Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-VL-3B-Instruct-AWQ
+library_name: peft
+---
+
+# 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 0.12.0

adapter_config.json

@@ -0,0 +1,279 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct-AWQ",
+  "bias": "none",
+  "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_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.11.self_attn.o_proj",
+    "model.layers.2.mlp.gate_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.34.self_attn.q_proj",
+    "model.layers.15.self_attn.k_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.8.mlp.gate_proj",
+    "model.layers.28.self_attn.k_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.13.self_attn.o_proj",
+    "model.layers.17.mlp.up_proj",
+    "model.layers.21.mlp.gate_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.15.mlp.down_proj",
+    "model.layers.18.mlp.gate_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.33.mlp.down_proj",
+    "model.layers.9.mlp.down_proj",
+    "model.layers.28.self_attn.v_proj",
+    "model.layers.4.mlp.gate_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.16.self_attn.k_proj",
+    "model.layers.14.mlp.down_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.11.self_attn.k_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.6.mlp.up_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.28.mlp.gate_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.24.self_attn.o_proj",
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.18.self_attn.o_proj",
+    "model.layers.29.mlp.down_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.24.mlp.up_proj",
+    "model.layers.19.self_attn.o_proj",
+    "model.layers.14.mlp.gate_proj",
+    "model.layers.18.self_attn.k_proj",
+    "model.layers.16.mlp.gate_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.34.mlp.up_proj",
+    "model.layers.22.mlp.down_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.19.mlp.gate_proj",
+    "model.layers.30.self_attn.o_proj",
+    "model.layers.31.self_attn.v_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.10.self_attn.k_proj",
+    "model.layers.20.mlp.down_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.11.mlp.up_proj",
+    "model.layers.5.mlp.gate_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.15.self_attn.o_proj",
+    "model.layers.27.self_attn.o_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.25.self_attn.k_proj",
+    "model.layers.32.mlp.gate_proj",
+    "model.layers.35.self_attn.k_proj",
+    "model.layers.30.self_attn.q_proj",
+    "model.layers.33.mlp.gate_proj",
+    "model.layers.34.mlp.down_proj",
+    "model.layers.32.self_attn.o_proj",
+    "model.layers.34.self_attn.v_proj",
+    "model.layers.0.self_attn.o_proj",
+    "model.layers.23.mlp.up_proj",
+    "model.layers.32.mlp.down_proj",
+    "model.layers.21.self_attn.k_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.35.mlp.gate_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.13.mlp.down_proj",
+    "model.layers.1.self_attn.o_proj",
+    "model.layers.23.self_attn.o_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.31.self_attn.q_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.35.mlp.down_proj",
+    "model.layers.9.mlp.up_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.13.mlp.up_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.23.self_attn.k_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.30.mlp.up_proj",
+    "model.layers.17.self_attn.k_proj",
+    "model.layers.31.self_attn.k_proj",
+    "model.layers.25.mlp.down_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.5.mlp.up_proj",
+    "model.layers.29.self_attn.v_proj",
+    "model.layers.11.mlp.gate_proj",
+    "model.layers.12.self_attn.o_proj",
+    "model.layers.32.self_attn.v_proj",
+    "model.layers.25.mlp.up_proj",
+    "model.layers.22.mlp.gate_proj",
+    "model.layers.9.self_attn.o_proj",
+    "model.layers.22.self_attn.o_proj",
+    "model.layers.9.mlp.gate_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.14.self_attn.o_proj",
+    "model.layers.34.self_attn.o_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.15.mlp.up_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.29.mlp.gate_proj",
+    "model.layers.35.self_attn.v_proj",
+    "model.layers.28.self_attn.q_proj",
+    "model.layers.3.mlp.up_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.10.self_attn.o_proj",
+    "model.layers.20.self_attn.o_proj",
+    "model.layers.26.mlp.down_proj",
+    "model.layers.7.mlp.down_proj",
+    "model.layers.31.mlp.down_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.24.mlp.gate_proj",
+    "model.layers.28.mlp.up_proj",
+    "model.layers.34.mlp.gate_proj",
+    "model.layers.17.self_attn.o_proj",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.22.self_attn.k_proj",
+    "model.layers.33.mlp.up_proj",
+    "model.layers.7.mlp.up_proj",
+    "model.layers.12.mlp.down_proj",
+    "model.layers.26.mlp.up_proj",
+    "model.layers.10.mlp.up_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.21.mlp.down_proj",
+    "model.layers.25.mlp.gate_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.29.self_attn.q_proj",
+    "model.layers.35.self_attn.o_proj",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.9.self_attn.k_proj",
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.29.self_attn.k_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.31.mlp.up_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.20.mlp.up_proj",
+    "model.layers.21.mlp.up_proj",
+    "model.layers.30.self_attn.k_proj",
+    "model.layers.16.mlp.up_proj",
+    "model.layers.11.mlp.down_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.20.mlp.gate_proj",
+    "model.layers.8.self_attn.o_proj",
+    "model.layers.16.self_attn.o_proj",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.35.mlp.up_proj",
+    "model.layers.17.mlp.down_proj",
+    "model.layers.34.self_attn.k_proj",
+    "model.layers.30.mlp.down_proj",
+    "model.layers.8.mlp.up_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.30.mlp.gate_proj",
+    "model.layers.14.mlp.up_proj",
+    "model.layers.27.mlp.up_proj",
+    "model.layers.35.self_attn.q_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.12.mlp.up_proj",
+    "model.layers.18.mlp.down_proj",
+    "model.layers.26.self_attn.k_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.13.self_attn.k_proj",
+    "model.layers.28.self_attn.o_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.31.mlp.gate_proj",
+    "model.layers.1.mlp.up_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.19.self_attn.k_proj",
+    "model.layers.26.self_attn.o_proj",
+    "model.layers.33.self_attn.q_proj",
+    "model.layers.4.self_attn.o_proj",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.23.mlp.gate_proj",
+    "model.layers.6.mlp.gate_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.13.mlp.gate_proj",
+    "model.layers.14.self_attn.k_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.19.mlp.down_proj",
+    "model.layers.30.self_attn.v_proj",
+    "model.layers.27.mlp.down_proj",
+    "model.layers.32.self_attn.q_proj",
+    "model.layers.29.mlp.up_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.23.mlp.down_proj",
+    "model.layers.17.mlp.gate_proj",
+    "model.layers.8.self_attn.k_proj",
+    "model.layers.12.self_attn.k_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.18.mlp.up_proj",
+    "model.layers.10.mlp.gate_proj",
+    "model.layers.1.mlp.gate_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.24.self_attn.k_proj",
+    "model.layers.7.mlp.gate_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.15.mlp.gate_proj",
+    "model.layers.21.self_attn.o_proj",
+    "model.layers.8.mlp.down_proj",
+    "model.layers.20.self_attn.k_proj",
+    "model.layers.22.mlp.up_proj",
+    "model.layers.26.mlp.gate_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.32.mlp.up_proj",
+    "model.layers.32.self_attn.k_proj",
+    "model.layers.10.mlp.down_proj",
+    "model.layers.24.mlp.down_proj",
+    "model.layers.27.mlp.gate_proj",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.12.mlp.gate_proj",
+    "model.layers.27.self_attn.k_proj",
+    "model.layers.19.mlp.up_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.25.self_attn.o_proj",
+    "model.layers.16.mlp.down_proj",
+    "model.layers.6.mlp.down_proj",
+    "model.layers.31.self_attn.o_proj",
+    "model.layers.33.self_attn.v_proj",
+    "model.layers.33.self_attn.o_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.33.self_attn.k_proj",
+    "model.layers.28.mlp.down_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.29.self_attn.o_proj",
+    "model.layers.16.self_attn.q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cef54a2a0c8c0b947fc558f2573f77be82470f2bf6f5dedee8417fd1cae0a5c4
+size 59933632

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 60000,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3141 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9966329966329965,
+  "eval_steps": 500,
+  "global_step": 444,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006734006734006734,
+      "grad_norm": 0.4674329161643982,
+      "learning_rate": 2.702702702702703e-07,
+      "loss": 0.8878,
+      "step": 1
+    },
+    {
+      "epoch": 0.013468013468013467,
+      "grad_norm": 0.4288882613182068,
+      "learning_rate": 5.405405405405406e-07,
+      "loss": 0.9554,
+      "step": 2
+    },
+    {
+      "epoch": 0.020202020202020204,
+      "grad_norm": 0.4333876669406891,
+      "learning_rate": 8.108108108108109e-07,
+      "loss": 0.9565,
+      "step": 3
+    },
+    {
+      "epoch": 0.026936026936026935,
+      "grad_norm": 0.4596662223339081,
+      "learning_rate": 1.0810810810810812e-06,
+      "loss": 0.9475,
+      "step": 4
+    },
+    {
+      "epoch": 0.03367003367003367,
+      "grad_norm": 0.476782888174057,
+      "learning_rate": 1.3513513513513515e-06,
+      "loss": 0.9307,
+      "step": 5
+    },
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 0.4502452313899994,
+      "learning_rate": 1.6216216216216219e-06,
+      "loss": 0.9489,
+      "step": 6
+    },
+    {
+      "epoch": 0.04713804713804714,
+      "grad_norm": 0.4531259536743164,
+      "learning_rate": 1.8918918918918922e-06,
+      "loss": 0.9744,
+      "step": 7
+    },
+    {
+      "epoch": 0.05387205387205387,
+      "grad_norm": 0.45402348041534424,
+      "learning_rate": 2.1621621621621623e-06,
+      "loss": 0.9425,
+      "step": 8
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 0.44291701912879944,
+      "learning_rate": 2.432432432432433e-06,
+      "loss": 0.9487,
+      "step": 9
+    },
+    {
+      "epoch": 0.06734006734006734,
+      "grad_norm": 0.4839108884334564,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 0.9382,
+      "step": 10
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.44631311297416687,
+      "learning_rate": 2.9729729729729736e-06,
+      "loss": 0.8985,
+      "step": 11
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 0.4725789427757263,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 0.9924,
+      "step": 12
+    },
+    {
+      "epoch": 0.08754208754208755,
+      "grad_norm": 0.4641851782798767,
+      "learning_rate": 3.513513513513514e-06,
+      "loss": 0.9142,
+      "step": 13
+    },
+    {
+      "epoch": 0.09427609427609428,
+      "grad_norm": 0.46973735094070435,
+      "learning_rate": 3.7837837837837844e-06,
+      "loss": 0.9383,
+      "step": 14
+    },
+    {
+      "epoch": 0.10101010101010101,
+      "grad_norm": 0.4747369885444641,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 0.9133,
+      "step": 15
+    },
+    {
+      "epoch": 0.10774410774410774,
+      "grad_norm": 0.4584101140499115,
+      "learning_rate": 4.324324324324325e-06,
+      "loss": 0.927,
+      "step": 16
+    },
+    {
+      "epoch": 0.11447811447811448,
+      "grad_norm": 0.4609006345272064,
+      "learning_rate": 4.594594594594596e-06,
+      "loss": 0.932,
+      "step": 17
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 0.4389339089393616,
+      "learning_rate": 4.864864864864866e-06,
+      "loss": 0.9318,
+      "step": 18
+    },
+    {
+      "epoch": 0.12794612794612795,
+      "grad_norm": 0.47249212861061096,
+      "learning_rate": 5.135135135135135e-06,
+      "loss": 0.9359,
+      "step": 19
+    },
+    {
+      "epoch": 0.13468013468013468,
+      "grad_norm": 0.46650782227516174,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 0.9073,
+      "step": 20
+    },
+    {
+      "epoch": 0.1414141414141414,
+      "grad_norm": 0.4591180980205536,
+      "learning_rate": 5.675675675675676e-06,
+      "loss": 0.9505,
+      "step": 21
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.49153509736061096,
+      "learning_rate": 5.945945945945947e-06,
+      "loss": 0.9104,
+      "step": 22
+    },
+    {
+      "epoch": 0.15488215488215487,
+      "grad_norm": 0.4966362416744232,
+      "learning_rate": 6.2162162162162164e-06,
+      "loss": 0.905,
+      "step": 23
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.4932939112186432,
+      "learning_rate": 6.486486486486487e-06,
+      "loss": 0.9592,
+      "step": 24
+    },
+    {
+      "epoch": 0.16835016835016836,
+      "grad_norm": 0.4675721824169159,
+      "learning_rate": 6.7567567567567575e-06,
+      "loss": 0.9215,
+      "step": 25
+    },
+    {
+      "epoch": 0.1750841750841751,
+      "grad_norm": 0.47080472111701965,
+      "learning_rate": 7.027027027027028e-06,
+      "loss": 0.9972,
+      "step": 26
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.4835442304611206,
+      "learning_rate": 7.297297297297298e-06,
+      "loss": 0.9141,
+      "step": 27
+    },
+    {
+      "epoch": 0.18855218855218855,
+      "grad_norm": 0.47605717182159424,
+      "learning_rate": 7.567567567567569e-06,
+      "loss": 0.9398,
+      "step": 28
+    },
+    {
+      "epoch": 0.19528619528619529,
+      "grad_norm": 0.4614209830760956,
+      "learning_rate": 7.837837837837838e-06,
+      "loss": 0.9129,
+      "step": 29
+    },
+    {
+      "epoch": 0.20202020202020202,
+      "grad_norm": 0.4712672531604767,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 0.9007,
+      "step": 30
+    },
+    {
+      "epoch": 0.20875420875420875,
+      "grad_norm": 0.4813186228275299,
+      "learning_rate": 8.378378378378378e-06,
+      "loss": 0.9331,
+      "step": 31
+    },
+    {
+      "epoch": 0.21548821548821548,
+      "grad_norm": 0.466824471950531,
+      "learning_rate": 8.64864864864865e-06,
+      "loss": 0.9479,
+      "step": 32
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.47713014483451843,
+      "learning_rate": 8.91891891891892e-06,
+      "loss": 0.9298,
+      "step": 33
+    },
+    {
+      "epoch": 0.22895622895622897,
+      "grad_norm": 0.4705861210823059,
+      "learning_rate": 9.189189189189191e-06,
+      "loss": 0.9446,
+      "step": 34
+    },
+    {
+      "epoch": 0.2356902356902357,
+      "grad_norm": 0.44828763604164124,
+      "learning_rate": 9.45945945945946e-06,
+      "loss": 0.9153,
+      "step": 35
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.4529784321784973,
+      "learning_rate": 9.729729729729732e-06,
+      "loss": 0.8959,
+      "step": 36
+    },
+    {
+      "epoch": 0.24915824915824916,
+      "grad_norm": 0.4544116258621216,
+      "learning_rate": 1e-05,
+      "loss": 0.9358,
+      "step": 37
+    },
+    {
+      "epoch": 0.2558922558922559,
+      "grad_norm": 0.47299325466156006,
+      "learning_rate": 9.999950073815046e-06,
+      "loss": 0.913,
+      "step": 38
+    },
+    {
+      "epoch": 0.26262626262626265,
+      "grad_norm": 0.46356692910194397,
+      "learning_rate": 9.999800296257234e-06,
+      "loss": 0.9063,
+      "step": 39
+    },
+    {
+      "epoch": 0.26936026936026936,
+      "grad_norm": 0.4557459056377411,
+      "learning_rate": 9.99955067031769e-06,
+      "loss": 0.9597,
+      "step": 40
+    },
+    {
+      "epoch": 0.2760942760942761,
+      "grad_norm": 0.4265868365764618,
+      "learning_rate": 9.999201200981566e-06,
+      "loss": 0.8871,
+      "step": 41
+    },
+    {
+      "epoch": 0.2828282828282828,
+      "grad_norm": 0.4292503297328949,
+      "learning_rate": 9.998751895227927e-06,
+      "loss": 0.8867,
+      "step": 42
+    },
+    {
+      "epoch": 0.2895622895622896,
+      "grad_norm": 0.3973385989665985,
+      "learning_rate": 9.998202762029626e-06,
+      "loss": 0.8663,
+      "step": 43
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.4129696190357208,
+      "learning_rate": 9.997553812353106e-06,
+      "loss": 0.8981,
+      "step": 44
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.4138651192188263,
+      "learning_rate": 9.996805059158208e-06,
+      "loss": 0.8688,
+      "step": 45
+    },
+    {
+      "epoch": 0.30976430976430974,
+      "grad_norm": 0.4028445780277252,
+      "learning_rate": 9.995956517397884e-06,
+      "loss": 0.9049,
+      "step": 46
+    },
+    {
+      "epoch": 0.3164983164983165,
+      "grad_norm": 0.3888985812664032,
+      "learning_rate": 9.995008204017914e-06,
+      "loss": 0.8332,
+      "step": 47
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.36326923966407776,
+      "learning_rate": 9.99396013795657e-06,
+      "loss": 0.8285,
+      "step": 48
+    },
+    {
+      "epoch": 0.32996632996632996,
+      "grad_norm": 0.343104749917984,
+      "learning_rate": 9.992812340144225e-06,
+      "loss": 0.8576,
+      "step": 49
+    },
+    {
+      "epoch": 0.3367003367003367,
+      "grad_norm": 0.3436315059661865,
+      "learning_rate": 9.991564833502944e-06,
+      "loss": 0.8509,
+      "step": 50
+    },
+    {
+      "epoch": 0.3434343434343434,
+      "grad_norm": 0.33012041449546814,
+      "learning_rate": 9.990217642946028e-06,
+      "loss": 0.8635,
+      "step": 51
+    },
+    {
+      "epoch": 0.3501683501683502,
+      "grad_norm": 0.32571494579315186,
+      "learning_rate": 9.988770795377512e-06,
+      "loss": 0.8585,
+      "step": 52
+    },
+    {
+      "epoch": 0.3569023569023569,
+      "grad_norm": 0.29031604528427124,
+      "learning_rate": 9.987224319691624e-06,
+      "loss": 0.8599,
+      "step": 53
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.2973954975605011,
+      "learning_rate": 9.98557824677222e-06,
+      "loss": 0.8528,
+      "step": 54
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.2861897945404053,
+      "learning_rate": 9.983832609492154e-06,
+      "loss": 0.8689,
+      "step": 55
+    },
+    {
+      "epoch": 0.3771043771043771,
+      "grad_norm": 0.2961727976799011,
+      "learning_rate": 9.981987442712634e-06,
+      "loss": 0.837,
+      "step": 56
+    },
+    {
+      "epoch": 0.3838383838383838,
+      "grad_norm": 0.28357475996017456,
+      "learning_rate": 9.98004278328251e-06,
+      "loss": 0.8244,
+      "step": 57
+    },
+    {
+      "epoch": 0.39057239057239057,
+      "grad_norm": 0.2743470370769501,
+      "learning_rate": 9.977998670037554e-06,
+      "loss": 0.8737,
+      "step": 58
+    },
+    {
+      "epoch": 0.39730639730639733,
+      "grad_norm": 0.2749946117401123,
+      "learning_rate": 9.97585514379968e-06,
+      "loss": 0.8848,
+      "step": 59
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.2607375979423523,
+      "learning_rate": 9.973612247376118e-06,
+      "loss": 0.8432,
+      "step": 60
+    },
+    {
+      "epoch": 0.4107744107744108,
+      "grad_norm": 0.25835004448890686,
+      "learning_rate": 9.971270025558576e-06,
+      "loss": 0.8362,
+      "step": 61
+    },
+    {
+      "epoch": 0.4175084175084175,
+      "grad_norm": 0.24998688697814941,
+      "learning_rate": 9.968828525122331e-06,
+      "loss": 0.7833,
+      "step": 62
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 0.25704672932624817,
+      "learning_rate": 9.966287794825305e-06,
+      "loss": 0.8186,
+      "step": 63
+    },
+    {
+      "epoch": 0.43097643097643096,
+      "grad_norm": 0.2764415740966797,
+      "learning_rate": 9.963647885407088e-06,
+      "loss": 0.798,
+      "step": 64
+    },
+    {
+      "epoch": 0.4377104377104377,
+      "grad_norm": 0.2261701226234436,
+      "learning_rate": 9.960908849587922e-06,
+      "loss": 0.7783,
+      "step": 65
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.26680904626846313,
+      "learning_rate": 9.958070742067649e-06,
+      "loss": 0.836,
+      "step": 66
+    },
+    {
+      "epoch": 0.4511784511784512,
+      "grad_norm": 0.23155707120895386,
+      "learning_rate": 9.955133619524623e-06,
+      "loss": 0.7938,
+      "step": 67
+    },
+    {
+      "epoch": 0.45791245791245794,
+      "grad_norm": 0.2517130374908447,
+      "learning_rate": 9.952097540614571e-06,
+      "loss": 0.8131,
+      "step": 68
+    },
+    {
+      "epoch": 0.46464646464646464,
+      "grad_norm": 0.2457548826932907,
+      "learning_rate": 9.948962565969431e-06,
+      "loss": 0.8164,
+      "step": 69
+    },
+    {
+      "epoch": 0.4713804713804714,
+      "grad_norm": 0.22898763418197632,
+      "learning_rate": 9.945728758196129e-06,
+      "loss": 0.7757,
+      "step": 70
+    },
+    {
+      "epoch": 0.4781144781144781,
+      "grad_norm": 0.2146165817975998,
+      "learning_rate": 9.942396181875342e-06,
+      "loss": 0.8254,
+      "step": 71
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.232045978307724,
+      "learning_rate": 9.938964903560198e-06,
+      "loss": 0.8173,
+      "step": 72
+    },
+    {
+      "epoch": 0.49158249158249157,
+      "grad_norm": 0.22347578406333923,
+      "learning_rate": 9.935434991774951e-06,
+      "loss": 0.8228,
+      "step": 73
+    },
+    {
+      "epoch": 0.4983164983164983,
+      "grad_norm": 0.22920922935009003,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 0.8275,
+      "step": 74
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 0.24698615074157715,
+      "learning_rate": 9.928079551738542e-06,
+      "loss": 0.8209,
+      "step": 75
+    },
+    {
+      "epoch": 0.5117845117845118,
+      "grad_norm": 0.23692172765731812,
+      "learning_rate": 9.924254170379007e-06,
+      "loss": 0.8215,
+      "step": 76
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.24865996837615967,
+      "learning_rate": 9.92033044932968e-06,
+      "loss": 0.7984,
+      "step": 77
+    },
+    {
+      "epoch": 0.5252525252525253,
+      "grad_norm": 0.23505768179893494,
+      "learning_rate": 9.916308466949134e-06,
+      "loss": 0.8014,
+      "step": 78
+    },
+    {
+      "epoch": 0.531986531986532,
+      "grad_norm": 0.2524789869785309,
+      "learning_rate": 9.912188303558263e-06,
+      "loss": 0.8097,
+      "step": 79
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 0.25673165917396545,
+      "learning_rate": 9.907970041438683e-06,
+      "loss": 0.8022,
+      "step": 80
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.2574709355831146,
+      "learning_rate": 9.903653764831088e-06,
+      "loss": 0.7995,
+      "step": 81
+    },
+    {
+      "epoch": 0.5521885521885522,
+      "grad_norm": 0.2411055862903595,
+      "learning_rate": 9.899239559933566e-06,
+      "loss": 0.7819,
+      "step": 82
+    },
+    {
+      "epoch": 0.5589225589225589,
+      "grad_norm": 0.24539045989513397,
+      "learning_rate": 9.894727514899883e-06,
+      "loss": 0.7956,
+      "step": 83
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 0.23138682544231415,
+      "learning_rate": 9.890117719837716e-06,
+      "loss": 0.7713,
+      "step": 84
+    },
+    {
+      "epoch": 0.5723905723905723,
+      "grad_norm": 0.21052764356136322,
+      "learning_rate": 9.885410266806858e-06,
+      "loss": 0.8155,
+      "step": 85
+    },
+    {
+      "epoch": 0.5791245791245792,
+      "grad_norm": 0.2486884891986847,
+      "learning_rate": 9.880605249817377e-06,
+      "loss": 0.8076,
+      "step": 86
+    },
+    {
+      "epoch": 0.5858585858585859,
+      "grad_norm": 0.2390533983707428,
+      "learning_rate": 9.875702764827739e-06,
+      "loss": 0.7993,
+      "step": 87
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.2276839017868042,
+      "learning_rate": 9.870702909742893e-06,
+      "loss": 0.776,
+      "step": 88
+    },
+    {
+      "epoch": 0.5993265993265994,
+      "grad_norm": 0.25543203949928284,
+      "learning_rate": 9.865605784412316e-06,
+      "loss": 0.7935,
+      "step": 89
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.23849958181381226,
+      "learning_rate": 9.860411490628017e-06,
+      "loss": 0.8,
+      "step": 90
+    },
+    {
+      "epoch": 0.6127946127946128,
+      "grad_norm": 0.22977019846439362,
+      "learning_rate": 9.855120132122503e-06,
+      "loss": 0.7497,
+      "step": 91
+    },
+    {
+      "epoch": 0.6195286195286195,
+      "grad_norm": 0.21937815845012665,
+      "learning_rate": 9.849731814566713e-06,
+      "loss": 0.7862,
+      "step": 92
+    },
+    {
+      "epoch": 0.6262626262626263,
+      "grad_norm": 0.23629795014858246,
+      "learning_rate": 9.844246645567903e-06,
+      "loss": 0.7901,
+      "step": 93
+    },
+    {
+      "epoch": 0.632996632996633,
+      "grad_norm": 0.22892089188098907,
+      "learning_rate": 9.838664734667496e-06,
+      "loss": 0.7674,
+      "step": 94
+    },
+    {
+      "epoch": 0.6397306397306397,
+      "grad_norm": 0.21019472181797028,
+      "learning_rate": 9.832986193338898e-06,
+      "loss": 0.779,
+      "step": 95
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.2447926104068756,
+      "learning_rate": 9.827211134985273e-06,
+      "loss": 0.7801,
+      "step": 96
+    },
+    {
+      "epoch": 0.6531986531986532,
+      "grad_norm": 0.23594583570957184,
+      "learning_rate": 9.821339674937274e-06,
+      "loss": 0.8055,
+      "step": 97
+    },
+    {
+      "epoch": 0.6599326599326599,
+      "grad_norm": 0.22600403428077698,
+      "learning_rate": 9.815371930450737e-06,
+      "loss": 0.8169,
+      "step": 98
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.24343664944171906,
+      "learning_rate": 9.809308020704353e-06,
+      "loss": 0.7987,
+      "step": 99
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "grad_norm": 0.22726725041866302,
+      "learning_rate": 9.80314806679727e-06,
+      "loss": 0.7347,
+      "step": 100
+    },
+    {
+      "epoch": 0.6801346801346801,
+      "grad_norm": 0.22291769087314606,
+      "learning_rate": 9.79689219174669e-06,
+      "loss": 0.7644,
+      "step": 101
+    },
+    {
+      "epoch": 0.6868686868686869,
+      "grad_norm": 0.24143223464488983,
+      "learning_rate": 9.790540520485402e-06,
+      "loss": 0.7759,
+      "step": 102
+    },
+    {
+      "epoch": 0.6936026936026936,
+      "grad_norm": 0.2362246811389923,
+      "learning_rate": 9.78409317985929e-06,
+      "loss": 0.8292,
+      "step": 103
+    },
+    {
+      "epoch": 0.7003367003367004,
+      "grad_norm": 0.2230088859796524,
+      "learning_rate": 9.777550298624805e-06,
+      "loss": 0.7516,
+      "step": 104
+    },
+    {
+      "epoch": 0.7070707070707071,
+      "grad_norm": 0.22827690839767456,
+      "learning_rate": 9.770912007446385e-06,
+      "loss": 0.7386,
+      "step": 105
+    },
+    {
+      "epoch": 0.7138047138047138,
+      "grad_norm": 0.2498016208410263,
+      "learning_rate": 9.76417843889385e-06,
+      "loss": 0.7624,
+      "step": 106
+    },
+    {
+      "epoch": 0.7205387205387206,
+      "grad_norm": 0.21709798276424408,
+      "learning_rate": 9.757349727439759e-06,
+      "loss": 0.764,
+      "step": 107
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.21755844354629517,
+      "learning_rate": 9.750426009456713e-06,
+      "loss": 0.7877,
+      "step": 108
+    },
+    {
+      "epoch": 0.734006734006734,
+      "grad_norm": 0.227566659450531,
+      "learning_rate": 9.743407423214643e-06,
+      "loss": 0.7611,
+      "step": 109
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.2640649676322937,
+      "learning_rate": 9.736294108878044e-06,
+      "loss": 0.7729,
+      "step": 110
+    },
+    {
+      "epoch": 0.7474747474747475,
+      "grad_norm": 0.2128470242023468,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 0.7576,
+      "step": 111
+    },
+    {
+      "epoch": 0.7542087542087542,
+      "grad_norm": 0.22666677832603455,
+      "learning_rate": 9.72178386603522e-06,
+      "loss": 0.7779,
+      "step": 112
+    },
+    {
+      "epoch": 0.7609427609427609,
+      "grad_norm": 0.21836517751216888,
+      "learning_rate": 9.714387227305422e-06,
+      "loss": 0.7299,
+      "step": 113
+    },
+    {
+      "epoch": 0.7676767676767676,
+      "grad_norm": 0.2525302469730377,
+      "learning_rate": 9.70689644002816e-06,
+      "loss": 0.7633,
+      "step": 114
+    },
+    {
+      "epoch": 0.7744107744107744,
+      "grad_norm": 0.24227039515972137,
+      "learning_rate": 9.69931165379801e-06,
+      "loss": 0.785,
+      "step": 115
+    },
+    {
+      "epoch": 0.7811447811447811,
+      "grad_norm": 0.22788166999816895,
+      "learning_rate": 9.691633020086745e-06,
+      "loss": 0.7537,
+      "step": 116
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.24258917570114136,
+      "learning_rate": 9.683860692240322e-06,
+      "loss": 0.7695,
+      "step": 117
+    },
+    {
+      "epoch": 0.7946127946127947,
+      "grad_norm": 0.23187682032585144,
+      "learning_rate": 9.67599482547581e-06,
+      "loss": 0.7411,
+      "step": 118
+    },
+    {
+      "epoch": 0.8013468013468014,
+      "grad_norm": 0.23363040387630463,
+      "learning_rate": 9.668035576878296e-06,
+      "loss": 0.749,
+      "step": 119
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.2519008219242096,
+      "learning_rate": 9.65998310539775e-06,
+      "loss": 0.7784,
+      "step": 120
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.22125515341758728,
+      "learning_rate": 9.651837571845842e-06,
+      "loss": 0.7455,
+      "step": 121
+    },
+    {
+      "epoch": 0.8215488215488216,
+      "grad_norm": 0.25824788212776184,
+      "learning_rate": 9.643599138892737e-06,
+      "loss": 0.7614,
+      "step": 122
+    },
+    {
+      "epoch": 0.8282828282828283,
+      "grad_norm": 0.23877231776714325,
+      "learning_rate": 9.635267971063848e-06,
+      "loss": 0.765,
+      "step": 123
+    },
+    {
+      "epoch": 0.835016835016835,
+      "grad_norm": 0.2506805956363678,
+      "learning_rate": 9.626844234736546e-06,
+      "loss": 0.7746,
+      "step": 124
+    },
+    {
+      "epoch": 0.8417508417508418,
+      "grad_norm": 0.2351042479276657,
+      "learning_rate": 9.618328098136838e-06,
+      "loss": 0.7471,
+      "step": 125
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.25443699955940247,
+      "learning_rate": 9.609719731336005e-06,
+      "loss": 0.77,
+      "step": 126
+    },
+    {
+      "epoch": 0.8552188552188552,
+      "grad_norm": 0.23053216934204102,
+      "learning_rate": 9.601019306247214e-06,
+      "loss": 0.7415,
+      "step": 127
+    },
+    {
+      "epoch": 0.8619528619528619,
+      "grad_norm": 0.24876555800437927,
+      "learning_rate": 9.59222699662208e-06,
+      "loss": 0.7723,
+      "step": 128
+    },
+    {
+      "epoch": 0.8686868686868687,
+      "grad_norm": 0.230879545211792,
+      "learning_rate": 9.58334297804719e-06,
+      "loss": 0.773,
+      "step": 129
+    },
+    {
+      "epoch": 0.8754208754208754,
+      "grad_norm": 0.267036110162735,
+      "learning_rate": 9.574367427940609e-06,
+      "loss": 0.7782,
+      "step": 130
+    },
+    {
+      "epoch": 0.8821548821548821,
+      "grad_norm": 0.2757895588874817,
+      "learning_rate": 9.565300525548327e-06,
+      "loss": 0.7624,
+      "step": 131
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.2372322976589203,
+      "learning_rate": 9.55614245194068e-06,
+      "loss": 0.7282,
+      "step": 132
+    },
+    {
+      "epoch": 0.8956228956228957,
+      "grad_norm": 0.23569901287555695,
+      "learning_rate": 9.546893390008737e-06,
+      "loss": 0.75,
+      "step": 133
+    },
+    {
+      "epoch": 0.9023569023569024,
+      "grad_norm": 0.24758505821228027,
+      "learning_rate": 9.537553524460656e-06,
+      "loss": 0.7947,
+      "step": 134
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.23305581510066986,
+      "learning_rate": 9.528123041817972e-06,
+      "loss": 0.7617,
+      "step": 135
+    },
+    {
+      "epoch": 0.9158249158249159,
+      "grad_norm": 0.23048968613147736,
+      "learning_rate": 9.518602130411894e-06,
+      "loss": 0.7707,
+      "step": 136
+    },
+    {
+      "epoch": 0.9225589225589226,
+      "grad_norm": 0.2431011199951172,
+      "learning_rate": 9.508990980379537e-06,
+      "loss": 0.742,
+      "step": 137
+    },
+    {
+      "epoch": 0.9292929292929293,
+      "grad_norm": 0.23194094002246857,
+      "learning_rate": 9.499289783660126e-06,
+      "loss": 0.7617,
+      "step": 138
+    },
+    {
+      "epoch": 0.936026936026936,
+      "grad_norm": 0.24811971187591553,
+      "learning_rate": 9.489498733991151e-06,
+      "loss": 0.7579,
+      "step": 139
+    },
+    {
+      "epoch": 0.9427609427609428,
+      "grad_norm": 0.24215534329414368,
+      "learning_rate": 9.47961802690452e-06,
+      "loss": 0.7752,
+      "step": 140
+    },
+    {
+      "epoch": 0.9494949494949495,
+      "grad_norm": 0.22330717742443085,
+      "learning_rate": 9.469647859722634e-06,
+      "loss": 0.738,
+      "step": 141
+    },
+    {
+      "epoch": 0.9562289562289562,
+      "grad_norm": 0.23054972290992737,
+      "learning_rate": 9.459588431554458e-06,
+      "loss": 0.7754,
+      "step": 142
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 0.2682708203792572,
+      "learning_rate": 9.449439943291541e-06,
+      "loss": 0.6985,
+      "step": 143
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.23973660171031952,
+      "learning_rate": 9.439202597604004e-06,
+      "loss": 0.7323,
+      "step": 144
+    },
+    {
+      "epoch": 0.9764309764309764,
+      "grad_norm": 0.23046766221523285,
+      "learning_rate": 9.42887659893649e-06,
+      "loss": 0.7203,
+      "step": 145
+    },
+    {
+      "epoch": 0.9831649831649831,
+      "grad_norm": 0.24555841088294983,
+      "learning_rate": 9.41846215350409e-06,
+      "loss": 0.7499,
+      "step": 146
+    },
+    {
+      "epoch": 0.98989898989899,
+      "grad_norm": 0.25212836265563965,
+      "learning_rate": 9.407959469288215e-06,
+      "loss": 0.745,
+      "step": 147
+    },
+    {
+      "epoch": 0.9966329966329966,
+      "grad_norm": 0.23800650238990784,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 0.7439,
+      "step": 148
+    },
+    {
+      "epoch": 1.0067340067340067,
+      "grad_norm": 0.28960976004600525,
+      "learning_rate": 9.386690225238346e-06,
+      "loss": 0.9352,
+      "step": 149
+    },
+    {
+      "epoch": 1.0134680134680134,
+      "grad_norm": 0.23404806852340698,
+      "learning_rate": 9.375924090161238e-06,
+      "loss": 0.7395,
+      "step": 150
+    },
+    {
+      "epoch": 1.02020202020202,
+      "grad_norm": 0.2719663381576538,
+      "learning_rate": 9.365070565805941e-06,
+      "loss": 0.7852,
+      "step": 151
+    },
+    {
+      "epoch": 1.026936026936027,
+      "grad_norm": 0.2808714807033539,
+      "learning_rate": 9.354129868922483e-06,
+      "loss": 0.7412,
+      "step": 152
+    },
+    {
+      "epoch": 1.0336700336700337,
+      "grad_norm": 0.23448531329631805,
+      "learning_rate": 9.343102218001763e-06,
+      "loss": 0.7073,
+      "step": 153
+    },
+    {
+      "epoch": 1.0404040404040404,
+      "grad_norm": 0.24488256871700287,
+      "learning_rate": 9.331987833271199e-06,
+      "loss": 0.7665,
+      "step": 154
+    },
+    {
+      "epoch": 1.0471380471380471,
+      "grad_norm": 0.27663859724998474,
+      "learning_rate": 9.32078693669032e-06,
+      "loss": 0.7074,
+      "step": 155
+    },
+    {
+      "epoch": 1.0538720538720538,
+      "grad_norm": 0.25091904401779175,
+      "learning_rate": 9.309499751946345e-06,
+      "loss": 0.7394,
+      "step": 156
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.25539129972457886,
+      "learning_rate": 9.298126504449697e-06,
+      "loss": 0.7411,
+      "step": 157
+    },
+    {
+      "epoch": 1.0673400673400673,
+      "grad_norm": 0.24508924782276154,
+      "learning_rate": 9.286667421329523e-06,
+      "loss": 0.7413,
+      "step": 158
+    },
+    {
+      "epoch": 1.074074074074074,
+      "grad_norm": 0.2480177879333496,
+      "learning_rate": 9.275122731429142e-06,
+      "loss": 0.773,
+      "step": 159
+    },
+    {
+      "epoch": 1.0808080808080809,
+      "grad_norm": 0.23678265511989594,
+      "learning_rate": 9.263492665301486e-06,
+      "loss": 0.7516,
+      "step": 160
+    },
+    {
+      "epoch": 1.0875420875420876,
+      "grad_norm": 0.24282552301883698,
+      "learning_rate": 9.251777455204485e-06,
+      "loss": 0.7634,
+      "step": 161
+    },
+    {
+      "epoch": 1.0942760942760943,
+      "grad_norm": 0.2432844042778015,
+      "learning_rate": 9.239977335096439e-06,
+      "loss": 0.7366,
+      "step": 162
+    },
+    {
+      "epoch": 1.101010101010101,
+      "grad_norm": 0.30914798378944397,
+      "learning_rate": 9.228092540631342e-06,
+      "loss": 0.7038,
+      "step": 163
+    },
+    {
+      "epoch": 1.1077441077441077,
+      "grad_norm": 0.24757800996303558,
+      "learning_rate": 9.216123309154169e-06,
+      "loss": 0.7019,
+      "step": 164
+    },
+    {
+      "epoch": 1.1144781144781144,
+      "grad_norm": 0.25173789262771606,
+      "learning_rate": 9.204069879696144e-06,
+      "loss": 0.7032,
+      "step": 165
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.25156348943710327,
+      "learning_rate": 9.191932492969972e-06,
+      "loss": 0.7092,
+      "step": 166
+    },
+    {
+      "epoch": 1.127946127946128,
+      "grad_norm": 0.23508214950561523,
+      "learning_rate": 9.179711391365015e-06,
+      "loss": 0.6959,
+      "step": 167
+    },
+    {
+      "epoch": 1.1346801346801347,
+      "grad_norm": 0.24067312479019165,
+      "learning_rate": 9.167406818942468e-06,
+      "loss": 0.6855,
+      "step": 168
+    },
+    {
+      "epoch": 1.1414141414141414,
+      "grad_norm": 0.24786119163036346,
+      "learning_rate": 9.155019021430469e-06,
+      "loss": 0.7041,
+      "step": 169
+    },
+    {
+      "epoch": 1.1481481481481481,
+      "grad_norm": 0.24527166783809662,
+      "learning_rate": 9.142548246219212e-06,
+      "loss": 0.7275,
+      "step": 170
+    },
+    {
+      "epoch": 1.1548821548821548,
+      "grad_norm": 0.25038015842437744,
+      "learning_rate": 9.129994742355985e-06,
+      "loss": 0.7218,
+      "step": 171
+    },
+    {
+      "epoch": 1.1616161616161615,
+      "grad_norm": 0.2645305395126343,
+      "learning_rate": 9.117358760540211e-06,
+      "loss": 0.7219,
+      "step": 172
+    },
+    {
+      "epoch": 1.1683501683501682,
+      "grad_norm": 0.2419489324092865,
+      "learning_rate": 9.104640553118436e-06,
+      "loss": 0.7023,
+      "step": 173
+    },
+    {
+      "epoch": 1.1750841750841752,
+      "grad_norm": 0.2727682888507843,
+      "learning_rate": 9.09184037407929e-06,
+      "loss": 0.7432,
+      "step": 174
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.23827053606510162,
+      "learning_rate": 9.078958479048419e-06,
+      "loss": 0.7002,
+      "step": 175
+    },
+    {
+      "epoch": 1.1885521885521886,
+      "grad_norm": 0.2524107098579407,
+      "learning_rate": 9.065995125283367e-06,
+      "loss": 0.7059,
+      "step": 176
+    },
+    {
+      "epoch": 1.1952861952861953,
+      "grad_norm": 0.2655806243419647,
+      "learning_rate": 9.052950571668458e-06,
+      "loss": 0.7418,
+      "step": 177
+    },
+    {
+      "epoch": 1.202020202020202,
+      "grad_norm": 0.249600350856781,
+      "learning_rate": 9.039825078709606e-06,
+      "loss": 0.7192,
+      "step": 178
+    },
+    {
+      "epoch": 1.2087542087542087,
+      "grad_norm": 0.23730139434337616,
+      "learning_rate": 9.026618908529132e-06,
+      "loss": 0.6776,
+      "step": 179
+    },
+    {
+      "epoch": 1.2154882154882154,
+      "grad_norm": 0.24353739619255066,
+      "learning_rate": 9.013332324860508e-06,
+      "loss": 0.7146,
+      "step": 180
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.26473721861839294,
+      "learning_rate": 8.999965593043113e-06,
+      "loss": 0.7188,
+      "step": 181
+    },
+    {
+      "epoch": 1.228956228956229,
+      "grad_norm": 0.27650538086891174,
+      "learning_rate": 8.986518980016914e-06,
+      "loss": 0.699,
+      "step": 182
+    },
+    {
+      "epoch": 1.2356902356902357,
+      "grad_norm": 0.2610260248184204,
+      "learning_rate": 8.972992754317144e-06,
+      "loss": 0.7126,
+      "step": 183
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 0.2537449896335602,
+      "learning_rate": 8.95938718606895e-06,
+      "loss": 0.7251,
+      "step": 184
+    },
+    {
+      "epoch": 1.2491582491582491,
+      "grad_norm": 0.25600242614746094,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 0.71,
+      "step": 185
+    },
+    {
+      "epoch": 1.2558922558922558,
+      "grad_norm": 0.28031960129737854,
+      "learning_rate": 8.931939110344935e-06,
+      "loss": 0.7254,
+      "step": 186
+    },
+    {
+      "epoch": 1.2626262626262625,
+      "grad_norm": 0.2574886679649353,
+      "learning_rate": 8.9180971510202e-06,
+      "loss": 0.7297,
+      "step": 187
+    },
+    {
+      "epoch": 1.2693602693602695,
+      "grad_norm": 0.25932928919792175,
+      "learning_rate": 8.904176945438255e-06,
+      "loss": 0.7118,
+      "step": 188
+    },
+    {
+      "epoch": 1.2760942760942762,
+      "grad_norm": 0.2755904197692871,
+      "learning_rate": 8.890178771592198e-06,
+      "loss": 0.7173,
+      "step": 189
+    },
+    {
+      "epoch": 1.2828282828282829,
+      "grad_norm": 0.26966917514801025,
+      "learning_rate": 8.8761029090322e-06,
+      "loss": 0.725,
+      "step": 190
+    },
+    {
+      "epoch": 1.2895622895622896,
+      "grad_norm": 0.27923187613487244,
+      "learning_rate": 8.861949638859908e-06,
+      "loss": 0.7216,
+      "step": 191
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.2591821551322937,
+      "learning_rate": 8.847719243722835e-06,
+      "loss": 0.7067,
+      "step": 192
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 0.284316748380661,
+      "learning_rate": 8.833412007808714e-06,
+      "loss": 0.7303,
+      "step": 193
+    },
+    {
+      "epoch": 1.3097643097643097,
+      "grad_norm": 0.25714966654777527,
+      "learning_rate": 8.819028216839831e-06,
+      "loss": 0.7035,
+      "step": 194
+    },
+    {
+      "epoch": 1.3164983164983166,
+      "grad_norm": 0.2684500813484192,
+      "learning_rate": 8.804568158067308e-06,
+      "loss": 0.7089,
+      "step": 195
+    },
+    {
+      "epoch": 1.3232323232323233,
+      "grad_norm": 0.25351622700691223,
+      "learning_rate": 8.790032120265373e-06,
+      "loss": 0.7044,
+      "step": 196
+    },
+    {
+      "epoch": 1.32996632996633,
+      "grad_norm": 0.25690147280693054,
+      "learning_rate": 8.775420393725592e-06,
+      "loss": 0.7208,
+      "step": 197
+    },
+    {
+      "epoch": 1.3367003367003367,
+      "grad_norm": 0.2771032154560089,
+      "learning_rate": 8.760733270251065e-06,
+      "loss": 0.716,
+      "step": 198
+    },
+    {
+      "epoch": 1.3434343434343434,
+      "grad_norm": 0.2745297849178314,
+      "learning_rate": 8.745971043150614e-06,
+      "loss": 0.7165,
+      "step": 199
+    },
+    {
+      "epoch": 1.3501683501683501,
+      "grad_norm": 0.275926411151886,
+      "learning_rate": 8.73113400723291e-06,
+      "loss": 0.7015,
+      "step": 200
+    },
+    {
+      "epoch": 1.3569023569023568,
+      "grad_norm": 0.2907668650150299,
+      "learning_rate": 8.716222458800591e-06,
+      "loss": 0.738,
+      "step": 201
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.2874827980995178,
+      "learning_rate": 8.70123669564435e-06,
+      "loss": 0.6867,
+      "step": 202
+    },
+    {
+      "epoch": 1.3703703703703702,
+      "grad_norm": 0.27132922410964966,
+      "learning_rate": 8.686177017036979e-06,
+      "loss": 0.7107,
+      "step": 203
+    },
+    {
+      "epoch": 1.3771043771043772,
+      "grad_norm": 0.30173900723457336,
+      "learning_rate": 8.671043723727396e-06,
+      "loss": 0.6803,
+      "step": 204
+    },
+    {
+      "epoch": 1.3838383838383839,
+      "grad_norm": 0.29518023133277893,
+      "learning_rate": 8.655837117934642e-06,
+      "loss": 0.7151,
+      "step": 205
+    },
+    {
+      "epoch": 1.3905723905723906,
+      "grad_norm": 0.2551437318325043,
+      "learning_rate": 8.640557503341843e-06,
+      "loss": 0.6806,
+      "step": 206
+    },
+    {
+      "epoch": 1.3973063973063973,
+      "grad_norm": 0.261708527803421,
+      "learning_rate": 8.625205185090147e-06,
+      "loss": 0.7056,
+      "step": 207
+    },
+    {
+      "epoch": 1.404040404040404,
+      "grad_norm": 0.2630426287651062,
+      "learning_rate": 8.609780469772623e-06,
+      "loss": 0.6659,
+      "step": 208
+    },
+    {
+      "epoch": 1.410774410774411,
+      "grad_norm": 0.3132041394710541,
+      "learning_rate": 8.594283665428147e-06,
+      "loss": 0.7101,
+      "step": 209
+    },
+    {
+      "epoch": 1.4175084175084174,
+      "grad_norm": 0.26227623224258423,
+      "learning_rate": 8.57871508153525e-06,
+      "loss": 0.7279,
+      "step": 210
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 0.3779846131801605,
+      "learning_rate": 8.563075029005924e-06,
+      "loss": 0.7379,
+      "step": 211
+    },
+    {
+      "epoch": 1.430976430976431,
+      "grad_norm": 0.2800910472869873,
+      "learning_rate": 8.547363820179442e-06,
+      "loss": 0.7168,
+      "step": 212
+    },
+    {
+      "epoch": 1.4377104377104377,
+      "grad_norm": 0.2794981002807617,
+      "learning_rate": 8.531581768816085e-06,
+      "loss": 0.6948,
+      "step": 213
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.3207724392414093,
+      "learning_rate": 8.515729190090895e-06,
+      "loss": 0.7106,
+      "step": 214
+    },
+    {
+      "epoch": 1.4511784511784511,
+      "grad_norm": 0.27082759141921997,
+      "learning_rate": 8.499806400587391e-06,
+      "loss": 0.7566,
+      "step": 215
+    },
+    {
+      "epoch": 1.457912457912458,
+      "grad_norm": 0.30250316858291626,
+      "learning_rate": 8.483813718291223e-06,
+      "loss": 0.679,
+      "step": 216
+    },
+    {
+      "epoch": 1.4646464646464645,
+      "grad_norm": 0.28343290090560913,
+      "learning_rate": 8.467751462583837e-06,
+      "loss": 0.726,
+      "step": 217
+    },
+    {
+      "epoch": 1.4713804713804715,
+      "grad_norm": 0.2696777582168579,
+      "learning_rate": 8.451619954236093e-06,
+      "loss": 0.7017,
+      "step": 218
+    },
+    {
+      "epoch": 1.4781144781144782,
+      "grad_norm": 0.2962685823440552,
+      "learning_rate": 8.435419515401856e-06,
+      "loss": 0.7455,
+      "step": 219
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 0.28010743856430054,
+      "learning_rate": 8.419150469611572e-06,
+      "loss": 0.6767,
+      "step": 220
+    },
+    {
+      "epoch": 1.4915824915824916,
+      "grad_norm": 0.2887760102748871,
+      "learning_rate": 8.402813141765796e-06,
+      "loss": 0.6452,
+      "step": 221
+    },
+    {
+      "epoch": 1.4983164983164983,
+      "grad_norm": 0.276254802942276,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 0.6759,
+      "step": 222
+    },
+    {
+      "epoch": 1.5050505050505052,
+      "grad_norm": 0.27473849058151245,
+      "learning_rate": 8.369934946321594e-06,
+      "loss": 0.7207,
+      "step": 223
+    },
+    {
+      "epoch": 1.5117845117845117,
+      "grad_norm": 0.26720133423805237,
+      "learning_rate": 8.353394735316317e-06,
+      "loss": 0.6672,
+      "step": 224
+    },
+    {
+      "epoch": 1.5185185185185186,
+      "grad_norm": 0.2742222547531128,
+      "learning_rate": 8.336787555428728e-06,
+      "loss": 0.7073,
+      "step": 225
+    },
+    {
+      "epoch": 1.5252525252525253,
+      "grad_norm": 0.27671125531196594,
+      "learning_rate": 8.320113738312081e-06,
+      "loss": 0.7018,
+      "step": 226
+    },
+    {
+      "epoch": 1.531986531986532,
+      "grad_norm": 0.266973614692688,
+      "learning_rate": 8.303373616950408e-06,
+      "loss": 0.6699,
+      "step": 227
+    },
+    {
+      "epoch": 1.5387205387205387,
+      "grad_norm": 0.26349687576293945,
+      "learning_rate": 8.286567525651865e-06,
+      "loss": 0.7135,
+      "step": 228
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.30225032567977905,
+      "learning_rate": 8.269695800042061e-06,
+      "loss": 0.7318,
+      "step": 229
+    },
+    {
+      "epoch": 1.5521885521885523,
+      "grad_norm": 0.28462594747543335,
+      "learning_rate": 8.252758777057355e-06,
+      "loss": 0.6692,
+      "step": 230
+    },
+    {
+      "epoch": 1.5589225589225588,
+      "grad_norm": 0.3298182189464569,
+      "learning_rate": 8.235756794938123e-06,
+      "loss": 0.7219,
+      "step": 231
+    },
+    {
+      "epoch": 1.5656565656565657,
+      "grad_norm": 0.26634180545806885,
+      "learning_rate": 8.218690193222007e-06,
+      "loss": 0.6879,
+      "step": 232
+    },
+    {
+      "epoch": 1.5723905723905722,
+      "grad_norm": 0.2943713366985321,
+      "learning_rate": 8.201559312737131e-06,
+      "loss": 0.6677,
+      "step": 233
+    },
+    {
+      "epoch": 1.5791245791245792,
+      "grad_norm": 0.2855622470378876,
+      "learning_rate": 8.1843644955953e-06,
+      "loss": 0.6951,
+      "step": 234
+    },
+    {
+      "epoch": 1.5858585858585859,
+      "grad_norm": 0.2742707133293152,
+      "learning_rate": 8.167106085185161e-06,
+      "loss": 0.6899,
+      "step": 235
+    },
+    {
+      "epoch": 1.5925925925925926,
+      "grad_norm": 0.2689763307571411,
+      "learning_rate": 8.149784426165351e-06,
+      "loss": 0.6886,
+      "step": 236
+    },
+    {
+      "epoch": 1.5993265993265995,
+      "grad_norm": 0.3123777210712433,
+      "learning_rate": 8.13239986445761e-06,
+      "loss": 0.7141,
+      "step": 237
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 0.284868448972702,
+      "learning_rate": 8.114952747239876e-06,
+      "loss": 0.6793,
+      "step": 238
+    },
+    {
+      "epoch": 1.612794612794613,
+      "grad_norm": 0.28802135586738586,
+      "learning_rate": 8.09744342293935e-06,
+      "loss": 0.6831,
+      "step": 239
+    },
+    {
+      "epoch": 1.6195286195286194,
+      "grad_norm": 0.2741600573062897,
+      "learning_rate": 8.079872241225534e-06,
+      "loss": 0.6887,
+      "step": 240
+    },
+    {
+      "epoch": 1.6262626262626263,
+      "grad_norm": 0.3155152499675751,
+      "learning_rate": 8.06223955300326e-06,
+      "loss": 0.7127,
+      "step": 241
+    },
+    {
+      "epoch": 1.632996632996633,
+      "grad_norm": 0.29525065422058105,
+      "learning_rate": 8.044545710405666e-06,
+      "loss": 0.7051,
+      "step": 242
+    },
+    {
+      "epoch": 1.6397306397306397,
+      "grad_norm": 0.3008731007575989,
+      "learning_rate": 8.026791066787177e-06,
+      "loss": 0.7012,
+      "step": 243
+    },
+    {
+      "epoch": 1.6464646464646466,
+      "grad_norm": 0.3014560639858246,
+      "learning_rate": 8.00897597671644e-06,
+      "loss": 0.6887,
+      "step": 244
+    },
+    {
+      "epoch": 1.6531986531986531,
+      "grad_norm": 0.28930526971817017,
+      "learning_rate": 7.991100795969248e-06,
+      "loss": 0.7171,
+      "step": 245
+    },
+    {
+      "epoch": 1.65993265993266,
+      "grad_norm": 0.3083915114402771,
+      "learning_rate": 7.973165881521435e-06,
+      "loss": 0.7202,
+      "step": 246
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3567061126232147,
+      "learning_rate": 7.955171591541739e-06,
+      "loss": 0.7043,
+      "step": 247
+    },
+    {
+      "epoch": 1.6734006734006734,
+      "grad_norm": 0.33908185362815857,
+      "learning_rate": 7.937118285384666e-06,
+      "loss": 0.6687,
+      "step": 248
+    },
+    {
+      "epoch": 1.6801346801346801,
+      "grad_norm": 0.28633400797843933,
+      "learning_rate": 7.91900632358329e-06,
+      "loss": 0.7112,
+      "step": 249
+    },
+    {
+      "epoch": 1.6868686868686869,
+      "grad_norm": 0.3234066069126129,
+      "learning_rate": 7.90083606784208e-06,
+      "loss": 0.7095,
+      "step": 250
+    },
+    {
+      "epoch": 1.6936026936026936,
+      "grad_norm": 0.2888222932815552,
+      "learning_rate": 7.882607881029652e-06,
+      "loss": 0.7193,
+      "step": 251
+    },
+    {
+      "epoch": 1.7003367003367003,
+      "grad_norm": 0.29027071595191956,
+      "learning_rate": 7.864322127171535e-06,
+      "loss": 0.7157,
+      "step": 252
+    },
+    {
+      "epoch": 1.7070707070707072,
+      "grad_norm": 0.29393255710601807,
+      "learning_rate": 7.8459791714429e-06,
+      "loss": 0.7104,
+      "step": 253
+    },
+    {
+      "epoch": 1.7138047138047137,
+      "grad_norm": 0.3067580759525299,
+      "learning_rate": 7.827579380161272e-06,
+      "loss": 0.6964,
+      "step": 254
+    },
+    {
+      "epoch": 1.7205387205387206,
+      "grad_norm": 0.2851170003414154,
+      "learning_rate": 7.809123120779201e-06,
+      "loss": 0.6804,
+      "step": 255
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.3147255778312683,
+      "learning_rate": 7.790610761876936e-06,
+      "loss": 0.6992,
+      "step": 256
+    },
+    {
+      "epoch": 1.734006734006734,
+      "grad_norm": 0.28082358837127686,
+      "learning_rate": 7.772042673155057e-06,
+      "loss": 0.664,
+      "step": 257
+    },
+    {
+      "epoch": 1.7407407407407407,
+      "grad_norm": 0.3215820789337158,
+      "learning_rate": 7.753419225427097e-06,
+      "loss": 0.6968,
+      "step": 258
+    },
+    {
+      "epoch": 1.7474747474747474,
+      "grad_norm": 0.30421900749206543,
+      "learning_rate": 7.734740790612137e-06,
+      "loss": 0.6951,
+      "step": 259
+    },
+    {
+      "epoch": 1.7542087542087543,
+      "grad_norm": 0.292523592710495,
+      "learning_rate": 7.716007741727368e-06,
+      "loss": 0.6859,
+      "step": 260
+    },
+    {
+      "epoch": 1.7609427609427608,
+      "grad_norm": 0.301112562417984,
+      "learning_rate": 7.69722045288066e-06,
+      "loss": 0.6942,
+      "step": 261
+    },
+    {
+      "epoch": 1.7676767676767677,
+      "grad_norm": 0.31593406200408936,
+      "learning_rate": 7.678379299263076e-06,
+      "loss": 0.689,
+      "step": 262
+    },
+    {
+      "epoch": 1.7744107744107744,
+      "grad_norm": 0.33452534675598145,
+      "learning_rate": 7.659484657141382e-06,
+      "loss": 0.752,
+      "step": 263
+    },
+    {
+      "epoch": 1.7811447811447811,
+      "grad_norm": 0.3017633259296417,
+      "learning_rate": 7.64053690385054e-06,
+      "loss": 0.7052,
+      "step": 264
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 0.28459274768829346,
+      "learning_rate": 7.621536417786159e-06,
+      "loss": 0.6738,
+      "step": 265
+    },
+    {
+      "epoch": 1.7946127946127945,
+      "grad_norm": 0.2791585624217987,
+      "learning_rate": 7.602483578396955e-06,
+      "loss": 0.6819,
+      "step": 266
+    },
+    {
+      "epoch": 1.8013468013468015,
+      "grad_norm": 0.3020349144935608,
+      "learning_rate": 7.583378766177163e-06,
+      "loss": 0.72,
+      "step": 267
+    },
+    {
+      "epoch": 1.808080808080808,
+      "grad_norm": 0.28048840165138245,
+      "learning_rate": 7.564222362658935e-06,
+      "loss": 0.6961,
+      "step": 268
+    },
+    {
+      "epoch": 1.8148148148148149,
+      "grad_norm": 0.29612207412719727,
+      "learning_rate": 7.54501475040473e-06,
+      "loss": 0.6902,
+      "step": 269
+    },
+    {
+      "epoch": 1.8215488215488216,
+      "grad_norm": 0.27847015857696533,
+      "learning_rate": 7.52575631299967e-06,
+      "loss": 0.706,
+      "step": 270
+    },
+    {
+      "epoch": 1.8282828282828283,
+      "grad_norm": 0.29833778738975525,
+      "learning_rate": 7.5064474350438755e-06,
+      "loss": 0.6795,
+      "step": 271
+    },
+    {
+      "epoch": 1.835016835016835,
+      "grad_norm": 0.30200687050819397,
+      "learning_rate": 7.487088502144793e-06,
+      "loss": 0.672,
+      "step": 272
+    },
+    {
+      "epoch": 1.8417508417508417,
+      "grad_norm": 0.2916306257247925,
+      "learning_rate": 7.467679900909489e-06,
+      "loss": 0.6495,
+      "step": 273
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.28734859824180603,
+      "learning_rate": 7.4482220189369295e-06,
+      "loss": 0.6752,
+      "step": 274
+    },
+    {
+      "epoch": 1.855218855218855,
+      "grad_norm": 0.31577038764953613,
+      "learning_rate": 7.428715244810238e-06,
+      "loss": 0.7235,
+      "step": 275
+    },
+    {
+      "epoch": 1.861952861952862,
+      "grad_norm": 0.31323179602622986,
+      "learning_rate": 7.4091599680889425e-06,
+      "loss": 0.6839,
+      "step": 276
+    },
+    {
+      "epoch": 1.8686868686868687,
+      "grad_norm": 0.28605639934539795,
+      "learning_rate": 7.389556579301186e-06,
+      "loss": 0.6638,
+      "step": 277
+    },
+    {
+      "epoch": 1.8754208754208754,
+      "grad_norm": 0.2822740077972412,
+      "learning_rate": 7.369905469935935e-06,
+      "loss": 0.6982,
+      "step": 278
+    },
+    {
+      "epoch": 1.8821548821548821,
+      "grad_norm": 0.290394127368927,
+      "learning_rate": 7.350207032435157e-06,
+      "loss": 0.7118,
+      "step": 279
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.2912713587284088,
+      "learning_rate": 7.330461660185987e-06,
+      "loss": 0.6776,
+      "step": 280
+    },
+    {
+      "epoch": 1.8956228956228958,
+      "grad_norm": 0.32215046882629395,
+      "learning_rate": 7.3106697475128655e-06,
+      "loss": 0.6909,
+      "step": 281
+    },
+    {
+      "epoch": 1.9023569023569022,
+      "grad_norm": 0.28878840804100037,
+      "learning_rate": 7.2908316896696725e-06,
+      "loss": 0.6768,
+      "step": 282
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.32832571864128113,
+      "learning_rate": 7.270947882831823e-06,
+      "loss": 0.7195,
+      "step": 283
+    },
+    {
+      "epoch": 1.9158249158249159,
+      "grad_norm": 0.32346925139427185,
+      "learning_rate": 7.251018724088367e-06,
+      "loss": 0.6962,
+      "step": 284
+    },
+    {
+      "epoch": 1.9225589225589226,
+      "grad_norm": 0.32384803891181946,
+      "learning_rate": 7.231044611434049e-06,
+      "loss": 0.6501,
+      "step": 285
+    },
+    {
+      "epoch": 1.9292929292929293,
+      "grad_norm": 0.3192203640937805,
+      "learning_rate": 7.211025943761367e-06,
+      "loss": 0.712,
+      "step": 286
+    },
+    {
+      "epoch": 1.936026936026936,
+      "grad_norm": 0.2892184853553772,
+      "learning_rate": 7.190963120852601e-06,
+      "loss": 0.6559,
+      "step": 287
+    },
+    {
+      "epoch": 1.942760942760943,
+      "grad_norm": 0.30964168906211853,
+      "learning_rate": 7.1708565433718354e-06,
+      "loss": 0.7041,
+      "step": 288
+    },
+    {
+      "epoch": 1.9494949494949494,
+      "grad_norm": 0.3227485418319702,
+      "learning_rate": 7.150706612856952e-06,
+      "loss": 0.6702,
+      "step": 289
+    },
+    {
+      "epoch": 1.9562289562289563,
+      "grad_norm": 0.30388596653938293,
+      "learning_rate": 7.130513731711616e-06,
+      "loss": 0.7115,
+      "step": 290
+    },
+    {
+      "epoch": 1.9629629629629628,
+      "grad_norm": 0.30058157444000244,
+      "learning_rate": 7.1102783031972326e-06,
+      "loss": 0.6723,
+      "step": 291
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.2957688570022583,
+      "learning_rate": 7.0900007314249e-06,
+      "loss": 0.6609,
+      "step": 292
+    },
+    {
+      "epoch": 1.9764309764309764,
+      "grad_norm": 0.32087063789367676,
+      "learning_rate": 7.06968142134734e-06,
+      "loss": 0.6666,
+      "step": 293
+    },
+    {
+      "epoch": 1.9831649831649831,
+      "grad_norm": 0.31820395588874817,
+      "learning_rate": 7.0493207787508034e-06,
+      "loss": 0.6853,
+      "step": 294
+    },
+    {
+      "epoch": 1.98989898989899,
+      "grad_norm": 0.32074615359306335,
+      "learning_rate": 7.028919210246975e-06,
+      "loss": 0.6757,
+      "step": 295
+    },
+    {
+      "epoch": 1.9966329966329965,
+      "grad_norm": 0.3086588680744171,
+      "learning_rate": 7.008477123264849e-06,
+      "loss": 0.6955,
+      "step": 296
+    },
+    {
+      "epoch": 2.006734006734007,
+      "grad_norm": 0.34101998805999756,
+      "learning_rate": 6.987994926042588e-06,
+      "loss": 0.8372,
+      "step": 297
+    },
+    {
+      "epoch": 2.0134680134680134,
+      "grad_norm": 0.30261072516441345,
+      "learning_rate": 6.967473027619381e-06,
+      "loss": 0.6775,
+      "step": 298
+    },
+    {
+      "epoch": 2.0202020202020203,
+      "grad_norm": 0.3041035532951355,
+      "learning_rate": 6.946911837827267e-06,
+      "loss": 0.6918,
+      "step": 299
+    },
+    {
+      "epoch": 2.026936026936027,
+      "grad_norm": 0.3256051242351532,
+      "learning_rate": 6.926311767282951e-06,
+      "loss": 0.7202,
+      "step": 300
+    },
+    {
+      "epoch": 2.0336700336700337,
+      "grad_norm": 0.31417331099510193,
+      "learning_rate": 6.905673227379606e-06,
+      "loss": 0.7169,
+      "step": 301
+    },
+    {
+      "epoch": 2.04040404040404,
+      "grad_norm": 0.30272215604782104,
+      "learning_rate": 6.884996630278654e-06,
+      "loss": 0.6821,
+      "step": 302
+    },
+    {
+      "epoch": 2.047138047138047,
+      "grad_norm": 0.3101252019405365,
+      "learning_rate": 6.864282388901544e-06,
+      "loss": 0.6856,
+      "step": 303
+    },
+    {
+      "epoch": 2.053872053872054,
+      "grad_norm": 0.2862723767757416,
+      "learning_rate": 6.84353091692149e-06,
+      "loss": 0.6475,
+      "step": 304
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 0.30249181389808655,
+      "learning_rate": 6.822742628755228e-06,
+      "loss": 0.6957,
+      "step": 305
+    },
+    {
+      "epoch": 2.0673400673400675,
+      "grad_norm": 0.3228001892566681,
+      "learning_rate": 6.801917939554721e-06,
+      "loss": 0.6636,
+      "step": 306
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 0.32464271783828735,
+      "learning_rate": 6.781057265198885e-06,
+      "loss": 0.6734,
+      "step": 307
+    },
+    {
+      "epoch": 2.080808080808081,
+      "grad_norm": 0.30116304755210876,
+      "learning_rate": 6.760161022285274e-06,
+      "loss": 0.6762,
+      "step": 308
+    },
+    {
+      "epoch": 2.0875420875420874,
+      "grad_norm": 0.31851866841316223,
+      "learning_rate": 6.739229628121765e-06,
+      "loss": 0.679,
+      "step": 309
+    },
+    {
+      "epoch": 2.0942760942760943,
+      "grad_norm": 0.30224835872650146,
+      "learning_rate": 6.7182635007182186e-06,
+      "loss": 0.6745,
+      "step": 310
+    },
+    {
+      "epoch": 2.101010101010101,
+      "grad_norm": 0.3195047676563263,
+      "learning_rate": 6.6972630587781385e-06,
+      "loss": 0.7181,
+      "step": 311
+    },
+    {
+      "epoch": 2.1077441077441077,
+      "grad_norm": 0.3004336357116699,
+      "learning_rate": 6.676228721690301e-06,
+      "loss": 0.6547,
+      "step": 312
+    },
+    {
+      "epoch": 2.1144781144781146,
+      "grad_norm": 0.2977725565433502,
+      "learning_rate": 6.655160909520391e-06,
+      "loss": 0.6855,
+      "step": 313
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 0.3015722334384918,
+      "learning_rate": 6.634060043002603e-06,
+      "loss": 0.688,
+      "step": 314
+    },
+    {
+      "epoch": 2.127946127946128,
+      "grad_norm": 0.3413928151130676,
+      "learning_rate": 6.6129265435312405e-06,
+      "loss": 0.7018,
+      "step": 315
+    },
+    {
+      "epoch": 2.1346801346801345,
+      "grad_norm": 0.30066797137260437,
+      "learning_rate": 6.591760833152306e-06,
+      "loss": 0.6873,
+      "step": 316
+    },
+    {
+      "epoch": 2.1414141414141414,
+      "grad_norm": 0.3292277157306671,
+      "learning_rate": 6.570563334555068e-06,
+      "loss": 0.6709,
+      "step": 317
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 0.29609090089797974,
+      "learning_rate": 6.54933447106362e-06,
+      "loss": 0.6582,
+      "step": 318
+    },
+    {
+      "epoch": 2.154882154882155,
+      "grad_norm": 0.3019602596759796,
+      "learning_rate": 6.52807466662843e-06,
+      "loss": 0.7016,
+      "step": 319
+    },
+    {
+      "epoch": 2.1616161616161618,
+      "grad_norm": 0.31941643357276917,
+      "learning_rate": 6.506784345817867e-06,
+      "loss": 0.6852,
+      "step": 320
+    },
+    {
+      "epoch": 2.1683501683501682,
+      "grad_norm": 0.33759576082229614,
+      "learning_rate": 6.48546393380973e-06,
+      "loss": 0.7457,
+      "step": 321
+    },
+    {
+      "epoch": 2.175084175084175,
+      "grad_norm": 0.32998767495155334,
+      "learning_rate": 6.464113856382752e-06,
+      "loss": 0.6925,
+      "step": 322
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.3006787598133087,
+      "learning_rate": 6.4427345399081e-06,
+      "loss": 0.6636,
+      "step": 323
+    },
+    {
+      "epoch": 2.1885521885521886,
+      "grad_norm": 0.31251853704452515,
+      "learning_rate": 6.421326411340855e-06,
+      "loss": 0.663,
+      "step": 324
+    },
+    {
+      "epoch": 2.1952861952861955,
+      "grad_norm": 0.31268492341041565,
+      "learning_rate": 6.399889898211495e-06,
+      "loss": 0.6522,
+      "step": 325
+    },
+    {
+      "epoch": 2.202020202020202,
+      "grad_norm": 0.31962957978248596,
+      "learning_rate": 6.378425428617343e-06,
+      "loss": 0.6674,
+      "step": 326
+    },
+    {
+      "epoch": 2.208754208754209,
+      "grad_norm": 0.29788488149642944,
+      "learning_rate": 6.356933431214034e-06,
+      "loss": 0.6994,
+      "step": 327
+    },
+    {
+      "epoch": 2.2154882154882154,
+      "grad_norm": 0.3490550220012665,
+      "learning_rate": 6.3354143352069415e-06,
+      "loss": 0.6686,
+      "step": 328
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.31461504101753235,
+      "learning_rate": 6.313868570342614e-06,
+      "loss": 0.6635,
+      "step": 329
+    },
+    {
+      "epoch": 2.228956228956229,
+      "grad_norm": 0.3282307982444763,
+      "learning_rate": 6.292296566900187e-06,
+      "loss": 0.689,
+      "step": 330
+    },
+    {
+      "epoch": 2.2356902356902357,
+      "grad_norm": 0.3187669813632965,
+      "learning_rate": 6.270698755682792e-06,
+      "loss": 0.6758,
+      "step": 331
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 0.3053145706653595,
+      "learning_rate": 6.249075568008961e-06,
+      "loss": 0.675,
+      "step": 332
+    },
+    {
+      "epoch": 2.249158249158249,
+      "grad_norm": 0.3063344359397888,
+      "learning_rate": 6.227427435703997e-06,
+      "loss": 0.6877,
+      "step": 333
+    },
+    {
+      "epoch": 2.255892255892256,
+      "grad_norm": 0.3036075532436371,
+      "learning_rate": 6.205754791091364e-06,
+      "loss": 0.6875,
+      "step": 334
+    },
+    {
+      "epoch": 2.2626262626262625,
+      "grad_norm": 0.34430813789367676,
+      "learning_rate": 6.1840580669840455e-06,
+      "loss": 0.7325,
+      "step": 335
+    },
+    {
+      "epoch": 2.2693602693602695,
+      "grad_norm": 0.3094182312488556,
+      "learning_rate": 6.162337696675909e-06,
+      "loss": 0.6818,
+      "step": 336
+    },
+    {
+      "epoch": 2.276094276094276,
+      "grad_norm": 0.3417794704437256,
+      "learning_rate": 6.140594113933043e-06,
+      "loss": 0.6773,
+      "step": 337
+    },
+    {
+      "epoch": 2.282828282828283,
+      "grad_norm": 0.33146169781684875,
+      "learning_rate": 6.1188277529851015e-06,
+      "loss": 0.6962,
+      "step": 338
+    },
+    {
+      "epoch": 2.28956228956229,
+      "grad_norm": 0.3180915415287018,
+      "learning_rate": 6.097039048516628e-06,
+      "loss": 0.661,
+      "step": 339
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": 0.30588653683662415,
+      "learning_rate": 6.075228435658379e-06,
+      "loss": 0.6746,
+      "step": 340
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 0.3140996992588043,
+      "learning_rate": 6.053396349978632e-06,
+      "loss": 0.662,
+      "step": 341
+    },
+    {
+      "epoch": 2.3097643097643097,
+      "grad_norm": 0.2963620722293854,
+      "learning_rate": 6.031543227474486e-06,
+      "loss": 0.62,
+      "step": 342
+    },
+    {
+      "epoch": 2.3164983164983166,
+      "grad_norm": 0.32323580980300903,
+      "learning_rate": 6.009669504563154e-06,
+      "loss": 0.6728,
+      "step": 343
+    },
+    {
+      "epoch": 2.323232323232323,
+      "grad_norm": 0.33873456716537476,
+      "learning_rate": 5.9877756180732505e-06,
+      "loss": 0.6658,
+      "step": 344
+    },
+    {
+      "epoch": 2.32996632996633,
+      "grad_norm": 0.3323650658130646,
+      "learning_rate": 5.965862005236067e-06,
+      "loss": 0.7106,
+      "step": 345
+    },
+    {
+      "epoch": 2.3367003367003365,
+      "grad_norm": 0.30574050545692444,
+      "learning_rate": 5.943929103676839e-06,
+      "loss": 0.6791,
+      "step": 346
+    },
+    {
+      "epoch": 2.3434343434343434,
+      "grad_norm": 0.3394505977630615,
+      "learning_rate": 5.921977351406004e-06,
+      "loss": 0.6929,
+      "step": 347
+    },
+    {
+      "epoch": 2.3501683501683504,
+      "grad_norm": 0.3277929425239563,
+      "learning_rate": 5.900007186810461e-06,
+      "loss": 0.6757,
+      "step": 348
+    },
+    {
+      "epoch": 2.356902356902357,
+      "grad_norm": 0.33306998014450073,
+      "learning_rate": 5.878019048644812e-06,
+      "loss": 0.6909,
+      "step": 349
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.34115421772003174,
+      "learning_rate": 5.856013376022594e-06,
+      "loss": 0.7159,
+      "step": 350
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.32741618156433105,
+      "learning_rate": 5.833990608407525e-06,
+      "loss": 0.6522,
+      "step": 351
+    },
+    {
+      "epoch": 2.377104377104377,
+      "grad_norm": 0.30264726281166077,
+      "learning_rate": 5.811951185604709e-06,
+      "loss": 0.6774,
+      "step": 352
+    },
+    {
+      "epoch": 2.3838383838383836,
+      "grad_norm": 0.31635618209838867,
+      "learning_rate": 5.789895547751867e-06,
+      "loss": 0.6415,
+      "step": 353
+    },
+    {
+      "epoch": 2.3905723905723906,
+      "grad_norm": 0.3575221598148346,
+      "learning_rate": 5.767824135310538e-06,
+      "loss": 0.6525,
+      "step": 354
+    },
+    {
+      "epoch": 2.3973063973063975,
+      "grad_norm": 0.3207171857357025,
+      "learning_rate": 5.745737389057294e-06,
+      "loss": 0.6584,
+      "step": 355
+    },
+    {
+      "epoch": 2.404040404040404,
+      "grad_norm": 0.3243761360645294,
+      "learning_rate": 5.723635750074924e-06,
+      "loss": 0.6651,
+      "step": 356
+    },
+    {
+      "epoch": 2.410774410774411,
+      "grad_norm": 0.318534255027771,
+      "learning_rate": 5.701519659743636e-06,
+      "loss": 0.6829,
+      "step": 357
+    },
+    {
+      "epoch": 2.4175084175084174,
+      "grad_norm": 0.33522891998291016,
+      "learning_rate": 5.679389559732234e-06,
+      "loss": 0.6908,
+      "step": 358
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 0.32205212116241455,
+      "learning_rate": 5.657245891989307e-06,
+      "loss": 0.6681,
+      "step": 359
+    },
+    {
+      "epoch": 2.430976430976431,
+      "grad_norm": 0.3299495279788971,
+      "learning_rate": 5.635089098734394e-06,
+      "loss": 0.6678,
+      "step": 360
+    },
+    {
+      "epoch": 2.4377104377104377,
+      "grad_norm": 0.329253226518631,
+      "learning_rate": 5.61291962244916e-06,
+      "loss": 0.668,
+      "step": 361
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.3404013216495514,
+      "learning_rate": 5.59073790586855e-06,
+      "loss": 0.6334,
+      "step": 362
+    },
+    {
+      "epoch": 2.451178451178451,
+      "grad_norm": 0.33572322130203247,
+      "learning_rate": 5.568544391971964e-06,
+      "loss": 0.6728,
+      "step": 363
+    },
+    {
+      "epoch": 2.457912457912458,
+      "grad_norm": 0.33126330375671387,
+      "learning_rate": 5.546339523974389e-06,
+      "loss": 0.6262,
+      "step": 364
+    },
+    {
+      "epoch": 2.4646464646464645,
+      "grad_norm": 0.3154200613498688,
+      "learning_rate": 5.5241237453175664e-06,
+      "loss": 0.6421,
+      "step": 365
+    },
+    {
+      "epoch": 2.4713804713804715,
+      "grad_norm": 0.3080921173095703,
+      "learning_rate": 5.501897499661123e-06,
+      "loss": 0.66,
+      "step": 366
+    },
+    {
+      "epoch": 2.478114478114478,
+      "grad_norm": 0.3175220191478729,
+      "learning_rate": 5.4796612308737225e-06,
+      "loss": 0.6566,
+      "step": 367
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 0.3048228621482849,
+      "learning_rate": 5.4574153830241905e-06,
+      "loss": 0.6684,
+      "step": 368
+    },
+    {
+      "epoch": 2.4915824915824913,
+      "grad_norm": 0.3418152630329132,
+      "learning_rate": 5.435160400372653e-06,
+      "loss": 0.7178,
+      "step": 369
+    },
+    {
+      "epoch": 2.4983164983164983,
+      "grad_norm": 0.34362682700157166,
+      "learning_rate": 5.412896727361663e-06,
+      "loss": 0.6925,
+      "step": 370
+    },
+    {
+      "epoch": 2.505050505050505,
+      "grad_norm": 0.30840158462524414,
+      "learning_rate": 5.390624808607321e-06,
+      "loss": 0.637,
+      "step": 371
+    },
+    {
+      "epoch": 2.5117845117845117,
+      "grad_norm": 0.33842259645462036,
+      "learning_rate": 5.368345088890401e-06,
+      "loss": 0.7088,
+      "step": 372
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": 0.34740138053894043,
+      "learning_rate": 5.34605801314747e-06,
+      "loss": 0.6908,
+      "step": 373
+    },
+    {
+      "epoch": 2.525252525252525,
+      "grad_norm": 0.35594460368156433,
+      "learning_rate": 5.323764026461988e-06,
+      "loss": 0.6766,
+      "step": 374
+    },
+    {
+      "epoch": 2.531986531986532,
+      "grad_norm": 0.3934316635131836,
+      "learning_rate": 5.301463574055441e-06,
+      "loss": 0.6603,
+      "step": 375
+    },
+    {
+      "epoch": 2.538720538720539,
+      "grad_norm": 0.3513649106025696,
+      "learning_rate": 5.279157101278433e-06,
+      "loss": 0.6872,
+      "step": 376
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.38326022028923035,
+      "learning_rate": 5.256845053601795e-06,
+      "loss": 0.6723,
+      "step": 377
+    },
+    {
+      "epoch": 2.5521885521885523,
+      "grad_norm": 0.35960447788238525,
+      "learning_rate": 5.234527876607698e-06,
+      "loss": 0.6664,
+      "step": 378
+    },
+    {
+      "epoch": 2.558922558922559,
+      "grad_norm": 0.3370625674724579,
+      "learning_rate": 5.212206015980742e-06,
+      "loss": 0.6935,
+      "step": 379
+    },
+    {
+      "epoch": 2.5656565656565657,
+      "grad_norm": 0.3355901837348938,
+      "learning_rate": 5.189879917499067e-06,
+      "loss": 0.6628,
+      "step": 380
+    },
+    {
+      "epoch": 2.5723905723905722,
+      "grad_norm": 0.33717080950737,
+      "learning_rate": 5.1675500270254385e-06,
+      "loss": 0.6683,
+      "step": 381
+    },
+    {
+      "epoch": 2.579124579124579,
+      "grad_norm": 0.3160232603549957,
+      "learning_rate": 5.145216790498355e-06,
+      "loss": 0.6727,
+      "step": 382
+    },
+    {
+      "epoch": 2.5858585858585856,
+      "grad_norm": 0.3072569668292999,
+      "learning_rate": 5.122880653923134e-06,
+      "loss": 0.6664,
+      "step": 383
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.3160644471645355,
+      "learning_rate": 5.100542063363013e-06,
+      "loss": 0.6614,
+      "step": 384
+    },
+    {
+      "epoch": 2.5993265993265995,
+      "grad_norm": 0.33290305733680725,
+      "learning_rate": 5.07820146493023e-06,
+      "loss": 0.6872,
+      "step": 385
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 0.3331235647201538,
+      "learning_rate": 5.055859304777127e-06,
+      "loss": 0.6443,
+      "step": 386
+    },
+    {
+      "epoch": 2.612794612794613,
+      "grad_norm": 0.3328459560871124,
+      "learning_rate": 5.033516029087231e-06,
+      "loss": 0.6589,
+      "step": 387
+    },
+    {
+      "epoch": 2.6195286195286194,
+      "grad_norm": 0.3131551742553711,
+      "learning_rate": 5.011172084066349e-06,
+      "loss": 0.648,
+      "step": 388
+    },
+    {
+      "epoch": 2.6262626262626263,
+      "grad_norm": 0.318933367729187,
+      "learning_rate": 4.988827915933652e-06,
+      "loss": 0.648,
+      "step": 389
+    },
+    {
+      "epoch": 2.6329966329966332,
+      "grad_norm": 0.3695783019065857,
+      "learning_rate": 4.966483970912769e-06,
+      "loss": 0.6652,
+      "step": 390
+    },
+    {
+      "epoch": 2.6397306397306397,
+      "grad_norm": 0.34661394357681274,
+      "learning_rate": 4.944140695222874e-06,
+      "loss": 0.6863,
+      "step": 391
+    },
+    {
+      "epoch": 2.6464646464646466,
+      "grad_norm": 0.3176628351211548,
+      "learning_rate": 4.92179853506977e-06,
+      "loss": 0.6591,
+      "step": 392
+    },
+    {
+      "epoch": 2.653198653198653,
+      "grad_norm": 0.3425232470035553,
+      "learning_rate": 4.899457936636988e-06,
+      "loss": 0.6772,
+      "step": 393
+    },
+    {
+      "epoch": 2.65993265993266,
+      "grad_norm": 0.32734331488609314,
+      "learning_rate": 4.877119346076868e-06,
+      "loss": 0.6877,
+      "step": 394
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.35816332697868347,
+      "learning_rate": 4.854783209501646e-06,
+      "loss": 0.6625,
+      "step": 395
+    },
+    {
+      "epoch": 2.6734006734006734,
+      "grad_norm": 0.322437584400177,
+      "learning_rate": 4.832449972974564e-06,
+      "loss": 0.6639,
+      "step": 396
+    },
+    {
+      "epoch": 2.68013468013468,
+      "grad_norm": 0.3232383131980896,
+      "learning_rate": 4.810120082500934e-06,
+      "loss": 0.6987,
+      "step": 397
+    },
+    {
+      "epoch": 2.686868686868687,
+      "grad_norm": 0.33261874318122864,
+      "learning_rate": 4.78779398401926e-06,
+      "loss": 0.6815,
+      "step": 398
+    },
+    {
+      "epoch": 2.6936026936026938,
+      "grad_norm": 0.3170070946216583,
+      "learning_rate": 4.765472123392304e-06,
+      "loss": 0.6881,
+      "step": 399
+    },
+    {
+      "epoch": 2.7003367003367003,
+      "grad_norm": 0.32975471019744873,
+      "learning_rate": 4.743154946398207e-06,
+      "loss": 0.6482,
+      "step": 400
+    },
+    {
+      "epoch": 2.707070707070707,
+      "grad_norm": 0.3293749988079071,
+      "learning_rate": 4.720842898721569e-06,
+      "loss": 0.629,
+      "step": 401
+    },
+    {
+      "epoch": 2.7138047138047137,
+      "grad_norm": 0.3324597477912903,
+      "learning_rate": 4.698536425944561e-06,
+      "loss": 0.6978,
+      "step": 402
+    },
+    {
+      "epoch": 2.7205387205387206,
+      "grad_norm": 0.3278536796569824,
+      "learning_rate": 4.6762359735380135e-06,
+      "loss": 0.6663,
+      "step": 403
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.33780574798583984,
+      "learning_rate": 4.653941986852533e-06,
+      "loss": 0.6926,
+      "step": 404
+    },
+    {
+      "epoch": 2.734006734006734,
+      "grad_norm": 0.35599419474601746,
+      "learning_rate": 4.6316549111096e-06,
+      "loss": 0.6759,
+      "step": 405
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": 0.32220327854156494,
+      "learning_rate": 4.60937519139268e-06,
+      "loss": 0.6677,
+      "step": 406
+    },
+    {
+      "epoch": 2.7474747474747474,
+      "grad_norm": 0.32263022661209106,
+      "learning_rate": 4.587103272638339e-06,
+      "loss": 0.6727,
+      "step": 407
+    },
+    {
+      "epoch": 2.7542087542087543,
+      "grad_norm": 0.32157519459724426,
+      "learning_rate": 4.564839599627347e-06,
+      "loss": 0.6603,
+      "step": 408
+    },
+    {
+      "epoch": 2.760942760942761,
+      "grad_norm": 0.32805973291397095,
+      "learning_rate": 4.542584616975811e-06,
+      "loss": 0.6964,
+      "step": 409
+    },
+    {
+      "epoch": 2.7676767676767677,
+      "grad_norm": 0.37896931171417236,
+      "learning_rate": 4.5203387691262774e-06,
+      "loss": 0.6656,
+      "step": 410
+    },
+    {
+      "epoch": 2.774410774410774,
+      "grad_norm": 0.35789135098457336,
+      "learning_rate": 4.498102500338879e-06,
+      "loss": 0.6379,
+      "step": 411
+    },
+    {
+      "epoch": 2.781144781144781,
+      "grad_norm": 0.3611665368080139,
+      "learning_rate": 4.475876254682436e-06,
+      "loss": 0.6765,
+      "step": 412
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 0.3591862618923187,
+      "learning_rate": 4.453660476025612e-06,
+      "loss": 0.6686,
+      "step": 413
+    },
+    {
+      "epoch": 2.7946127946127945,
+      "grad_norm": 0.32585394382476807,
+      "learning_rate": 4.431455608028038e-06,
+      "loss": 0.6655,
+      "step": 414
+    },
+    {
+      "epoch": 2.8013468013468015,
+      "grad_norm": 0.32006388902664185,
+      "learning_rate": 4.40926209413145e-06,
+      "loss": 0.6695,
+      "step": 415
+    },
+    {
+      "epoch": 2.808080808080808,
+      "grad_norm": 0.3642265200614929,
+      "learning_rate": 4.387080377550843e-06,
+      "loss": 0.643,
+      "step": 416
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.3640241026878357,
+      "learning_rate": 4.364910901265607e-06,
+      "loss": 0.6859,
+      "step": 417
+    },
+    {
+      "epoch": 2.821548821548822,
+      "grad_norm": 0.31810638308525085,
+      "learning_rate": 4.342754108010695e-06,
+      "loss": 0.6802,
+      "step": 418
+    },
+    {
+      "epoch": 2.8282828282828283,
+      "grad_norm": 0.3474580645561218,
+      "learning_rate": 4.320610440267766e-06,
+      "loss": 0.6944,
+      "step": 419
+    },
+    {
+      "epoch": 2.8350168350168348,
+      "grad_norm": 0.340483695268631,
+      "learning_rate": 4.298480340256365e-06,
+      "loss": 0.663,
+      "step": 420
+    },
+    {
+      "epoch": 2.8417508417508417,
+      "grad_norm": 0.320322185754776,
+      "learning_rate": 4.2763642499250765e-06,
+      "loss": 0.6115,
+      "step": 421
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 0.33514732122421265,
+      "learning_rate": 4.254262610942707e-06,
+      "loss": 0.6722,
+      "step": 422
+    },
+    {
+      "epoch": 2.855218855218855,
+      "grad_norm": 0.3475134074687958,
+      "learning_rate": 4.232175864689464e-06,
+      "loss": 0.6517,
+      "step": 423
+    },
+    {
+      "epoch": 2.861952861952862,
+      "grad_norm": 0.32075583934783936,
+      "learning_rate": 4.210104452248135e-06,
+      "loss": 0.6677,
+      "step": 424
+    },
+    {
+      "epoch": 2.8686868686868685,
+      "grad_norm": 0.350498229265213,
+      "learning_rate": 4.188048814395293e-06,
+      "loss": 0.6616,
+      "step": 425
+    },
+    {
+      "epoch": 2.8754208754208754,
+      "grad_norm": 0.3592052161693573,
+      "learning_rate": 4.166009391592476e-06,
+      "loss": 0.6494,
+      "step": 426
+    },
+    {
+      "epoch": 2.8821548821548824,
+      "grad_norm": 0.32770347595214844,
+      "learning_rate": 4.1439866239774065e-06,
+      "loss": 0.6604,
+      "step": 427
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.34549760818481445,
+      "learning_rate": 4.12198095135519e-06,
+      "loss": 0.657,
+      "step": 428
+    },
+    {
+      "epoch": 2.8956228956228958,
+      "grad_norm": 0.3358047604560852,
+      "learning_rate": 4.09999281318954e-06,
+      "loss": 0.6635,
+      "step": 429
+    },
+    {
+      "epoch": 2.9023569023569022,
+      "grad_norm": 0.3430233299732208,
+      "learning_rate": 4.078022648593997e-06,
+      "loss": 0.6589,
+      "step": 430
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.3354911208152771,
+      "learning_rate": 4.056070896323163e-06,
+      "loss": 0.6881,
+      "step": 431
+    },
+    {
+      "epoch": 2.915824915824916,
+      "grad_norm": 0.3450566828250885,
+      "learning_rate": 4.034137994763934e-06,
+      "loss": 0.6407,
+      "step": 432
+    },
+    {
+      "epoch": 2.9225589225589226,
+      "grad_norm": 0.32240331172943115,
+      "learning_rate": 4.01222438192675e-06,
+      "loss": 0.6892,
+      "step": 433
+    },
+    {
+      "epoch": 2.929292929292929,
+      "grad_norm": 0.3347194790840149,
+      "learning_rate": 3.990330495436848e-06,
+      "loss": 0.6664,
+      "step": 434
+    },
+    {
+      "epoch": 2.936026936026936,
+      "grad_norm": 0.354972779750824,
+      "learning_rate": 3.968456772525515e-06,
+      "loss": 0.6419,
+      "step": 435
+    },
+    {
+      "epoch": 2.942760942760943,
+      "grad_norm": 0.3557754456996918,
+      "learning_rate": 3.94660365002137e-06,
+      "loss": 0.6996,
+      "step": 436
+    },
+    {
+      "epoch": 2.9494949494949494,
+      "grad_norm": 0.35374686121940613,
+      "learning_rate": 3.924771564341621e-06,
+      "loss": 0.6786,
+      "step": 437
+    },
+    {
+      "epoch": 2.9562289562289563,
+      "grad_norm": 0.3219892680644989,
+      "learning_rate": 3.902960951483375e-06,
+      "loss": 0.6512,
+      "step": 438
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.36575546860694885,
+      "learning_rate": 3.881172247014899e-06,
+      "loss": 0.6893,
+      "step": 439
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 0.3633718490600586,
+      "learning_rate": 3.859405886066959e-06,
+      "loss": 0.6841,
+      "step": 440
+    },
+    {
+      "epoch": 2.9764309764309766,
+      "grad_norm": 0.3494553565979004,
+      "learning_rate": 3.837662303324093e-06,
+      "loss": 0.6643,
+      "step": 441
+    },
+    {
+      "epoch": 2.983164983164983,
+      "grad_norm": 0.3369433283805847,
+      "learning_rate": 3.815941933015956e-06,
+      "loss": 0.648,
+      "step": 442
+    },
+    {
+      "epoch": 2.98989898989899,
+      "grad_norm": 0.33903154730796814,
+      "learning_rate": 3.794245208908639e-06,
+      "loss": 0.6514,
+      "step": 443
+    },
+    {
+      "epoch": 2.9966329966329965,
+      "grad_norm": 0.3544797897338867,
+      "learning_rate": 3.7725725642960047e-06,
+      "loss": 0.6624,
+      "step": 444
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 740,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.92370854035456e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9ff54961c96c7c3f6b270b9ec39ea99fc537b992005e1314bb5d6de7e46a7c
+size 5752