norm": 0.2938965818242203,
+      "learning_rate": 3.249187865729264e-06,
+      "loss": 0.4036,
+      "num_input_tokens_seen": 89565696,
+      "step": 231,
+      "train_runtime": 19511.8505,
+      "train_tokens_per_second": 4590.323
+    },
+    {
+      "epoch": 4.46829268292683,
+      "grad_norm": 0.3009741802462199,
+      "learning_rate": 3.0383704426442394e-06,
+      "loss": 0.4109,
+      "num_input_tokens_seen": 89958528,
+      "step": 232,
+      "train_runtime": 19597.5003,
+      "train_tokens_per_second": 4590.306
+    },
+    {
+      "epoch": 4.487804878048781,
+      "grad_norm": 0.30572185629569554,
+      "learning_rate": 2.8344093371128424e-06,
+      "loss": 0.4177,
+      "num_input_tokens_seen": 90351360,
+      "step": 233,
+      "train_runtime": 19683.1546,
+      "train_tokens_per_second": 4590.289
+    },
+    {
+      "epoch": 4.507317073170732,
+      "grad_norm": 0.3060090032156781,
+      "learning_rate": 2.637334327107466e-06,
+      "loss": 0.4167,
+      "num_input_tokens_seen": 90744192,
+      "step": 234,
+      "train_runtime": 19768.7311,
+      "train_tokens_per_second": 4590.289
+    },
+    {
+      "epoch": 4.526829268292683,
+      "grad_norm": 0.30158648786459336,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4214,
+      "num_input_tokens_seen": 91137024,
+      "step": 235,
+      "train_runtime": 19854.2512,
+      "train_tokens_per_second": 4590.303
+    },
+    {
+      "epoch": 4.546341463414635,
+      "grad_norm": 0.30106548477413225,
+      "learning_rate": 2.2639566745727205e-06,
+      "loss": 0.4038,
+      "num_input_tokens_seen": 91529856,
+      "step": 236,
+      "train_runtime": 19939.85,
+      "train_tokens_per_second": 4590.298
+    },
+    {
+      "epoch": 4.565853658536585,
+      "grad_norm": 0.31280608719577163,
+      "learning_rate": 2.087708544541689e-06,
+      "loss": 0.4087,
+      "num_input_tokens_seen": 91922688,
+      "step": 237,
+      "train_runtime": 20025.4609,
+      "train_tokens_per_second": 4590.291
+    },
+    {
+      "epoch": 4.585365853658536,
+      "grad_norm": 0.3151237023853444,
+      "learning_rate": 1.9184555270746194e-06,
+      "loss": 0.4099,
+      "num_input_tokens_seen": 92315520,
+      "step": 238,
+      "train_runtime": 20111.0379,
+      "train_tokens_per_second": 4590.291
+    },
+    {
+      "epoch": 4.6048780487804875,
+      "grad_norm": 0.2979822004749027,
+      "learning_rate": 1.7562223328224325e-06,
+      "loss": 0.4098,
+      "num_input_tokens_seen": 92708352,
+      "step": 239,
+      "train_runtime": 20196.6063,
+      "train_tokens_per_second": 4590.294
+    },
+    {
+      "epoch": 4.624390243902439,
+      "grad_norm": 0.29641279383853864,
+      "learning_rate": 1.601032647553863e-06,
+      "loss": 0.4106,
+      "num_input_tokens_seen": 93101184,
+      "step": 240,
+      "train_runtime": 20282.2193,
+      "train_tokens_per_second": 4590.286
+    },
+    {
+      "epoch": 4.64390243902439,
+      "grad_norm": 0.30405930218468175,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 0.4204,
+      "num_input_tokens_seen": 93494016,
+      "step": 241,
+      "train_runtime": 20367.7887,
+      "train_tokens_per_second": 4590.288
+    },
+    {
+      "epoch": 4.663414634146341,
+      "grad_norm": 0.30816493741451845,
+      "learning_rate": 1.3118734020333256e-06,
+      "loss": 0.4069,
+      "num_input_tokens_seen": 93886848,
+      "step": 242,
+      "train_runtime": 20453.3944,
+      "train_tokens_per_second": 4590.282
+    },
+    {
+      "epoch": 4.682926829268292,
+      "grad_norm": 0.295889585872778,
+      "learning_rate": 1.1779460585363944e-06,
+      "loss": 0.4206,
+      "num_input_tokens_seen": 94279680,
+      "step": 243,
+      "train_runtime": 20538.896,
+      "train_tokens_per_second": 4590.299
+    },
+    {
+      "epoch": 4.702439024390244,
+      "grad_norm": 0.30064754265380783,
+      "learning_rate": 1.0511466513695777e-06,
+      "loss": 0.4216,
+      "num_input_tokens_seen": 94672512,
+      "step": 244,
+      "train_runtime": 20624.455,
+      "train_tokens_per_second": 4590.304
+    },
+    {
+      "epoch": 4.721951219512195,
+      "grad_norm": 0.2956056728342269,
+      "learning_rate": 9.314936930293283e-07,
+      "loss": 0.4067,
+      "num_input_tokens_seen": 95065344,
+      "step": 245,
+      "train_runtime": 20710.4849,
+      "train_tokens_per_second": 4590.204
+    },
+    {
+      "epoch": 4.741463414634146,
+      "grad_norm": 1.2801159100545316,
+      "learning_rate": 8.190046526428242e-07,
+      "loss": 0.4149,
+      "num_input_tokens_seen": 95458176,
+      "step": 246,
+      "train_runtime": 20796.2392,
+      "train_tokens_per_second": 4590.165
+    },
+    {
+      "epoch": 4.760975609756097,
+      "grad_norm": 0.2962901875713787,
+      "learning_rate": 7.136959534174592e-07,
+      "loss": 0.4104,
+      "num_input_tokens_seen": 95851008,
+      "step": 247,
+      "train_runtime": 20881.9173,
+      "train_tokens_per_second": 4590.144
+    },
+    {
+      "epoch": 4.780487804878049,
+      "grad_norm": 0.29775756656133795,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.4275,
+      "num_input_tokens_seen": 96243840,
+      "step": 248,
+      "train_runtime": 20967.6297,
+      "train_tokens_per_second": 4590.115
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.30152743001548155,
+      "learning_rate": 5.246800274474439e-07,
+      "loss": 0.4168,
+      "num_input_tokens_seen": 96636672,
+      "step": 249,
+      "train_runtime": 21053.3487,
+      "train_tokens_per_second": 4590.086
+    },
+    {
+      "epoch": 4.819512195121951,
+      "grad_norm": 0.3006544700138266,
+      "learning_rate": 4.4100039670454395e-07,
+      "loss": 0.4227,
+      "num_input_tokens_seen": 97029504,
+      "step": 250,
+      "train_runtime": 21139.1446,
+      "train_tokens_per_second": 4590.039
+    },
+    {
+      "epoch": 4.839024390243902,
+      "grad_norm": 0.3694815192213994,
+      "learning_rate": 3.6455629509730136e-07,
+      "loss": 0.4224,
+      "num_input_tokens_seen": 97422336,
+      "step": 251,
+      "train_runtime": 21224.947,
+      "train_tokens_per_second": 4589.992
+    },
+    {
+      "epoch": 4.8585365853658535,
+      "grad_norm": 0.29849891867672973,
+      "learning_rate": 2.953588833337406e-07,
+      "loss": 0.409,
+      "num_input_tokens_seen": 97815168,
+      "step": 252,
+      "train_runtime": 21311.0603,
+      "train_tokens_per_second": 4589.878
+    },
+    {
+      "epoch": 4.878048780487805,
+      "grad_norm": 0.29318102693895126,
+      "learning_rate": 2.334182641175686e-07,
+      "loss": 0.4164,
+      "num_input_tokens_seen": 98208000,
+      "step": 253,
+      "train_runtime": 21396.8922,
+      "train_tokens_per_second": 4589.825
+    },
+    {
+      "epoch": 4.897560975609756,
+      "grad_norm": 0.29392220191104595,
+      "learning_rate": 1.7874348067319912e-07,
+      "loss": 0.4048,
+      "num_input_tokens_seen": 98600832,
+      "step": 254,
+      "train_runtime": 21482.6378,
+      "train_tokens_per_second": 4589.792
+    },
+    {
+      "epoch": 4.917073170731707,
+      "grad_norm": 0.29522364415867186,
+      "learning_rate": 1.3134251542544774e-07,
+      "loss": 0.4082,
+      "num_input_tokens_seen": 98993664,
+      "step": 255,
+      "train_runtime": 21568.4139,
+      "train_tokens_per_second": 4589.752
+    },
+    {
+      "epoch": 4.9365853658536585,
+      "grad_norm": 0.29818003556233796,
+      "learning_rate": 9.12222888341252e-08,
+      "loss": 0.4214,
+      "num_input_tokens_seen": 99386496,
+      "step": 256,
+      "train_runtime": 21654.0911,
+      "train_tokens_per_second": 4589.733
+    },
+    {
+      "epoch": 4.95609756097561,
+      "grad_norm": 0.29688566274903394,
+      "learning_rate": 5.838865838366792e-08,
+      "loss": 0.413,
+      "num_input_tokens_seen": 99779328,
+      "step": 257,
+      "train_runtime": 21739.8502,
+      "train_tokens_per_second": 4589.697
+    },
+    {
+      "epoch": 4.975609756097561,
+      "grad_norm": 0.2972951381912236,
+      "learning_rate": 3.284641772793862e-08,
+      "loss": 0.4118,
+      "num_input_tokens_seen": 100172160,
+      "step": 258,
+      "train_runtime": 21825.6482,
+      "train_tokens_per_second": 4589.653
+    },
+    {
+      "epoch": 4.995121951219512,
+      "grad_norm": 0.2934977397098327,
+      "learning_rate": 1.4599295990352924e-08,
+      "loss": 0.4169,
+      "num_input_tokens_seen": 100564992,
+      "step": 259,
+      "train_runtime": 21911.3681,
+      "train_tokens_per_second": 4589.626
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.598332221412963,
+      "learning_rate": 3.6499572194648167e-09,
+      "loss": 0.3937,
+      "num_input_tokens_seen": 100663200,
+      "step": 260,
+      "train_runtime": 21932.7813,
+      "train_tokens_per_second": 4589.623
+    },
+    {
+      "epoch": 5.0,
+      "num_input_tokens_seen": 100663200,
+      "step": 260,
+      "total_flos": 2377568804143104.0,
+      "train_loss": 0.697018449810835,
+      "train_runtime": 22008.2973,
+      "train_samples_per_second": 4.45,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 260,
+  "num_input_tokens_seen": 100663200,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2377568804143104.0,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28367a7f01f97d093d01f03db18770fc51c71f24731638d1414a6bbecdecf30
+size 8081