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 +1,210 @@
+---
+base_model: unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097d5196bcf3b163451a1a7ff09b82ec88037bae30892f67ca3c28426e85b8e2
+size 323014168

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 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
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a4b0f1731e6edbdd38688d40ea7ab1d2179fc8d1b7230f06033dac48be44e3
+size 164465413

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df20b155c6c71ba517a94d5f1e2e7dda50a33a536607f61184d8be5ae5706208
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84194bf2a3f4a7a6d2f28d6d19d68f7e053be06766e12d3e36c88146a7ff1ace
+size 1465

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": "<|PAD_TOKEN|>",
+    "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:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

tokenizer_config.json

@@ -0,0 +1,217 @@
+{
+  "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": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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 Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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": {},
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1454 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9997049277072882,
+  "eval_steps": 500,
+  "global_step": 10166,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009835743090390479,
+      "grad_norm": 0.05815335735678673,
+      "learning_rate": 0.00019999032134813635,
+      "loss": 0.9008,
+      "step": 50
+    },
+    {
+      "epoch": 0.019671486180780958,
+      "grad_norm": 0.06804105639457703,
+      "learning_rate": 0.00019995686668528316,
+      "loss": 0.7784,
+      "step": 100
+    },
+    {
+      "epoch": 0.029507229271171435,
+      "grad_norm": 0.07179820537567139,
+      "learning_rate": 0.0001998995245149411,
+      "loss": 0.765,
+      "step": 150
+    },
+    {
+      "epoch": 0.039342972361561916,
+      "grad_norm": 0.07887151092290878,
+      "learning_rate": 0.00019981830854063617,
+      "loss": 0.7539,
+      "step": 200
+    },
+    {
+      "epoch": 0.0491787154519524,
+      "grad_norm": 0.06816300749778748,
+      "learning_rate": 0.00019971323817121194,
+      "loss": 0.7355,
+      "step": 250
+    },
+    {
+      "epoch": 0.05901445854234287,
+      "grad_norm": 0.0781150683760643,
+      "learning_rate": 0.00019958433851619142,
+      "loss": 0.7295,
+      "step": 300
+    },
+    {
+      "epoch": 0.06885020163273335,
+      "grad_norm": 0.07763133943080902,
+      "learning_rate": 0.00019943164037977625,
+      "loss": 0.7326,
+      "step": 350
+    },
+    {
+      "epoch": 0.07868594472312383,
+      "grad_norm": 0.07704794406890869,
+      "learning_rate": 0.00019925518025348511,
+      "loss": 0.7267,
+      "step": 400
+    },
+    {
+      "epoch": 0.08852168781351431,
+      "grad_norm": 0.06781066209077835,
+      "learning_rate": 0.00019905500030743332,
+      "loss": 0.7203,
+      "step": 450
+    },
+    {
+      "epoch": 0.0983574309039048,
+      "grad_norm": 0.06790652126073837,
+      "learning_rate": 0.00019883114838025484,
+      "loss": 0.7243,
+      "step": 500
+    },
+    {
+      "epoch": 0.10819317399429527,
+      "grad_norm": 0.07213232666254044,
+      "learning_rate": 0.00019858367796767002,
+      "loss": 0.7159,
+      "step": 550
+    },
+    {
+      "epoch": 0.11802891708468574,
+      "grad_norm": 0.06770846992731094,
+      "learning_rate": 0.00019831264820970127,
+      "loss": 0.7115,
+      "step": 600
+    },
+    {
+      "epoch": 0.12786466017507622,
+      "grad_norm": 0.07667895406484604,
+      "learning_rate": 0.00019801812387653983,
+      "loss": 0.7135,
+      "step": 650
+    },
+    {
+      "epoch": 0.1377004032654667,
+      "grad_norm": 0.06398730725049973,
+      "learning_rate": 0.00019770017535306717,
+      "loss": 0.707,
+      "step": 700
+    },
+    {
+      "epoch": 0.14753614635585718,
+      "grad_norm": 0.0711282268166542,
+      "learning_rate": 0.00019735887862203457,
+      "loss": 0.7045,
+      "step": 750
+    },
+    {
+      "epoch": 0.15737188944624766,
+      "grad_norm": 0.06350903958082199,
+      "learning_rate": 0.00019699431524590477,
+      "loss": 0.6977,
+      "step": 800
+    },
+    {
+      "epoch": 0.16720763253663815,
+      "grad_norm": 0.06291402131319046,
+      "learning_rate": 0.00019660657234736045,
+      "loss": 0.7017,
+      "step": 850
+    },
+    {
+      "epoch": 0.17704337562702863,
+      "grad_norm": 0.07249592989683151,
+      "learning_rate": 0.00019619574258848376,
+      "loss": 0.6997,
+      "step": 900
+    },
+    {
+      "epoch": 0.1868791187174191,
+      "grad_norm": 0.07148096710443497,
+      "learning_rate": 0.00019576192414861215,
+      "loss": 0.6931,
+      "step": 950
+    },
+    {
+      "epoch": 0.1967148618078096,
+      "grad_norm": 0.080138199031353,
+      "learning_rate": 0.00019530522070087554,
+      "loss": 0.6956,
+      "step": 1000
+    },
+    {
+      "epoch": 0.20655060489820007,
+      "grad_norm": 0.07587867230176926,
+      "learning_rate": 0.00019482574138742086,
+      "loss": 0.6972,
+      "step": 1050
+    },
+    {
+      "epoch": 0.21638634798859055,
+      "grad_norm": 0.0822625681757927,
+      "learning_rate": 0.0001943236007933294,
+      "loss": 0.6887,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22622209107898103,
+      "grad_norm": 0.06909151375293732,
+      "learning_rate": 0.0001937989189192334,
+      "loss": 0.6872,
+      "step": 1150
+    },
+    {
+      "epoch": 0.23605783416937148,
+      "grad_norm": 0.06804945319890976,
+      "learning_rate": 0.00019325182115263859,
+      "loss": 0.6875,
+      "step": 1200
+    },
+    {
+      "epoch": 0.24589357725976196,
+      "grad_norm": 0.07097342610359192,
+      "learning_rate": 0.00019268243823795936,
+      "loss": 0.6794,
+      "step": 1250
+    },
+    {
+      "epoch": 0.25572932035015244,
+      "grad_norm": 0.06648524850606918,
+      "learning_rate": 0.0001920909062452736,
+      "loss": 0.6844,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2655650634405429,
+      "grad_norm": 0.06843659281730652,
+      "learning_rate": 0.00019147736653780508,
+      "loss": 0.684,
+      "step": 1350
+    },
+    {
+      "epoch": 0.2754008065309334,
+      "grad_norm": 0.06251444667577744,
+      "learning_rate": 0.00019084196573814047,
+      "loss": 0.6856,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2852365496213239,
+      "grad_norm": 0.07899219542741776,
+      "learning_rate": 0.00019018485569319003,
+      "loss": 0.6753,
+      "step": 1450
+    },
+    {
+      "epoch": 0.29507229271171437,
+      "grad_norm": 0.07931499183177948,
+      "learning_rate": 0.00018950619343789934,
+      "loss": 0.6808,
+      "step": 1500
+    },
+    {
+      "epoch": 0.30490803580210485,
+      "grad_norm": 0.061664845794439316,
+      "learning_rate": 0.00018880614115772138,
+      "loss": 0.6797,
+      "step": 1550
+    },
+    {
+      "epoch": 0.31474377889249533,
+      "grad_norm": 0.0717281773686409,
+      "learning_rate": 0.00018808486614985782,
+      "loss": 0.6774,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3245795219828858,
+      "grad_norm": 0.07137037068605423,
+      "learning_rate": 0.00018734254078327868,
+      "loss": 0.6787,
+      "step": 1650
+    },
+    {
+      "epoch": 0.3344152650732763,
+      "grad_norm": 0.07462574541568756,
+      "learning_rate": 0.0001865793424575298,
+      "loss": 0.6836,
+      "step": 1700
+    },
+    {
+      "epoch": 0.34425100816366677,
+      "grad_norm": 0.06719885766506195,
+      "learning_rate": 0.00018579545356033823,
+      "loss": 0.6737,
+      "step": 1750
+    },
+    {
+      "epoch": 0.35408675125405725,
+      "grad_norm": 0.06752898544073105,
+      "learning_rate": 0.00018499106142402563,
+      "loss": 0.6767,
+      "step": 1800
+    },
+    {
+      "epoch": 0.36392249434444773,
+      "grad_norm": 0.072923943400383,
+      "learning_rate": 0.00018416635828073994,
+      "loss": 0.6756,
+      "step": 1850
+    },
+    {
+      "epoch": 0.3737582374348382,
+      "grad_norm": 0.07471544295549393,
+      "learning_rate": 0.00018332154121651598,
+      "loss": 0.675,
+      "step": 1900
+    },
+    {
+      "epoch": 0.3835939805252287,
+      "grad_norm": 0.0654042437672615,
+      "learning_rate": 0.00018245681212417631,
+      "loss": 0.6662,
+      "step": 1950
+    },
+    {
+      "epoch": 0.3934297236156192,
+      "grad_norm": 0.07551202178001404,
+      "learning_rate": 0.00018157237765508325,
+      "loss": 0.6635,
+      "step": 2000
+    },
+    {
+      "epoch": 0.40326546670600966,
+      "grad_norm": 0.07835708558559418,
+      "learning_rate": 0.00018066844916975354,
+      "loss": 0.6701,
+      "step": 2050
+    },
+    {
+      "epoch": 0.41310120979640014,
+      "grad_norm": 0.06583021581172943,
+      "learning_rate": 0.0001797452426873481,
+      "loss": 0.6644,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4229369528867906,
+      "grad_norm": 0.07056088745594025,
+      "learning_rate": 0.0001788029788340479,
+      "loss": 0.6696,
+      "step": 2150
+    },
+    {
+      "epoch": 0.4327726959771811,
+      "grad_norm": 0.061976175755262375,
+      "learning_rate": 0.00017784188279032932,
+      "loss": 0.6641,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4426084390675716,
+      "grad_norm": 0.06996449083089828,
+      "learning_rate": 0.00017686218423715072,
+      "loss": 0.6666,
+      "step": 2250
+    },
+    {
+      "epoch": 0.45244418215796206,
+      "grad_norm": 0.07750783860683441,
+      "learning_rate": 0.00017586411730106399,
+      "loss": 0.6608,
+      "step": 2300
+    },
+    {
+      "epoch": 0.4622799252483525,
+      "grad_norm": 0.06929858028888702,
+      "learning_rate": 0.00017484792049826306,
+      "loss": 0.6693,
+      "step": 2350
+    },
+    {
+      "epoch": 0.47211566833874297,
+      "grad_norm": 0.07935669273138046,
+      "learning_rate": 0.00017381383667758416,
+      "loss": 0.6709,
+      "step": 2400
+    },
+    {
+      "epoch": 0.48195141142913345,
+      "grad_norm": 0.06911829113960266,
+      "learning_rate": 0.00017276211296246986,
+      "loss": 0.6592,
+      "step": 2450
+    },
+    {
+      "epoch": 0.49178715451952393,
+      "grad_norm": 0.06784563511610031,
+      "learning_rate": 0.00017169300069191224,
+      "loss": 0.6631,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5016228976099144,
+      "grad_norm": 0.06838862597942352,
+      "learning_rate": 0.00017060675536038818,
+      "loss": 0.6685,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5114586407003049,
+      "grad_norm": 0.07473283261060715,
+      "learning_rate": 0.000169503636556802,
+      "loss": 0.6579,
+      "step": 2600
+    },
+    {
+      "epoch": 0.5212943837906954,
+      "grad_norm": 0.07981903851032257,
+      "learning_rate": 0.000168383907902449,
+      "loss": 0.6531,
+      "step": 2650
+    },
+    {
+      "epoch": 0.5311301268810859,
+      "grad_norm": 0.07383566349744797,
+      "learning_rate": 0.00016724783698801615,
+      "loss": 0.6552,
+      "step": 2700
+    },
+    {
+      "epoch": 0.5409658699714763,
+      "grad_norm": 0.075548455119133,
+      "learning_rate": 0.00016609569530963352,
+      "loss": 0.665,
+      "step": 2750
+    },
+    {
+      "epoch": 0.5508016130618668,
+      "grad_norm": 0.0663590133190155,
+      "learning_rate": 0.00016492775820399258,
+      "loss": 0.663,
+      "step": 2800
+    },
+    {
+      "epoch": 0.5606373561522573,
+      "grad_norm": 0.07384879887104034,
+      "learning_rate": 0.00016374430478254697,
+      "loss": 0.656,
+      "step": 2850
+    },
+    {
+      "epoch": 0.5704730992426478,
+      "grad_norm": 0.06946936994791031,
+      "learning_rate": 0.00016254561786481077,
+      "loss": 0.6585,
+      "step": 2900
+    },
+    {
+      "epoch": 0.5803088423330383,
+      "grad_norm": 0.06723761558532715,
+      "learning_rate": 0.00016133198391077096,
+      "loss": 0.6563,
+      "step": 2950
+    },
+    {
+      "epoch": 0.5901445854234287,
+      "grad_norm": 0.06926653534173965,
+      "learning_rate": 0.00016010369295242955,
+      "loss": 0.6542,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5999803285138192,
+      "grad_norm": 0.07461749017238617,
+      "learning_rate": 0.00015886103852449254,
+      "loss": 0.6618,
+      "step": 3050
+    },
+    {
+      "epoch": 0.6098160716042097,
+      "grad_norm": 0.07314767688512802,
+      "learning_rate": 0.00015760431759422118,
+      "loss": 0.6509,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6196518146946002,
+      "grad_norm": 0.07121975719928741,
+      "learning_rate": 0.00015633383049046365,
+      "loss": 0.6574,
+      "step": 3150
+    },
+    {
+      "epoch": 0.6294875577849907,
+      "grad_norm": 0.08515851944684982,
+      "learning_rate": 0.00015504988083188281,
+      "loss": 0.6576,
+      "step": 3200
+    },
+    {
+      "epoch": 0.6393233008753811,
+      "grad_norm": 0.07423117756843567,
+      "learning_rate": 0.000153752775454398,
+      "loss": 0.6512,
+      "step": 3250
+    },
+    {
+      "epoch": 0.6491590439657716,
+      "grad_norm": 0.06631764024496078,
+      "learning_rate": 0.00015244282433785796,
+      "loss": 0.6552,
+      "step": 3300
+    },
+    {
+      "epoch": 0.6589947870561621,
+      "grad_norm": 0.06597639620304108,
+      "learning_rate": 0.00015112034053196247,
+      "loss": 0.6572,
+      "step": 3350
+    },
+    {
+      "epoch": 0.6688305301465526,
+      "grad_norm": 0.07060743868350983,
+      "learning_rate": 0.00014978564008145032,
+      "loss": 0.6468,
+      "step": 3400
+    },
+    {
+      "epoch": 0.6786662732369431,
+      "grad_norm": 0.07211815565824509,
+      "learning_rate": 0.00014843904195057137,
+      "loss": 0.6476,
+      "step": 3450
+    },
+    {
+      "epoch": 0.6885020163273335,
+      "grad_norm": 0.0679902508854866,
+      "learning_rate": 0.00014708086794686128,
+      "loss": 0.6516,
+      "step": 3500
+    },
+    {
+      "epoch": 0.698337759417724,
+      "grad_norm": 0.06677327305078506,
+      "learning_rate": 0.00014571144264423642,
+      "loss": 0.654,
+      "step": 3550
+    },
+    {
+      "epoch": 0.7081735025081145,
+      "grad_norm": 0.07432771474123001,
+      "learning_rate": 0.00014433109330542769,
+      "loss": 0.6484,
+      "step": 3600
+    },
+    {
+      "epoch": 0.718009245598505,
+      "grad_norm": 0.07363554835319519,
+      "learning_rate": 0.00014294014980377213,
+      "loss": 0.6477,
+      "step": 3650
+    },
+    {
+      "epoch": 0.7278449886888955,
+      "grad_norm": 0.07398252189159393,
+      "learning_rate": 0.00014153894454438018,
+      "loss": 0.6494,
+      "step": 3700
+    },
+    {
+      "epoch": 0.737680731779286,
+      "grad_norm": 0.06380564719438553,
+      "learning_rate": 0.00014012781238469823,
+      "loss": 0.6511,
+      "step": 3750
+    },
+    {
+      "epoch": 0.7475164748696764,
+      "grad_norm": 0.06673400104045868,
+      "learning_rate": 0.00013870709055448504,
+      "loss": 0.649,
+      "step": 3800
+    },
+    {
+      "epoch": 0.7573522179600669,
+      "grad_norm": 0.07433997839689255,
+      "learning_rate": 0.00013727711857522095,
+      "loss": 0.642,
+      "step": 3850
+    },
+    {
+      "epoch": 0.7671879610504574,
+      "grad_norm": 0.07073818892240524,
+      "learning_rate": 0.00013583823817897006,
+      "loss": 0.6371,
+      "step": 3900
+    },
+    {
+      "epoch": 0.7770237041408479,
+      "grad_norm": 0.06574368476867676,
+      "learning_rate": 0.0001343907932267134,
+      "loss": 0.6493,
+      "step": 3950
+    },
+    {
+      "epoch": 0.7868594472312384,
+      "grad_norm": 0.067158043384552,
+      "learning_rate": 0.00013293512962617377,
+      "loss": 0.6433,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7966951903216288,
+      "grad_norm": 0.07653222978115082,
+      "learning_rate": 0.0001314715952491514,
+      "loss": 0.6457,
+      "step": 4050
+    },
+    {
+      "epoch": 0.8065309334120193,
+      "grad_norm": 0.07320449501276016,
+      "learning_rate": 0.0001300005398483902,
+      "loss": 0.642,
+      "step": 4100
+    },
+    {
+      "epoch": 0.8163666765024098,
+      "grad_norm": 0.07599062472581863,
+      "learning_rate": 0.0001285223149739944,
+      "loss": 0.6444,
+      "step": 4150
+    },
+    {
+      "epoch": 0.8262024195928003,
+      "grad_norm": 0.07315944135189056,
+      "learning_rate": 0.00012703727388941577,
+      "loss": 0.646,
+      "step": 4200
+    },
+    {
+      "epoch": 0.8360381626831908,
+      "grad_norm": 0.0766439437866211,
+      "learning_rate": 0.00012554577148703148,
+      "loss": 0.6391,
+      "step": 4250
+    },
+    {
+      "epoch": 0.8458739057735812,
+      "grad_norm": 0.07688874751329422,
+      "learning_rate": 0.00012404816420333247,
+      "loss": 0.6423,
+      "step": 4300
+    },
+    {
+      "epoch": 0.8557096488639717,
+      "grad_norm": 0.07058276981115341,
+      "learning_rate": 0.0001225448099337429,
+      "loss": 0.6473,
+      "step": 4350
+    },
+    {
+      "epoch": 0.8655453919543622,
+      "grad_norm": 0.07005015760660172,
+      "learning_rate": 0.00012103606794709112,
+      "loss": 0.638,
+      "step": 4400
+    },
+    {
+      "epoch": 0.8753811350447527,
+      "grad_norm": 0.06887346506118774,
+      "learning_rate": 0.00011952229879975207,
+      "loss": 0.6428,
+      "step": 4450
+    },
+    {
+      "epoch": 0.8852168781351432,
+      "grad_norm": 0.06948423385620117,
+      "learning_rate": 0.00011800386424948227,
+      "loss": 0.6413,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8950526212255336,
+      "grad_norm": 0.08220444619655609,
+      "learning_rate": 0.00011648112716896771,
+      "loss": 0.6413,
+      "step": 4550
+    },
+    {
+      "epoch": 0.9048883643159241,
+      "grad_norm": 0.07942084223031998,
+      "learning_rate": 0.000114954451459105,
+      "loss": 0.642,
+      "step": 4600
+    },
+    {
+      "epoch": 0.9147241074063146,
+      "grad_norm": 0.074773870408535,
+      "learning_rate": 0.00011342420196203719,
+      "loss": 0.64,
+      "step": 4650
+    },
+    {
+      "epoch": 0.924559850496705,
+      "grad_norm": 0.06527584791183472,
+      "learning_rate": 0.00011189074437396438,
+      "loss": 0.6448,
+      "step": 4700
+    },
+    {
+      "epoch": 0.9343955935870955,
+      "grad_norm": 0.0640060305595398,
+      "learning_rate": 0.00011035444515775035,
+      "loss": 0.6381,
+      "step": 4750
+    },
+    {
+      "epoch": 0.9442313366774859,
+      "grad_norm": 0.06932298839092255,
+      "learning_rate": 0.00010881567145534591,
+      "loss": 0.6424,
+      "step": 4800
+    },
+    {
+      "epoch": 0.9540670797678764,
+      "grad_norm": 0.0729447677731514,
+      "learning_rate": 0.00010727479100005005,
+      "loss": 0.6398,
+      "step": 4850
+    },
+    {
+      "epoch": 0.9639028228582669,
+      "grad_norm": 0.06698109209537506,
+      "learning_rate": 0.00010573217202862959,
+      "loss": 0.64,
+      "step": 4900
+    },
+    {
+      "epoch": 0.9737385659486574,
+      "grad_norm": 0.0725114643573761,
+      "learning_rate": 0.0001041881831933188,
+      "loss": 0.6389,
+      "step": 4950
+    },
+    {
+      "epoch": 0.9835743090390479,
+      "grad_norm": 0.06850885599851608,
+      "learning_rate": 0.00010264319347371951,
+      "loss": 0.6341,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9934100521294383,
+      "grad_norm": 0.07343582063913345,
+      "learning_rate": 0.00010109757208862299,
+      "loss": 0.6315,
+      "step": 5050
+    },
+    {
+      "epoch": 1.003147437788925,
+      "grad_norm": 0.07858431339263916,
+      "learning_rate": 9.955168840777474e-05,
+      "loss": 0.6336,
+      "step": 5100
+    },
+    {
+      "epoch": 1.0129831808793155,
+      "grad_norm": 0.07285405695438385,
+      "learning_rate": 9.800591186360323e-05,
+      "loss": 0.6202,
+      "step": 5150
+    },
+    {
+      "epoch": 1.0228189239697059,
+      "grad_norm": 0.07421938329935074,
+      "learning_rate": 9.646061186293367e-05,
+      "loss": 0.6256,
+      "step": 5200
+    },
+    {
+      "epoch": 1.0326546670600965,
+      "grad_norm": 0.06922327727079391,
+      "learning_rate": 9.491615769870769e-05,
+      "loss": 0.6214,
+      "step": 5250
+    },
+    {
+      "epoch": 1.0424904101504868,
+      "grad_norm": 0.08220986276865005,
+      "learning_rate": 9.337291846173059e-05,
+      "loss": 0.6272,
+      "step": 5300
+    },
+    {
+      "epoch": 1.0523261532408774,
+      "grad_norm": 0.06896129250526428,
+      "learning_rate": 9.183126295246645e-05,
+      "loss": 0.6219,
+      "step": 5350
+    },
+    {
+      "epoch": 1.0621618963312678,
+      "grad_norm": 0.07372142374515533,
+      "learning_rate": 9.029155959290319e-05,
+      "loss": 0.6171,
+      "step": 5400
+    },
+    {
+      "epoch": 1.0719976394216584,
+      "grad_norm": 0.07114165276288986,
+      "learning_rate": 8.875417633850746e-05,
+      "loss": 0.6189,
+      "step": 5450
+    },
+    {
+      "epoch": 1.0818333825120487,
+      "grad_norm": 0.0711623951792717,
+      "learning_rate": 8.721948059029161e-05,
+      "loss": 0.6167,
+      "step": 5500
+    },
+    {
+      "epoch": 1.0916691256024393,
+      "grad_norm": 0.07456561177968979,
+      "learning_rate": 8.568783910701252e-05,
+      "loss": 0.6141,
+      "step": 5550
+    },
+    {
+      "epoch": 1.1015048686928297,
+      "grad_norm": 0.0760912150144577,
+      "learning_rate": 8.415961791752472e-05,
+      "loss": 0.6167,
+      "step": 5600
+    },
+    {
+      "epoch": 1.1113406117832203,
+      "grad_norm": 0.07034651935100555,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.6125,
+      "step": 5650
+    },
+    {
+      "epoch": 1.1211763548736107,
+      "grad_norm": 0.07252858579158783,
+      "learning_rate": 8.111489636118522e-05,
+      "loss": 0.6181,
+      "step": 5700
+    },
+    {
+      "epoch": 1.1310120979640013,
+      "grad_norm": 0.07909699529409409,
+      "learning_rate": 7.959912361627082e-05,
+      "loss": 0.6214,
+      "step": 5750
+    },
+    {
+      "epoch": 1.1408478410543916,
+      "grad_norm": 0.07374490797519684,
+      "learning_rate": 7.808822623513643e-05,
+      "loss": 0.625,
+      "step": 5800
+    },
+    {
+      "epoch": 1.1506835841447822,
+      "grad_norm": 0.07597927004098892,
+      "learning_rate": 7.658256528924909e-05,
+      "loss": 0.6199,
+      "step": 5850
+    },
+    {
+      "epoch": 1.1605193272351726,
+      "grad_norm": 0.07946628332138062,
+      "learning_rate": 7.508250059868249e-05,
+      "loss": 0.615,
+      "step": 5900
+    },
+    {
+      "epoch": 1.1703550703255632,
+      "grad_norm": 0.07706974446773529,
+      "learning_rate": 7.358839064612726e-05,
+      "loss": 0.6126,
+      "step": 5950
+    },
+    {
+      "epoch": 1.1801908134159536,
+      "grad_norm": 0.0789932906627655,
+      "learning_rate": 7.210059249122193e-05,
+      "loss": 0.6192,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1900265565063441,
+      "grad_norm": 0.08002398908138275,
+      "learning_rate": 7.061946168522318e-05,
+      "loss": 0.6167,
+      "step": 6050
+    },
+    {
+      "epoch": 1.1998622995967345,
+      "grad_norm": 0.07844787836074829,
+      "learning_rate": 6.914535218603708e-05,
+      "loss": 0.6208,
+      "step": 6100
+    },
+    {
+      "epoch": 1.209698042687125,
+      "grad_norm": 0.08679769188165665,
+      "learning_rate": 6.767861627363054e-05,
+      "loss": 0.6157,
+      "step": 6150
+    },
+    {
+      "epoch": 1.2195337857775155,
+      "grad_norm": 0.07716654241085052,
+      "learning_rate": 6.621960446584452e-05,
+      "loss": 0.61,
+      "step": 6200
+    },
+    {
+      "epoch": 1.229369528867906,
+      "grad_norm": 0.08282492309808731,
+      "learning_rate": 6.476866543462761e-05,
+      "loss": 0.6145,
+      "step": 6250
+    },
+    {
+      "epoch": 1.2392052719582964,
+      "grad_norm": 0.09066256135702133,
+      "learning_rate": 6.332614592271122e-05,
+      "loss": 0.6237,
+      "step": 6300
+    },
+    {
+      "epoch": 1.2490410150486868,
+      "grad_norm": 0.07888253778219223,
+      "learning_rate": 6.18923906607455e-05,
+      "loss": 0.6149,
+      "step": 6350
+    },
+    {
+      "epoch": 1.2588767581390774,
+      "grad_norm": 0.08149804919958115,
+      "learning_rate": 6.046774228491643e-05,
+      "loss": 0.6166,
+      "step": 6400
+    },
+    {
+      "epoch": 1.268712501229468,
+      "grad_norm": 0.07619079202413559,
+      "learning_rate": 5.905254125506301e-05,
+      "loss": 0.6111,
+      "step": 6450
+    },
+    {
+      "epoch": 1.2785482443198584,
+      "grad_norm": 0.08567807078361511,
+      "learning_rate": 5.76471257733151e-05,
+      "loss": 0.6153,
+      "step": 6500
+    },
+    {
+      "epoch": 1.2883839874102487,
+      "grad_norm": 0.0711495652794838,
+      "learning_rate": 5.625183170327017e-05,
+      "loss": 0.6126,
+      "step": 6550
+    },
+    {
+      "epoch": 1.2982197305006393,
+      "grad_norm": 0.08142837882041931,
+      "learning_rate": 5.4866992489729554e-05,
+      "loss": 0.6212,
+      "step": 6600
+    },
+    {
+      "epoch": 1.30805547359103,
+      "grad_norm": 0.07909776270389557,
+      "learning_rate": 5.3492939079012206e-05,
+      "loss": 0.6139,
+      "step": 6650
+    },
+    {
+      "epoch": 1.3178912166814203,
+      "grad_norm": 0.08278420567512512,
+      "learning_rate": 5.2129999839865796e-05,
+      "loss": 0.6115,
+      "step": 6700
+    },
+    {
+      "epoch": 1.3277269597718107,
+      "grad_norm": 0.08086064457893372,
+      "learning_rate": 5.077850048499388e-05,
+      "loss": 0.6111,
+      "step": 6750
+    },
+    {
+      "epoch": 1.3375627028622012,
+      "grad_norm": 0.07711977511644363,
+      "learning_rate": 4.9438763993217495e-05,
+      "loss": 0.6101,
+      "step": 6800
+    },
+    {
+      "epoch": 1.3473984459525918,
+      "grad_norm": 0.08161487430334091,
+      "learning_rate": 4.811111053229043e-05,
+      "loss": 0.6167,
+      "step": 6850
+    },
+    {
+      "epoch": 1.3572341890429822,
+      "grad_norm": 0.0841764435172081,
+      "learning_rate": 4.6795857382386044e-05,
+      "loss": 0.6121,
+      "step": 6900
+    },
+    {
+      "epoch": 1.3670699321333726,
+      "grad_norm": 0.0816132128238678,
+      "learning_rate": 4.549331886027429e-05,
+      "loss": 0.6078,
+      "step": 6950
+    },
+    {
+      "epoch": 1.3769056752237632,
+      "grad_norm": 0.08330381661653519,
+      "learning_rate": 4.4203806244206756e-05,
+      "loss": 0.6195,
+      "step": 7000
+    },
+    {
+      "epoch": 1.3867414183141538,
+      "grad_norm": 0.0845024362206459,
+      "learning_rate": 4.292762769952816e-05,
+      "loss": 0.6133,
+      "step": 7050
+    },
+    {
+      "epoch": 1.3965771614045441,
+      "grad_norm": 0.07662446796894073,
+      "learning_rate": 4.1665088205031334e-05,
+      "loss": 0.6129,
+      "step": 7100
+    },
+    {
+      "epoch": 1.4064129044949345,
+      "grad_norm": 0.08240839838981628,
+      "learning_rate": 4.041648948007416e-05,
+      "loss": 0.6156,
+      "step": 7150
+    },
+    {
+      "epoch": 1.416248647585325,
+      "grad_norm": 0.07303918898105621,
+      "learning_rate": 3.918212991247514e-05,
+      "loss": 0.6156,
+      "step": 7200
+    },
+    {
+      "epoch": 1.4260843906757157,
+      "grad_norm": 0.07239814847707748,
+      "learning_rate": 3.796230448720526e-05,
+      "loss": 0.6131,
+      "step": 7250
+    },
+    {
+      "epoch": 1.435920133766106,
+      "grad_norm": 0.07538265734910965,
+      "learning_rate": 3.675730471589286e-05,
+      "loss": 0.6116,
+      "step": 7300
+    },
+    {
+      "epoch": 1.4457558768564964,
+      "grad_norm": 0.08947084844112396,
+      "learning_rate": 3.556741856715907e-05,
+      "loss": 0.6147,
+      "step": 7350
+    },
+    {
+      "epoch": 1.455591619946887,
+      "grad_norm": 0.08240395039319992,
+      "learning_rate": 3.4392930397799194e-05,
+      "loss": 0.6125,
+      "step": 7400
+    },
+    {
+      "epoch": 1.4654273630372774,
+      "grad_norm": 0.07328338176012039,
+      "learning_rate": 3.3234120884828e-05,
+      "loss": 0.6041,
+      "step": 7450
+    },
+    {
+      "epoch": 1.475263106127668,
+      "grad_norm": 0.07761271297931671,
+      "learning_rate": 3.209126695840382e-05,
+      "loss": 0.6116,
+      "step": 7500
+    },
+    {
+      "epoch": 1.4850988492180583,
+      "grad_norm": 0.084846630692482,
+      "learning_rate": 3.0964641735648423e-05,
+      "loss": 0.6141,
+      "step": 7550
+    },
+    {
+      "epoch": 1.494934592308449,
+      "grad_norm": 0.08141667395830154,
+      "learning_rate": 2.9854514455377837e-05,
+      "loss": 0.6073,
+      "step": 7600
+    },
+    {
+      "epoch": 1.5047703353988395,
+      "grad_norm": 0.07505550980567932,
+      "learning_rate": 2.876115041376034e-05,
+      "loss": 0.6091,
+      "step": 7650
+    },
+    {
+      "epoch": 1.51460607848923,
+      "grad_norm": 0.07819739729166031,
+      "learning_rate": 2.7684810900916315e-05,
+      "loss": 0.6141,
+      "step": 7700
+    },
+    {
+      "epoch": 1.5244418215796203,
+      "grad_norm": 0.07576938718557358,
+      "learning_rate": 2.6625753138475718e-05,
+      "loss": 0.6046,
+      "step": 7750
+    },
+    {
+      "epoch": 1.5342775646700109,
+      "grad_norm": 0.07528570294380188,
+      "learning_rate": 2.5584230218107718e-05,
+      "loss": 0.6114,
+      "step": 7800
+    },
+    {
+      "epoch": 1.5441133077604015,
+      "grad_norm": 0.08330899477005005,
+      "learning_rate": 2.456049104103726e-05,
+      "loss": 0.609,
+      "step": 7850
+    },
+    {
+      "epoch": 1.5539490508507918,
+      "grad_norm": 0.0729718878865242,
+      "learning_rate": 2.3554780258563125e-05,
+      "loss": 0.6138,
+      "step": 7900
+    },
+    {
+      "epoch": 1.5637847939411822,
+      "grad_norm": 0.07709172368049622,
+      "learning_rate": 2.256733821359168e-05,
+      "loss": 0.6038,
+      "step": 7950
+    },
+    {
+      "epoch": 1.5736205370315728,
+      "grad_norm": 0.07105692476034164,
+      "learning_rate": 2.1598400883200065e-05,
+      "loss": 0.6078,
+      "step": 8000
+    },
+    {
+      "epoch": 1.5834562801219634,
+      "grad_norm": 0.0719430074095726,
+      "learning_rate": 2.0648199822242953e-05,
+      "loss": 0.6121,
+      "step": 8050
+    },
+    {
+      "epoch": 1.5932920232123537,
+      "grad_norm": 0.08640766143798828,
+      "learning_rate": 1.971696210801589e-05,
+      "loss": 0.5973,
+      "step": 8100
+    },
+    {
+      "epoch": 1.6031277663027441,
+      "grad_norm": 0.07854746282100677,
+      "learning_rate": 1.8804910285988885e-05,
+      "loss": 0.6176,
+      "step": 8150
+    },
+    {
+      "epoch": 1.6129635093931345,
+      "grad_norm": 0.09165063500404358,
+      "learning_rate": 1.7912262316622753e-05,
+      "loss": 0.6112,
+      "step": 8200
+    },
+    {
+      "epoch": 1.622799252483525,
+      "grad_norm": 0.07630006968975067,
+      "learning_rate": 1.703923152328145e-05,
+      "loss": 0.6053,
+      "step": 8250
+    },
+    {
+      "epoch": 1.6326349955739157,
+      "grad_norm": 0.0875934585928917,
+      "learning_rate": 1.6186026541252452e-05,
+      "loss": 0.6082,
+      "step": 8300
+    },
+    {
+      "epoch": 1.642470738664306,
+      "grad_norm": 0.08449984341859818,
+      "learning_rate": 1.5352851267887423e-05,
+      "loss": 0.6139,
+      "step": 8350
+    },
+    {
+      "epoch": 1.6523064817546964,
+      "grad_norm": 0.07857895642518997,
+      "learning_rate": 1.453990481387526e-05,
+      "loss": 0.6134,
+      "step": 8400
+    },
+    {
+      "epoch": 1.662142224845087,
+      "grad_norm": 0.0947275385260582,
+      "learning_rate": 1.3747381455658848e-05,
+      "loss": 0.6018,
+      "step": 8450
+    },
+    {
+      "epoch": 1.6719779679354776,
+      "grad_norm": 0.08134233206510544,
+      "learning_rate": 1.2975470589007454e-05,
+      "loss": 0.6127,
+      "step": 8500
+    },
+    {
+      "epoch": 1.681813711025868,
+      "grad_norm": 0.07631494104862213,
+      "learning_rate": 1.2224356683755089e-05,
+      "loss": 0.6105,
+      "step": 8550
+    },
+    {
+      "epoch": 1.6916494541162583,
+      "grad_norm": 0.07870069146156311,
+      "learning_rate": 1.1494219239716353e-05,
+      "loss": 0.6076,
+      "step": 8600
+    },
+    {
+      "epoch": 1.701485197206649,
+      "grad_norm": 0.08626607805490494,
+      "learning_rate": 1.0785232743789808e-05,
+      "loss": 0.6102,
+      "step": 8650
+    },
+    {
+      "epoch": 1.7113209402970395,
+      "grad_norm": 0.08474079519510269,
+      "learning_rate": 1.0097566628259614e-05,
+      "loss": 0.6018,
+      "step": 8700
+    },
+    {
+      "epoch": 1.7211566833874299,
+      "grad_norm": 0.08202967047691345,
+      "learning_rate": 9.431385230304613e-06,
+      "loss": 0.6016,
+      "step": 8750
+    },
+    {
+      "epoch": 1.7309924264778203,
+      "grad_norm": 0.07875273376703262,
+      "learning_rate": 8.786847752725614e-06,
+      "loss": 0.616,
+      "step": 8800
+    },
+    {
+      "epoch": 1.7408281695682108,
+      "grad_norm": 0.09360364079475403,
+      "learning_rate": 8.164108225899214e-06,
+      "loss": 0.6046,
+      "step": 8850
+    },
+    {
+      "epoch": 1.7506639126586014,
+      "grad_norm": 0.07391002029180527,
+      "learning_rate": 7.5633154709680575e-06,
+      "loss": 0.6117,
+      "step": 8900
+    },
+    {
+      "epoch": 1.7604996557489918,
+      "grad_norm": 0.06737073510885239,
+      "learning_rate": 6.984613064275658e-06,
+      "loss": 0.6034,
+      "step": 8950
+    },
+    {
+      "epoch": 1.7703353988393822,
+      "grad_norm": 0.0800662711262703,
+      "learning_rate": 6.428139303054981e-06,
+      "loss": 0.6054,
+      "step": 9000
+    },
+    {
+      "epoch": 1.7801711419297728,
+      "grad_norm": 0.07634767144918442,
+      "learning_rate": 5.894027172378247e-06,
+      "loss": 0.6041,
+      "step": 9050
+    },
+    {
+      "epoch": 1.7900068850201634,
+      "grad_norm": 0.0848456546664238,
+      "learning_rate": 5.382404313376555e-06,
+      "loss": 0.6013,
+      "step": 9100
+    },
+    {
+      "epoch": 1.7998426281105537,
+      "grad_norm": 0.08109795302152634,
+      "learning_rate": 4.893392992736301e-06,
+      "loss": 0.6037,
+      "step": 9150
+    },
+    {
+      "epoch": 1.809678371200944,
+      "grad_norm": 0.08365663886070251,
+      "learning_rate": 4.427110073480245e-06,
+      "loss": 0.604,
+      "step": 9200
+    },
+    {
+      "epoch": 1.8195141142913347,
+      "grad_norm": 0.07841967046260834,
+      "learning_rate": 3.983666987039691e-06,
+      "loss": 0.602,
+      "step": 9250
+    },
+    {
+      "epoch": 1.8293498573817253,
+      "grad_norm": 0.07770159840583801,
+      "learning_rate": 3.5631697066249024e-06,
+      "loss": 0.6051,
+      "step": 9300
+    },
+    {
+      "epoch": 1.8391856004721157,
+      "grad_norm": 0.07518593221902847,
+      "learning_rate": 3.1657187218997464e-06,
+      "loss": 0.6065,
+      "step": 9350
+    },
+    {
+      "epoch": 1.849021343562506,
+      "grad_norm": 0.08144789189100266,
+      "learning_rate": 2.791409014966895e-06,
+      "loss": 0.6096,
+      "step": 9400
+    },
+    {
+      "epoch": 1.8588570866528966,
+      "grad_norm": 0.08269818127155304,
+      "learning_rate": 2.4403300376691473e-06,
+      "loss": 0.61,
+      "step": 9450
+    },
+    {
+      "epoch": 1.8686928297432872,
+      "grad_norm": 0.07822602987289429,
+      "learning_rate": 2.112565690212465e-06,
+      "loss": 0.6063,
+      "step": 9500
+    },
+    {
+      "epoch": 1.8785285728336776,
+      "grad_norm": 0.09586796164512634,
+      "learning_rate": 1.8081943011155623e-06,
+      "loss": 0.6025,
+      "step": 9550
+    },
+    {
+      "epoch": 1.888364315924068,
+      "grad_norm": 0.0846213847398758,
+      "learning_rate": 1.527288608491173e-06,
+      "loss": 0.6098,
+      "step": 9600
+    },
+    {
+      "epoch": 1.8982000590144585,
+      "grad_norm": 0.08927745372056961,
+      "learning_rate": 1.2699157426631858e-06,
+      "loss": 0.6077,
+      "step": 9650
+    },
+    {
+      "epoch": 1.9080358021048491,
+      "grad_norm": 0.07482849806547165,
+      "learning_rate": 1.0361372101239997e-06,
+      "loss": 0.6045,
+      "step": 9700
+    },
+    {
+      "epoch": 1.9178715451952395,
+      "grad_norm": 0.07779071480035782,
+      "learning_rate": 8.260088788357711e-07,
+      "loss": 0.6068,
+      "step": 9750
+    },
+    {
+      "epoch": 1.9277072882856299,
+      "grad_norm": 0.079287588596344,
+      "learning_rate": 6.395809648792384e-07,
+      "loss": 0.6053,
+      "step": 9800
+    },
+    {
+      "epoch": 1.9375430313760205,
+      "grad_norm": 0.08390713483095169,
+      "learning_rate": 4.768980204531426e-07,
+      "loss": 0.6083,
+      "step": 9850
+    },
+    {
+      "epoch": 1.947378774466411,
+      "grad_norm": 0.07710904628038406,
+      "learning_rate": 3.3799892322726735e-07,
+      "loss": 0.6058,
+      "step": 9900
+    },
+    {
+      "epoch": 1.9572145175568014,
+      "grad_norm": 0.08125531673431396,
+      "learning_rate": 2.229168670514481e-07,
+      "loss": 0.6087,
+      "step": 9950
+    },
+    {
+      "epoch": 1.9670502606471918,
+      "grad_norm": 0.07178232818841934,
+      "learning_rate": 1.3167935402305098e-07,
+      "loss": 0.6064,
+      "step": 10000
+    },
+    {
+      "epoch": 1.9768860037375824,
+      "grad_norm": 0.08764079213142395,
+      "learning_rate": 6.430818791451909e-08,
+      "loss": 0.6119,
+      "step": 10050
+    },
+    {
+      "epoch": 1.986721746827973,
+      "grad_norm": 0.07766247540712357,
+      "learning_rate": 2.0819468962773868e-08,
+      "loss": 0.6038,
+      "step": 10100
+    },
+    {
+      "epoch": 1.9965574899183633,
+      "grad_norm": 0.08261710405349731,
+      "learning_rate": 1.2235900215817885e-09,
+      "loss": 0.6115,
+      "step": 10150
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 10166,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.464591551750786e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319d9f92aa4df7f8ce8c41e99b3e60ecd86f3018a094d6c3a22d4ae2400177f1
+size 5905