Training in progress, epoch 0, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+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 0.15.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-4B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c03a430f900162183c844da78c9c279143d7d98694b2e99898bc0a0994d117b
+size 132187888

last-checkpoint/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ad1ee883fd30b65e7ea23f64929c18ec102e7c9130f39e537f600533e27ca6
+size 264672826

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2de36b4e01eb1249ae808d93ddc0cab7a02fec160ce612b5ca00c8162a50b107
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa967f990168a530e88ae8b8795df76b2e71d52f0690de47483c7f1210a8359c
+size 1064

last-checkpoint/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
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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 not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32935364347468093,
+  "eval_steps": 500,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0016467682173734047,
+      "grad_norm": 0.8953161835670471,
+      "learning_rate": 0.0002,
+      "loss": 1.2729,
+      "step": 4
+    },
+    {
+      "epoch": 0.0032935364347468094,
+      "grad_norm": 1.5862153768539429,
+      "learning_rate": 0.0002,
+      "loss": 0.7538,
+      "step": 8
+    },
+    {
+      "epoch": 0.004940304652120214,
+      "grad_norm": 0.8695824146270752,
+      "learning_rate": 0.0002,
+      "loss": 0.4738,
+      "step": 12
+    },
+    {
+      "epoch": 0.006587072869493619,
+      "grad_norm": 0.9425486326217651,
+      "learning_rate": 0.0002,
+      "loss": 0.4576,
+      "step": 16
+    },
+    {
+      "epoch": 0.008233841086867023,
+      "grad_norm": 0.583549439907074,
+      "learning_rate": 0.0002,
+      "loss": 0.4221,
+      "step": 20
+    },
+    {
+      "epoch": 0.009880609304240428,
+      "grad_norm": 0.658524215221405,
+      "learning_rate": 0.0002,
+      "loss": 0.4462,
+      "step": 24
+    },
+    {
+      "epoch": 0.011527377521613832,
+      "grad_norm": 0.3896760940551758,
+      "learning_rate": 0.0002,
+      "loss": 0.3846,
+      "step": 28
+    },
+    {
+      "epoch": 0.013174145738987238,
+      "grad_norm": 0.911998987197876,
+      "learning_rate": 0.0002,
+      "loss": 0.3839,
+      "step": 32
+    },
+    {
+      "epoch": 0.014820913956360642,
+      "grad_norm": 0.4576844573020935,
+      "learning_rate": 0.0002,
+      "loss": 0.3756,
+      "step": 36
+    },
+    {
+      "epoch": 0.016467682173734045,
+      "grad_norm": 0.4635961055755615,
+      "learning_rate": 0.0002,
+      "loss": 0.4354,
+      "step": 40
+    },
+    {
+      "epoch": 0.018114450391107453,
+      "grad_norm": 0.5143406987190247,
+      "learning_rate": 0.0002,
+      "loss": 0.416,
+      "step": 44
+    },
+    {
+      "epoch": 0.019761218608480857,
+      "grad_norm": 0.3770541846752167,
+      "learning_rate": 0.0002,
+      "loss": 0.41,
+      "step": 48
+    },
+    {
+      "epoch": 0.02140798682585426,
+      "grad_norm": 0.495487779378891,
+      "learning_rate": 0.0002,
+      "loss": 0.375,
+      "step": 52
+    },
+    {
+      "epoch": 0.023054755043227664,
+      "grad_norm": 0.34729987382888794,
+      "learning_rate": 0.0002,
+      "loss": 0.3548,
+      "step": 56
+    },
+    {
+      "epoch": 0.02470152326060107,
+      "grad_norm": 0.43879908323287964,
+      "learning_rate": 0.0002,
+      "loss": 0.3712,
+      "step": 60
+    },
+    {
+      "epoch": 0.026348291477974475,
+      "grad_norm": 0.3719766139984131,
+      "learning_rate": 0.0002,
+      "loss": 0.3696,
+      "step": 64
+    },
+    {
+      "epoch": 0.02799505969534788,
+      "grad_norm": 0.41326195001602173,
+      "learning_rate": 0.0002,
+      "loss": 0.3397,
+      "step": 68
+    },
+    {
+      "epoch": 0.029641827912721283,
+      "grad_norm": 0.2662048041820526,
+      "learning_rate": 0.0002,
+      "loss": 0.3243,
+      "step": 72
+    },
+    {
+      "epoch": 0.03128859613009469,
+      "grad_norm": 0.5144301056861877,
+      "learning_rate": 0.0002,
+      "loss": 0.363,
+      "step": 76
+    },
+    {
+      "epoch": 0.03293536434746809,
+      "grad_norm": 0.3776210844516754,
+      "learning_rate": 0.0002,
+      "loss": 0.3744,
+      "step": 80
+    },
+    {
+      "epoch": 0.0345821325648415,
+      "grad_norm": 0.5404049754142761,
+      "learning_rate": 0.0002,
+      "loss": 0.3786,
+      "step": 84
+    },
+    {
+      "epoch": 0.036228900782214905,
+      "grad_norm": 0.3791569173336029,
+      "learning_rate": 0.0002,
+      "loss": 0.3821,
+      "step": 88
+    },
+    {
+      "epoch": 0.03787566899958831,
+      "grad_norm": 0.3683268129825592,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 92
+    },
+    {
+      "epoch": 0.03952243721696171,
+      "grad_norm": 0.5596205592155457,
+      "learning_rate": 0.0002,
+      "loss": 0.3749,
+      "step": 96
+    },
+    {
+      "epoch": 0.04116920543433512,
+      "grad_norm": 0.26782289147377014,
+      "learning_rate": 0.0002,
+      "loss": 0.3506,
+      "step": 100
+    },
+    {
+      "epoch": 0.04281597365170852,
+      "grad_norm": 0.4424424171447754,
+      "learning_rate": 0.0002,
+      "loss": 0.4109,
+      "step": 104
+    },
+    {
+      "epoch": 0.044462741869081925,
+      "grad_norm": 0.4442334771156311,
+      "learning_rate": 0.0002,
+      "loss": 0.3886,
+      "step": 108
+    },
+    {
+      "epoch": 0.04610951008645533,
+      "grad_norm": 0.4271283745765686,
+      "learning_rate": 0.0002,
+      "loss": 0.4005,
+      "step": 112
+    },
+    {
+      "epoch": 0.04775627830382874,
+      "grad_norm": 0.2204190194606781,
+      "learning_rate": 0.0002,
+      "loss": 0.3921,
+      "step": 116
+    },
+    {
+      "epoch": 0.04940304652120214,
+      "grad_norm": 0.4910134971141815,
+      "learning_rate": 0.0002,
+      "loss": 0.3751,
+      "step": 120
+    },
+    {
+      "epoch": 0.05104981473857555,
+      "grad_norm": 0.324329674243927,
+      "learning_rate": 0.0002,
+      "loss": 0.3564,
+      "step": 124
+    },
+    {
+      "epoch": 0.05269658295594895,
+      "grad_norm": 0.2656424045562744,
+      "learning_rate": 0.0002,
+      "loss": 0.3999,
+      "step": 128
+    },
+    {
+      "epoch": 0.054343351173322355,
+      "grad_norm": 0.3686066269874573,
+      "learning_rate": 0.0002,
+      "loss": 0.3509,
+      "step": 132
+    },
+    {
+      "epoch": 0.05599011939069576,
+      "grad_norm": 0.4783218204975128,
+      "learning_rate": 0.0002,
+      "loss": 0.3445,
+      "step": 136
+    },
+    {
+      "epoch": 0.05763688760806916,
+      "grad_norm": 0.36549270153045654,
+      "learning_rate": 0.0002,
+      "loss": 0.4018,
+      "step": 140
+    },
+    {
+      "epoch": 0.059283655825442566,
+      "grad_norm": 0.35924282670021057,
+      "learning_rate": 0.0002,
+      "loss": 0.3875,
+      "step": 144
+    },
+    {
+      "epoch": 0.06093042404281598,
+      "grad_norm": 0.3744836151599884,
+      "learning_rate": 0.0002,
+      "loss": 0.3534,
+      "step": 148
+    },
+    {
+      "epoch": 0.06257719226018937,
+      "grad_norm": 0.30991196632385254,
+      "learning_rate": 0.0002,
+      "loss": 0.3367,
+      "step": 152
+    },
+    {
+      "epoch": 0.06422396047756278,
+      "grad_norm": 0.33193591237068176,
+      "learning_rate": 0.0002,
+      "loss": 0.3334,
+      "step": 156
+    },
+    {
+      "epoch": 0.06587072869493618,
+      "grad_norm": 0.4016105830669403,
+      "learning_rate": 0.0002,
+      "loss": 0.3656,
+      "step": 160
+    },
+    {
+      "epoch": 0.0675174969123096,
+      "grad_norm": 4.736868858337402,
+      "learning_rate": 0.0002,
+      "loss": 0.3925,
+      "step": 164
+    },
+    {
+      "epoch": 0.069164265129683,
+      "grad_norm": 9.175511360168457,
+      "learning_rate": 0.0002,
+      "loss": 0.3883,
+      "step": 168
+    },
+    {
+      "epoch": 0.0708110333470564,
+      "grad_norm": 0.3544243276119232,
+      "learning_rate": 0.0002,
+      "loss": 0.338,
+      "step": 172
+    },
+    {
+      "epoch": 0.07245780156442981,
+      "grad_norm": 0.5001965165138245,
+      "learning_rate": 0.0002,
+      "loss": 0.4973,
+      "step": 176
+    },
+    {
+      "epoch": 0.07410456978180321,
+      "grad_norm": 0.3355480432510376,
+      "learning_rate": 0.0002,
+      "loss": 0.4024,
+      "step": 180
+    },
+    {
+      "epoch": 0.07575133799917662,
+      "grad_norm": 0.5296071767807007,
+      "learning_rate": 0.0002,
+      "loss": 0.4062,
+      "step": 184
+    },
+    {
+      "epoch": 0.07739810621655002,
+      "grad_norm": 0.24464838206768036,
+      "learning_rate": 0.0002,
+      "loss": 0.3381,
+      "step": 188
+    },
+    {
+      "epoch": 0.07904487443392343,
+      "grad_norm": 0.32045015692710876,
+      "learning_rate": 0.0002,
+      "loss": 0.3486,
+      "step": 192
+    },
+    {
+      "epoch": 0.08069164265129683,
+      "grad_norm": 0.34248587489128113,
+      "learning_rate": 0.0002,
+      "loss": 0.3586,
+      "step": 196
+    },
+    {
+      "epoch": 0.08233841086867023,
+      "grad_norm": 0.4850979447364807,
+      "learning_rate": 0.0002,
+      "loss": 0.3781,
+      "step": 200
+    },
+    {
+      "epoch": 0.08398517908604364,
+      "grad_norm": 0.34937235713005066,
+      "learning_rate": 0.0002,
+      "loss": 0.3947,
+      "step": 204
+    },
+    {
+      "epoch": 0.08563194730341704,
+      "grad_norm": 0.42456161975860596,
+      "learning_rate": 0.0002,
+      "loss": 0.4083,
+      "step": 208
+    },
+    {
+      "epoch": 0.08727871552079045,
+      "grad_norm": 0.23034583032131195,
+      "learning_rate": 0.0002,
+      "loss": 0.3825,
+      "step": 212
+    },
+    {
+      "epoch": 0.08892548373816385,
+      "grad_norm": 0.3292698264122009,
+      "learning_rate": 0.0002,
+      "loss": 0.3538,
+      "step": 216
+    },
+    {
+      "epoch": 0.09057225195553725,
+      "grad_norm": 0.39245980978012085,
+      "learning_rate": 0.0002,
+      "loss": 0.4415,
+      "step": 220
+    },
+    {
+      "epoch": 0.09221902017291066,
+      "grad_norm": 0.2923140823841095,
+      "learning_rate": 0.0002,
+      "loss": 0.3788,
+      "step": 224
+    },
+    {
+      "epoch": 0.09386578839028406,
+      "grad_norm": 0.207213893532753,
+      "learning_rate": 0.0002,
+      "loss": 0.3539,
+      "step": 228
+    },
+    {
+      "epoch": 0.09551255660765748,
+      "grad_norm": 0.3439698815345764,
+      "learning_rate": 0.0002,
+      "loss": 0.3607,
+      "step": 232
+    },
+    {
+      "epoch": 0.09715932482503088,
+      "grad_norm": 0.5888385772705078,
+      "learning_rate": 0.0002,
+      "loss": 0.3689,
+      "step": 236
+    },
+    {
+      "epoch": 0.09880609304240429,
+      "grad_norm": 0.4489259123802185,
+      "learning_rate": 0.0002,
+      "loss": 0.385,
+      "step": 240
+    },
+    {
+      "epoch": 0.10045286125977769,
+      "grad_norm": 0.2808224558830261,
+      "learning_rate": 0.0002,
+      "loss": 0.3557,
+      "step": 244
+    },
+    {
+      "epoch": 0.1020996294771511,
+      "grad_norm": 0.3597584366798401,
+      "learning_rate": 0.0002,
+      "loss": 0.3883,
+      "step": 248
+    },
+    {
+      "epoch": 0.1037463976945245,
+      "grad_norm": 0.32132285833358765,
+      "learning_rate": 0.0002,
+      "loss": 0.4035,
+      "step": 252
+    },
+    {
+      "epoch": 0.1053931659118979,
+      "grad_norm": 0.22531771659851074,
+      "learning_rate": 0.0002,
+      "loss": 0.3779,
+      "step": 256
+    },
+    {
+      "epoch": 0.1070399341292713,
+      "grad_norm": 0.318766325712204,
+      "learning_rate": 0.0002,
+      "loss": 0.3744,
+      "step": 260
+    },
+    {
+      "epoch": 0.10868670234664471,
+      "grad_norm": 0.6397304534912109,
+      "learning_rate": 0.0002,
+      "loss": 0.3393,
+      "step": 264
+    },
+    {
+      "epoch": 0.11033347056401811,
+      "grad_norm": 0.6063392758369446,
+      "learning_rate": 0.0002,
+      "loss": 0.3951,
+      "step": 268
+    },
+    {
+      "epoch": 0.11198023878139152,
+      "grad_norm": 0.24683332443237305,
+      "learning_rate": 0.0002,
+      "loss": 0.3553,
+      "step": 272
+    },
+    {
+      "epoch": 0.11362700699876492,
+      "grad_norm": 0.31904444098472595,
+      "learning_rate": 0.0002,
+      "loss": 0.3304,
+      "step": 276
+    },
+    {
+      "epoch": 0.11527377521613832,
+      "grad_norm": 0.28900399804115295,
+      "learning_rate": 0.0002,
+      "loss": 0.3497,
+      "step": 280
+    },
+    {
+      "epoch": 0.11692054343351173,
+      "grad_norm": 0.40302807092666626,
+      "learning_rate": 0.0002,
+      "loss": 0.3565,
+      "step": 284
+    },
+    {
+      "epoch": 0.11856731165088513,
+      "grad_norm": 0.2882011830806732,
+      "learning_rate": 0.0002,
+      "loss": 0.3915,
+      "step": 288
+    },
+    {
+      "epoch": 0.12021407986825854,
+      "grad_norm": 0.24462762475013733,
+      "learning_rate": 0.0002,
+      "loss": 0.3608,
+      "step": 292
+    },
+    {
+      "epoch": 0.12186084808563195,
+      "grad_norm": 0.37398672103881836,
+      "learning_rate": 0.0002,
+      "loss": 0.3845,
+      "step": 296
+    },
+    {
+      "epoch": 0.12350761630300536,
+      "grad_norm": 0.18008679151535034,
+      "learning_rate": 0.0002,
+      "loss": 0.3793,
+      "step": 300
+    },
+    {
+      "epoch": 0.12515438452037875,
+      "grad_norm": 0.28548237681388855,
+      "learning_rate": 0.0002,
+      "loss": 0.3658,
+      "step": 304
+    },
+    {
+      "epoch": 0.12680115273775217,
+      "grad_norm": 0.41167348623275757,
+      "learning_rate": 0.0002,
+      "loss": 0.3583,
+      "step": 308
+    },
+    {
+      "epoch": 0.12844792095512556,
+      "grad_norm": 0.25915321707725525,
+      "learning_rate": 0.0002,
+      "loss": 0.3468,
+      "step": 312
+    },
+    {
+      "epoch": 0.13009468917249897,
+      "grad_norm": 0.20780526101589203,
+      "learning_rate": 0.0002,
+      "loss": 0.3748,
+      "step": 316
+    },
+    {
+      "epoch": 0.13174145738987236,
+      "grad_norm": 0.34936532378196716,
+      "learning_rate": 0.0002,
+      "loss": 0.3696,
+      "step": 320
+    },
+    {
+      "epoch": 0.13338822560724578,
+      "grad_norm": 0.32812872529029846,
+      "learning_rate": 0.0002,
+      "loss": 0.3567,
+      "step": 324
+    },
+    {
+      "epoch": 0.1350349938246192,
+      "grad_norm": 0.4097863435745239,
+      "learning_rate": 0.0002,
+      "loss": 0.3421,
+      "step": 328
+    },
+    {
+      "epoch": 0.1366817620419926,
+      "grad_norm": 0.37446022033691406,
+      "learning_rate": 0.0002,
+      "loss": 0.3543,
+      "step": 332
+    },
+    {
+      "epoch": 0.138328530259366,
+      "grad_norm": 0.3094286024570465,
+      "learning_rate": 0.0002,
+      "loss": 0.3581,
+      "step": 336
+    },
+    {
+      "epoch": 0.1399752984767394,
+      "grad_norm": 0.480590283870697,
+      "learning_rate": 0.0002,
+      "loss": 0.3815,
+      "step": 340
+    },
+    {
+      "epoch": 0.1416220666941128,
+      "grad_norm": 0.7308598160743713,
+      "learning_rate": 0.0002,
+      "loss": 0.3773,
+      "step": 344
+    },
+    {
+      "epoch": 0.1432688349114862,
+      "grad_norm": 0.30192887783050537,
+      "learning_rate": 0.0002,
+      "loss": 0.321,
+      "step": 348
+    },
+    {
+      "epoch": 0.14491560312885962,
+      "grad_norm": 0.4484156668186188,
+      "learning_rate": 0.0002,
+      "loss": 0.3656,
+      "step": 352
+    },
+    {
+      "epoch": 0.146562371346233,
+      "grad_norm": 0.7545529007911682,
+      "learning_rate": 0.0002,
+      "loss": 0.3705,
+      "step": 356
+    },
+    {
+      "epoch": 0.14820913956360643,
+      "grad_norm": 0.31941813230514526,
+      "learning_rate": 0.0002,
+      "loss": 0.4046,
+      "step": 360
+    },
+    {
+      "epoch": 0.14985590778097982,
+      "grad_norm": 0.3942190706729889,
+      "learning_rate": 0.0002,
+      "loss": 0.3426,
+      "step": 364
+    },
+    {
+      "epoch": 0.15150267599835324,
+      "grad_norm": 0.35361188650131226,
+      "learning_rate": 0.0002,
+      "loss": 0.3852,
+      "step": 368
+    },
+    {
+      "epoch": 0.15314944421572663,
+      "grad_norm": 0.3657994866371155,
+      "learning_rate": 0.0002,
+      "loss": 0.3582,
+      "step": 372
+    },
+    {
+      "epoch": 0.15479621243310004,
+      "grad_norm": 0.34935927391052246,
+      "learning_rate": 0.0002,
+      "loss": 0.3879,
+      "step": 376
+    },
+    {
+      "epoch": 0.15644298065047343,
+      "grad_norm": 0.30978021025657654,
+      "learning_rate": 0.0002,
+      "loss": 0.3272,
+      "step": 380
+    },
+    {
+      "epoch": 0.15808974886784685,
+      "grad_norm": 0.506018877029419,
+      "learning_rate": 0.0002,
+      "loss": 0.3961,
+      "step": 384
+    },
+    {
+      "epoch": 0.15973651708522024,
+      "grad_norm": 0.3043360412120819,
+      "learning_rate": 0.0002,
+      "loss": 0.3576,
+      "step": 388
+    },
+    {
+      "epoch": 0.16138328530259366,
+      "grad_norm": 0.179752916097641,
+      "learning_rate": 0.0002,
+      "loss": 0.3734,
+      "step": 392
+    },
+    {
+      "epoch": 0.16303005351996708,
+      "grad_norm": 0.27808040380477905,
+      "learning_rate": 0.0002,
+      "loss": 0.3671,
+      "step": 396
+    },
+    {
+      "epoch": 0.16467682173734047,
+      "grad_norm": 0.3754728138446808,
+      "learning_rate": 0.0002,
+      "loss": 0.348,
+      "step": 400
+    },
+    {
+      "epoch": 0.16632358995471389,
+      "grad_norm": 0.3945702314376831,
+      "learning_rate": 0.0002,
+      "loss": 0.3636,
+      "step": 404
+    },
+    {
+      "epoch": 0.16797035817208728,
+      "grad_norm": 0.3527517020702362,
+      "learning_rate": 0.0002,
+      "loss": 0.3696,
+      "step": 408
+    },
+    {
+      "epoch": 0.1696171263894607,
+      "grad_norm": 0.3773639500141144,
+      "learning_rate": 0.0002,
+      "loss": 0.3473,
+      "step": 412
+    },
+    {
+      "epoch": 0.17126389460683408,
+      "grad_norm": 0.4464412033557892,
+      "learning_rate": 0.0002,
+      "loss": 0.4264,
+      "step": 416
+    },
+    {
+      "epoch": 0.1729106628242075,
+      "grad_norm": 0.42413341999053955,
+      "learning_rate": 0.0002,
+      "loss": 0.4167,
+      "step": 420
+    },
+    {
+      "epoch": 0.1745574310415809,
+      "grad_norm": 0.25921425223350525,
+      "learning_rate": 0.0002,
+      "loss": 0.3779,
+      "step": 424
+    },
+    {
+      "epoch": 0.1762041992589543,
+      "grad_norm": 0.3992401361465454,
+      "learning_rate": 0.0002,
+      "loss": 0.393,
+      "step": 428
+    },
+    {
+      "epoch": 0.1778509674763277,
+      "grad_norm": 0.2668096125125885,
+      "learning_rate": 0.0002,
+      "loss": 0.3727,
+      "step": 432
+    },
+    {
+      "epoch": 0.17949773569370112,
+      "grad_norm": 0.3423740565776825,
+      "learning_rate": 0.0002,
+      "loss": 0.391,
+      "step": 436
+    },
+    {
+      "epoch": 0.1811445039110745,
+      "grad_norm": 0.2589094340801239,
+      "learning_rate": 0.0002,
+      "loss": 0.3229,
+      "step": 440
+    },
+    {
+      "epoch": 0.18279127212844792,
+      "grad_norm": 0.3569371700286865,
+      "learning_rate": 0.0002,
+      "loss": 0.3844,
+      "step": 444
+    },
+    {
+      "epoch": 0.1844380403458213,
+      "grad_norm": 0.3202153742313385,
+      "learning_rate": 0.0002,
+      "loss": 0.3491,
+      "step": 448
+    },
+    {
+      "epoch": 0.18608480856319473,
+      "grad_norm": 0.28952282667160034,
+      "learning_rate": 0.0002,
+      "loss": 0.3524,
+      "step": 452
+    },
+    {
+      "epoch": 0.18773157678056812,
+      "grad_norm": 0.24042993783950806,
+      "learning_rate": 0.0002,
+      "loss": 0.3446,
+      "step": 456
+    },
+    {
+      "epoch": 0.18937834499794154,
+      "grad_norm": 0.24099212884902954,
+      "learning_rate": 0.0002,
+      "loss": 0.3446,
+      "step": 460
+    },
+    {
+      "epoch": 0.19102511321531496,
+      "grad_norm": 0.2019130438566208,
+      "learning_rate": 0.0002,
+      "loss": 0.3489,
+      "step": 464
+    },
+    {
+      "epoch": 0.19267188143268835,
+      "grad_norm": 0.3622491955757141,
+      "learning_rate": 0.0002,
+      "loss": 0.3568,
+      "step": 468
+    },
+    {
+      "epoch": 0.19431864965006176,
+      "grad_norm": 0.3211140036582947,
+      "learning_rate": 0.0002,
+      "loss": 0.397,
+      "step": 472
+    },
+    {
+      "epoch": 0.19596541786743515,
+      "grad_norm": 0.2493632435798645,
+      "learning_rate": 0.0002,
+      "loss": 0.3621,
+      "step": 476
+    },
+    {
+      "epoch": 0.19761218608480857,
+      "grad_norm": 0.5503110885620117,
+      "learning_rate": 0.0002,
+      "loss": 0.3579,
+      "step": 480
+    },
+    {
+      "epoch": 0.19925895430218196,
+      "grad_norm": 0.4082036316394806,
+      "learning_rate": 0.0002,
+      "loss": 0.3028,
+      "step": 484
+    },
+    {
+      "epoch": 0.20090572251955538,
+      "grad_norm": 0.41690894961357117,
+      "learning_rate": 0.0002,
+      "loss": 0.3921,
+      "step": 488
+    },
+    {
+      "epoch": 0.20255249073692877,
+      "grad_norm": 0.35619014501571655,
+      "learning_rate": 0.0002,
+      "loss": 0.3799,
+      "step": 492
+    },
+    {
+      "epoch": 0.2041992589543022,
+      "grad_norm": 2.7761363983154297,
+      "learning_rate": 0.0002,
+      "loss": 0.4695,
+      "step": 496
+    },
+    {
+      "epoch": 0.20584602717167558,
+      "grad_norm": 0.38763320446014404,
+      "learning_rate": 0.0002,
+      "loss": 0.5242,
+      "step": 500
+    },
+    {
+      "epoch": 0.207492795389049,
+      "grad_norm": 1.2838047742843628,
+      "learning_rate": 0.0002,
+      "loss": 0.4055,
+      "step": 504
+    },
+    {
+      "epoch": 0.20913956360642239,
+      "grad_norm": 0.4990096986293793,
+      "learning_rate": 0.0002,
+      "loss": 0.369,
+      "step": 508
+    },
+    {
+      "epoch": 0.2107863318237958,
+      "grad_norm": 0.3528285026550293,
+      "learning_rate": 0.0002,
+      "loss": 0.3755,
+      "step": 512
+    },
+    {
+      "epoch": 0.2124331000411692,
+      "grad_norm": 0.3972186744213104,
+      "learning_rate": 0.0002,
+      "loss": 0.4113,
+      "step": 516
+    },
+    {
+      "epoch": 0.2140798682585426,
+      "grad_norm": 0.5024253726005554,
+      "learning_rate": 0.0002,
+      "loss": 0.3837,
+      "step": 520
+    },
+    {
+      "epoch": 0.21572663647591603,
+      "grad_norm": 0.3288867175579071,
+      "learning_rate": 0.0002,
+      "loss": 0.3585,
+      "step": 524
+    },
+    {
+      "epoch": 0.21737340469328942,
+      "grad_norm": 0.5578015446662903,
+      "learning_rate": 0.0002,
+      "loss": 0.4363,
+      "step": 528
+    },
+    {
+      "epoch": 0.21902017291066284,
+      "grad_norm": 0.33496353030204773,
+      "learning_rate": 0.0002,
+      "loss": 0.3783,
+      "step": 532
+    },
+    {
+      "epoch": 0.22066694112803623,
+      "grad_norm": 0.26905229687690735,
+      "learning_rate": 0.0002,
+      "loss": 0.3569,
+      "step": 536
+    },
+    {
+      "epoch": 0.22231370934540964,
+      "grad_norm": 0.2863016128540039,
+      "learning_rate": 0.0002,
+      "loss": 0.3505,
+      "step": 540
+    },
+    {
+      "epoch": 0.22396047756278303,
+      "grad_norm": 0.46342360973358154,
+      "learning_rate": 0.0002,
+      "loss": 0.3698,
+      "step": 544
+    },
+    {
+      "epoch": 0.22560724578015645,
+      "grad_norm": 0.4255537986755371,
+      "learning_rate": 0.0002,
+      "loss": 0.3864,
+      "step": 548
+    },
+    {
+      "epoch": 0.22725401399752984,
+      "grad_norm": 0.46673330664634705,
+      "learning_rate": 0.0002,
+      "loss": 0.4047,
+      "step": 552
+    },
+    {
+      "epoch": 0.22890078221490326,
+      "grad_norm": 0.3291438817977905,
+      "learning_rate": 0.0002,
+      "loss": 0.3813,
+      "step": 556
+    },
+    {
+      "epoch": 0.23054755043227665,
+      "grad_norm": 0.31650590896606445,
+      "learning_rate": 0.0002,
+      "loss": 0.3566,
+      "step": 560
+    },
+    {
+      "epoch": 0.23219431864965007,
+      "grad_norm": 0.18546172976493835,
+      "learning_rate": 0.0002,
+      "loss": 0.3213,
+      "step": 564
+    },
+    {
+      "epoch": 0.23384108686702346,
+      "grad_norm": 0.3104104995727539,
+      "learning_rate": 0.0002,
+      "loss": 0.3874,
+      "step": 568
+    },
+    {
+      "epoch": 0.23548785508439687,
+      "grad_norm": 0.32556912302970886,
+      "learning_rate": 0.0002,
+      "loss": 0.3105,
+      "step": 572
+    },
+    {
+      "epoch": 0.23713462330177026,
+      "grad_norm": 0.9034080505371094,
+      "learning_rate": 0.0002,
+      "loss": 0.4377,
+      "step": 576
+    },
+    {
+      "epoch": 0.23878139151914368,
+      "grad_norm": 0.6370987296104431,
+      "learning_rate": 0.0002,
+      "loss": 0.3497,
+      "step": 580
+    },
+    {
+      "epoch": 0.24042815973651707,
+      "grad_norm": 0.4280830919742584,
+      "learning_rate": 0.0002,
+      "loss": 0.4,
+      "step": 584
+    },
+    {
+      "epoch": 0.2420749279538905,
+      "grad_norm": 0.44038718938827515,
+      "learning_rate": 0.0002,
+      "loss": 0.4012,
+      "step": 588
+    },
+    {
+      "epoch": 0.2437216961712639,
+      "grad_norm": 0.2128431349992752,
+      "learning_rate": 0.0002,
+      "loss": 0.3304,
+      "step": 592
+    },
+    {
+      "epoch": 0.2453684643886373,
+      "grad_norm": 0.4544263482093811,
+      "learning_rate": 0.0002,
+      "loss": 0.3944,
+      "step": 596
+    },
+    {
+      "epoch": 0.24701523260601072,
+      "grad_norm": 0.3102782070636749,
+      "learning_rate": 0.0002,
+      "loss": 0.3834,
+      "step": 600
+    },
+    {
+      "epoch": 0.2486620008233841,
+      "grad_norm": 0.24082337319850922,
+      "learning_rate": 0.0002,
+      "loss": 0.3544,
+      "step": 604
+    },
+    {
+      "epoch": 0.2503087690407575,
+      "grad_norm": 0.33522674441337585,
+      "learning_rate": 0.0002,
+      "loss": 0.3516,
+      "step": 608
+    },
+    {
+      "epoch": 0.2519555372581309,
+      "grad_norm": 0.5705686211585999,
+      "learning_rate": 0.0002,
+      "loss": 0.3423,
+      "step": 612
+    },
+    {
+      "epoch": 0.25360230547550433,
+      "grad_norm": 0.28851550817489624,
+      "learning_rate": 0.0002,
+      "loss": 0.3588,
+      "step": 616
+    },
+    {
+      "epoch": 0.25524907369287775,
+      "grad_norm": 0.37969881296157837,
+      "learning_rate": 0.0002,
+      "loss": 0.378,
+      "step": 620
+    },
+    {
+      "epoch": 0.2568958419102511,
+      "grad_norm": 0.40770289301872253,
+      "learning_rate": 0.0002,
+      "loss": 0.363,
+      "step": 624
+    },
+    {
+      "epoch": 0.25854261012762453,
+      "grad_norm": 0.45175468921661377,
+      "learning_rate": 0.0002,
+      "loss": 0.3539,
+      "step": 628
+    },
+    {
+      "epoch": 0.26018937834499795,
+      "grad_norm": 0.5527524948120117,
+      "learning_rate": 0.0002,
+      "loss": 0.3452,
+      "step": 632
+    },
+    {
+      "epoch": 0.26183614656237136,
+      "grad_norm": 0.5055177211761475,
+      "learning_rate": 0.0002,
+      "loss": 0.3744,
+      "step": 636
+    },
+    {
+      "epoch": 0.2634829147797447,
+      "grad_norm": 0.27861982583999634,
+      "learning_rate": 0.0002,
+      "loss": 0.3748,
+      "step": 640
+    },
+    {
+      "epoch": 0.26512968299711814,
+      "grad_norm": 0.24840442836284637,
+      "learning_rate": 0.0002,
+      "loss": 0.427,
+      "step": 644
+    },
+    {
+      "epoch": 0.26677645121449156,
+      "grad_norm": 0.3442547023296356,
+      "learning_rate": 0.0002,
+      "loss": 0.3569,
+      "step": 648
+    },
+    {
+      "epoch": 0.268423219431865,
+      "grad_norm": 0.39899468421936035,
+      "learning_rate": 0.0002,
+      "loss": 0.3811,
+      "step": 652
+    },
+    {
+      "epoch": 0.2700699876492384,
+      "grad_norm": 0.29878517985343933,
+      "learning_rate": 0.0002,
+      "loss": 0.4218,
+      "step": 656
+    },
+    {
+      "epoch": 0.27171675586661176,
+      "grad_norm": 0.2453669160604477,
+      "learning_rate": 0.0002,
+      "loss": 0.3881,
+      "step": 660
+    },
+    {
+      "epoch": 0.2733635240839852,
+      "grad_norm": 0.3179525136947632,
+      "learning_rate": 0.0002,
+      "loss": 0.3606,
+      "step": 664
+    },
+    {
+      "epoch": 0.2750102923013586,
+      "grad_norm": 0.4071681797504425,
+      "learning_rate": 0.0002,
+      "loss": 0.3666,
+      "step": 668
+    },
+    {
+      "epoch": 0.276657060518732,
+      "grad_norm": 0.20715802907943726,
+      "learning_rate": 0.0002,
+      "loss": 0.4557,
+      "step": 672
+    },
+    {
+      "epoch": 0.2783038287361054,
+      "grad_norm": 0.32174447178840637,
+      "learning_rate": 0.0002,
+      "loss": 0.3465,
+      "step": 676
+    },
+    {
+      "epoch": 0.2799505969534788,
+      "grad_norm": 0.4294211268424988,
+      "learning_rate": 0.0002,
+      "loss": 0.4125,
+      "step": 680
+    },
+    {
+      "epoch": 0.2815973651708522,
+      "grad_norm": 0.44794681668281555,
+      "learning_rate": 0.0002,
+      "loss": 0.3676,
+      "step": 684
+    },
+    {
+      "epoch": 0.2832441333882256,
+      "grad_norm": 0.29573217034339905,
+      "learning_rate": 0.0002,
+      "loss": 0.352,
+      "step": 688
+    },
+    {
+      "epoch": 0.284890901605599,
+      "grad_norm": 0.4403010904788971,
+      "learning_rate": 0.0002,
+      "loss": 0.356,
+      "step": 692
+    },
+    {
+      "epoch": 0.2865376698229724,
+      "grad_norm": 0.5202733278274536,
+      "learning_rate": 0.0002,
+      "loss": 0.3888,
+      "step": 696
+    },
+    {
+      "epoch": 0.2881844380403458,
+      "grad_norm": 0.44568759202957153,
+      "learning_rate": 0.0002,
+      "loss": 0.3591,
+      "step": 700
+    },
+    {
+      "epoch": 0.28983120625771924,
+      "grad_norm": 0.3248206675052643,
+      "learning_rate": 0.0002,
+      "loss": 0.3368,
+      "step": 704
+    },
+    {
+      "epoch": 0.2914779744750926,
+      "grad_norm": 0.3348717987537384,
+      "learning_rate": 0.0002,
+      "loss": 0.3539,
+      "step": 708
+    },
+    {
+      "epoch": 0.293124742692466,
+      "grad_norm": 0.5104221105575562,
+      "learning_rate": 0.0002,
+      "loss": 0.3917,
+      "step": 712
+    },
+    {
+      "epoch": 0.29477151090983944,
+      "grad_norm": 0.46784690022468567,
+      "learning_rate": 0.0002,
+      "loss": 0.3887,
+      "step": 716
+    },
+    {
+      "epoch": 0.29641827912721286,
+      "grad_norm": 0.37764814496040344,
+      "learning_rate": 0.0002,
+      "loss": 0.3503,
+      "step": 720
+    },
+    {
+      "epoch": 0.2980650473445863,
+      "grad_norm": 0.17547918856143951,
+      "learning_rate": 0.0002,
+      "loss": 0.3264,
+      "step": 724
+    },
+    {
+      "epoch": 0.29971181556195964,
+      "grad_norm": 0.5112257599830627,
+      "learning_rate": 0.0002,
+      "loss": 0.3981,
+      "step": 728
+    },
+    {
+      "epoch": 0.30135858377933306,
+      "grad_norm": 0.3400379717350006,
+      "learning_rate": 0.0002,
+      "loss": 0.377,
+      "step": 732
+    },
+    {
+      "epoch": 0.3030053519967065,
+      "grad_norm": 0.33754292130470276,
+      "learning_rate": 0.0002,
+      "loss": 0.3329,
+      "step": 736
+    },
+    {
+      "epoch": 0.3046521202140799,
+      "grad_norm": 0.2636474668979645,
+      "learning_rate": 0.0002,
+      "loss": 0.326,
+      "step": 740
+    },
+    {
+      "epoch": 0.30629888843145325,
+      "grad_norm": 0.4797205924987793,
+      "learning_rate": 0.0002,
+      "loss": 0.3298,
+      "step": 744
+    },
+    {
+      "epoch": 0.30794565664882667,
+      "grad_norm": 0.5526637434959412,
+      "learning_rate": 0.0002,
+      "loss": 0.4004,
+      "step": 748
+    },
+    {
+      "epoch": 0.3095924248662001,
+      "grad_norm": 0.4279467463493347,
+      "learning_rate": 0.0002,
+      "loss": 0.383,
+      "step": 752
+    },
+    {
+      "epoch": 0.3112391930835735,
+      "grad_norm": 0.28754350543022156,
+      "learning_rate": 0.0002,
+      "loss": 0.3714,
+      "step": 756
+    },
+    {
+      "epoch": 0.31288596130094687,
+      "grad_norm": 0.29990026354789734,
+      "learning_rate": 0.0002,
+      "loss": 0.3753,
+      "step": 760
+    },
+    {
+      "epoch": 0.3145327295183203,
+      "grad_norm": 0.30254223942756653,
+      "learning_rate": 0.0002,
+      "loss": 0.3609,
+      "step": 764
+    },
+    {
+      "epoch": 0.3161794977356937,
+      "grad_norm": 0.8052358031272888,
+      "learning_rate": 0.0002,
+      "loss": 0.414,
+      "step": 768
+    },
+    {
+      "epoch": 0.3178262659530671,
+      "grad_norm": 0.5187978744506836,
+      "learning_rate": 0.0002,
+      "loss": 0.3906,
+      "step": 772
+    },
+    {
+      "epoch": 0.3194730341704405,
+      "grad_norm": 0.43508270382881165,
+      "learning_rate": 0.0002,
+      "loss": 0.3532,
+      "step": 776
+    },
+    {
+      "epoch": 0.3211198023878139,
+      "grad_norm": 0.3715954124927521,
+      "learning_rate": 0.0002,
+      "loss": 0.3464,
+      "step": 780
+    },
+    {
+      "epoch": 0.3227665706051873,
+      "grad_norm": 0.2788250148296356,
+      "learning_rate": 0.0002,
+      "loss": 0.3788,
+      "step": 784
+    },
+    {
+      "epoch": 0.32441333882256074,
+      "grad_norm": 0.3440225422382355,
+      "learning_rate": 0.0002,
+      "loss": 0.3591,
+      "step": 788
+    },
+    {
+      "epoch": 0.32606010703993416,
+      "grad_norm": 0.4949939250946045,
+      "learning_rate": 0.0002,
+      "loss": 0.373,
+      "step": 792
+    },
+    {
+      "epoch": 0.3277068752573075,
+      "grad_norm": 0.3172508180141449,
+      "learning_rate": 0.0002,
+      "loss": 0.3971,
+      "step": 796
+    },
+    {
+      "epoch": 0.32935364347468093,
+      "grad_norm": 0.4251808226108551,
+      "learning_rate": 0.0002,
+      "loss": 0.3554,
+      "step": 800
+    }
+  ],
+  "logging_steps": 4,
+  "max_steps": 800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.88348602105856e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2f80b57d94f278467008f794e8740b768c7e0c9d8ee79bd4ea24074e4132d2
+size 7160