Upload LoRA fine-tuned PMB chatbot

README.md

@@ -0,0 +1,209 @@
+---
+base_model: HuggingFaceH4/zephyr-7b-beta
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:HuggingFaceH4/zephyr-7b-beta
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.16.0

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "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:b3ead7e3066e80cfa4bb53b6a35906b6f925b219be40c98b7a54e110e5904c8f
+size 83945296

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:320cc78ed5548305583a9f19d074fcdef27aace78e9159ffd3b3982fc66a7963
+size 168149539

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a3ae16c7d9e2b34ead6785863cf981fc52cbf8b02d092ac3bcb981bf9d2917
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0984e75370fd0f920a2690fbfe37926629fa7a6666636f32ed583f054361ef
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4316eb011cda40a2369bca90737f198059d303bd27eafac608f4f9eaca5ea4
+size 1465

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,466 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 480,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0625,
+      "grad_norm": 2.5752453804016113,
+      "learning_rate": 0.00019625,
+      "loss": 1.2442,
+      "mean_token_accuracy": 0.7333131074905396,
+      "num_tokens": 8445.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 2.048556327819824,
+      "learning_rate": 0.00019208333333333336,
+      "loss": 0.8951,
+      "mean_token_accuracy": 0.7932066351175309,
+      "num_tokens": 16406.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 1.801416277885437,
+      "learning_rate": 0.00018833333333333335,
+      "loss": 0.9104,
+      "mean_token_accuracy": 0.7811209857463837,
+      "num_tokens": 26390.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.045475721359253,
+      "learning_rate": 0.00018416666666666665,
+      "loss": 0.7925,
+      "mean_token_accuracy": 0.8067008703947067,
+      "num_tokens": 35985.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 1.7908813953399658,
+      "learning_rate": 0.00018,
+      "loss": 0.7831,
+      "mean_token_accuracy": 0.8088378280401229,
+      "num_tokens": 45075.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 1.80556321144104,
+      "learning_rate": 0.00017583333333333334,
+      "loss": 0.7615,
+      "mean_token_accuracy": 0.8116786539554596,
+      "num_tokens": 54190.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 1.7150429487228394,
+      "learning_rate": 0.00017166666666666667,
+      "loss": 0.7645,
+      "mean_token_accuracy": 0.814566045999527,
+      "num_tokens": 63103.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.1259572505950928,
+      "learning_rate": 0.0001675,
+      "loss": 0.7304,
+      "mean_token_accuracy": 0.8198390424251556,
+      "num_tokens": 71820.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 1.862838864326477,
+      "learning_rate": 0.00016333333333333334,
+      "loss": 0.8033,
+      "mean_token_accuracy": 0.8004607737064362,
+      "num_tokens": 80005.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.9493387937545776,
+      "learning_rate": 0.00015916666666666667,
+      "loss": 0.7443,
+      "mean_token_accuracy": 0.8172103732824325,
+      "num_tokens": 89061.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 1.6027424335479736,
+      "learning_rate": 0.000155,
+      "loss": 0.6381,
+      "mean_token_accuracy": 0.840108859539032,
+      "num_tokens": 97490.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.662534236907959,
+      "learning_rate": 0.00015083333333333333,
+      "loss": 0.6839,
+      "mean_token_accuracy": 0.8289641946554184,
+      "num_tokens": 106341.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 1.8097492456436157,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.6565,
+      "mean_token_accuracy": 0.8321241825819016,
+      "num_tokens": 114882.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 1.62300705909729,
+      "learning_rate": 0.00014250000000000002,
+      "loss": 0.7479,
+      "mean_token_accuracy": 0.8141300559043885,
+      "num_tokens": 124454.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 1.7561979293823242,
+      "learning_rate": 0.00013833333333333333,
+      "loss": 0.7585,
+      "mean_token_accuracy": 0.8148397266864776,
+      "num_tokens": 134032.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7069191932678223,
+      "learning_rate": 0.00013416666666666666,
+      "loss": 0.6857,
+      "mean_token_accuracy": 0.8240068614482879,
+      "num_tokens": 142641.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.0625,
+      "grad_norm": 1.4199870824813843,
+      "learning_rate": 0.00013000000000000002,
+      "loss": 0.5387,
+      "mean_token_accuracy": 0.855182683467865,
+      "num_tokens": 151794.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 1.7815680503845215,
+      "learning_rate": 0.00012583333333333335,
+      "loss": 0.4761,
+      "mean_token_accuracy": 0.8708458811044693,
+      "num_tokens": 160718.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.1875,
+      "grad_norm": 1.5737107992172241,
+      "learning_rate": 0.00012166666666666667,
+      "loss": 0.4533,
+      "mean_token_accuracy": 0.8779246717691421,
+      "num_tokens": 169265.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.5212680101394653,
+      "learning_rate": 0.00011750000000000001,
+      "loss": 0.4593,
+      "mean_token_accuracy": 0.8714338272809983,
+      "num_tokens": 178575.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.3125,
+      "grad_norm": 1.6155683994293213,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 0.4431,
+      "mean_token_accuracy": 0.8786879241466522,
+      "num_tokens": 187096.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 1.5768648386001587,
+      "learning_rate": 0.00010916666666666666,
+      "loss": 0.472,
+      "mean_token_accuracy": 0.8672873705625535,
+      "num_tokens": 196017.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.4375,
+      "grad_norm": 1.7005512714385986,
+      "learning_rate": 0.000105,
+      "loss": 0.5119,
+      "mean_token_accuracy": 0.8617127776145935,
+      "num_tokens": 205263.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.488906741142273,
+      "learning_rate": 0.00010083333333333334,
+      "loss": 0.4911,
+      "mean_token_accuracy": 0.8672636389732361,
+      "num_tokens": 214207.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 1.4198739528656006,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 0.4975,
+      "mean_token_accuracy": 0.8657440841197968,
+      "num_tokens": 223185.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 1.7783927917480469,
+      "learning_rate": 9.250000000000001e-05,
+      "loss": 0.4264,
+      "mean_token_accuracy": 0.8798577606678009,
+      "num_tokens": 231929.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.6875,
+      "grad_norm": 1.6650081872940063,
+      "learning_rate": 8.833333333333333e-05,
+      "loss": 0.5051,
+      "mean_token_accuracy": 0.8662203460931778,
+      "num_tokens": 240854.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.7360109090805054,
+      "learning_rate": 8.416666666666668e-05,
+      "loss": 0.4374,
+      "mean_token_accuracy": 0.8734647989273071,
+      "num_tokens": 249782.0,
+      "step": 280
+    },
+    {
+      "epoch": 1.8125,
+      "grad_norm": 1.6823853254318237,
+      "learning_rate": 8e-05,
+      "loss": 0.5122,
+      "mean_token_accuracy": 0.8641923427581787,
+      "num_tokens": 258703.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.5906269550323486,
+      "learning_rate": 7.583333333333334e-05,
+      "loss": 0.4609,
+      "mean_token_accuracy": 0.870806086063385,
+      "num_tokens": 267959.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.9375,
+      "grad_norm": 1.8694252967834473,
+      "learning_rate": 7.166666666666667e-05,
+      "loss": 0.453,
+      "mean_token_accuracy": 0.8763782948255538,
+      "num_tokens": 276882.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.3819427490234375,
+      "learning_rate": 6.750000000000001e-05,
+      "loss": 0.461,
+      "mean_token_accuracy": 0.870858433842659,
+      "num_tokens": 285282.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.0625,
+      "grad_norm": 1.8256394863128662,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 0.2972,
+      "mean_token_accuracy": 0.9117195069789886,
+      "num_tokens": 293953.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 2.1064252853393555,
+      "learning_rate": 5.916666666666667e-05,
+      "loss": 0.2972,
+      "mean_token_accuracy": 0.9105454385280609,
+      "num_tokens": 302419.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 1.7595354318618774,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.2999,
+      "mean_token_accuracy": 0.9117335736751556,
+      "num_tokens": 311476.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 1.5239249467849731,
+      "learning_rate": 5.0833333333333333e-05,
+      "loss": 0.2678,
+      "mean_token_accuracy": 0.9190936297178268,
+      "num_tokens": 320231.0,
+      "step": 360
+    },
+    {
+      "epoch": 2.3125,
+      "grad_norm": 2.142015218734741,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.2834,
+      "mean_token_accuracy": 0.9148718416690826,
+      "num_tokens": 329086.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 1.3271563053131104,
+      "learning_rate": 4.25e-05,
+      "loss": 0.2828,
+      "mean_token_accuracy": 0.9135244160890579,
+      "num_tokens": 338575.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.4375,
+      "grad_norm": 2.033243417739868,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.2644,
+      "mean_token_accuracy": 0.9237385660409927,
+      "num_tokens": 347842.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 2.177577018737793,
+      "learning_rate": 3.4166666666666666e-05,
+      "loss": 0.2666,
+      "mean_token_accuracy": 0.9173466831445694,
+      "num_tokens": 356622.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.5625,
+      "grad_norm": 1.9091131687164307,
+      "learning_rate": 3e-05,
+      "loss": 0.2547,
+      "mean_token_accuracy": 0.9216690093278885,
+      "num_tokens": 365430.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 1.8569989204406738,
+      "learning_rate": 2.5833333333333336e-05,
+      "loss": 0.2641,
+      "mean_token_accuracy": 0.920384281873703,
+      "num_tokens": 374989.0,
+      "step": 420
+    },
+    {
+      "epoch": 2.6875,
+      "grad_norm": 2.433670997619629,
+      "learning_rate": 2.2083333333333333e-05,
+      "loss": 0.2929,
+      "mean_token_accuracy": 0.9130927324295044,
+      "num_tokens": 383763.0,
+      "step": 430
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 1.7513527870178223,
+      "learning_rate": 1.7916666666666667e-05,
+      "loss": 0.265,
+      "mean_token_accuracy": 0.9221676260232925,
+      "num_tokens": 392872.0,
+      "step": 440
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 2.320101737976074,
+      "learning_rate": 1.3750000000000002e-05,
+      "loss": 0.288,
+      "mean_token_accuracy": 0.915841493010521,
+      "num_tokens": 401207.0,
+      "step": 450
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 1.8214130401611328,
+      "learning_rate": 9.583333333333334e-06,
+      "loss": 0.2768,
+      "mean_token_accuracy": 0.9163581758737565,
+      "num_tokens": 410106.0,
+      "step": 460
+    },
+    {
+      "epoch": 2.9375,
+      "grad_norm": 2.07955265045166,
+      "learning_rate": 5.416666666666667e-06,
+      "loss": 0.2594,
+      "mean_token_accuracy": 0.924983486533165,
+      "num_tokens": 419029.0,
+      "step": 470
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.6197588443756104,
+      "learning_rate": 1.25e-06,
+      "loss": 0.2769,
+      "mean_token_accuracy": 0.9173476547002792,
+      "num_tokens": 427923.0,
+      "step": 480
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.081552109551616e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d142a4e903f8125c95aad77e6960ae2cdd942918ef108cf6a254a09fcdd1eac
+size 6161