Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Rombo-Org/Rombo-LLM-V3.0-Qwen-32b
+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 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Rombo-Org/Rombo-LLM-V3.0-Qwen-32b",
+  "bias": "none",
+  "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",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:167fa6ef8344123ecc694386954edbeab4ddfd4d57ecd8fd91136da2051d4750
+size 536991984

added_tokens.json

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

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa23ac6f1ab79d9f1e46a7f3f4ecdaa17bb13a004c14fb47b7517f4ed9d460f2
+size 269968157

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8187b77168ad6d78ab12ecfc220ea78df172fa7fb8363dd89f59a31f531e5cf0
+size 14443

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7463d7c81e4b7e0d0fdef9fbf007e2a5121678ca6fc9042ca21969578218213
+size 1263

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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1273 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.864,
+  "eval_steps": 500,
+  "global_step": 155,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 0.1512966901063919,
+      "learning_rate": 1.25e-07,
+      "loss": 1.3529,
+      "mean_token_accuracy": 0.6367230899631977,
+      "step": 1
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.1354781985282898,
+      "learning_rate": 2.5e-07,
+      "loss": 1.2691,
+      "mean_token_accuracy": 0.6164033822715282,
+      "step": 2
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.12998351454734802,
+      "learning_rate": 3.75e-07,
+      "loss": 1.2648,
+      "mean_token_accuracy": 0.6137149464339018,
+      "step": 3
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.14289270341396332,
+      "learning_rate": 5e-07,
+      "loss": 1.2474,
+      "mean_token_accuracy": 0.5892269946634769,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.16390180587768555,
+      "learning_rate": 6.249999999999999e-07,
+      "loss": 1.4205,
+      "mean_token_accuracy": 0.6229604724794626,
+      "step": 5
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 0.16394473612308502,
+      "learning_rate": 7.5e-07,
+      "loss": 1.4764,
+      "mean_token_accuracy": 0.6162877101451159,
+      "step": 6
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.14390598237514496,
+      "learning_rate": 8.75e-07,
+      "loss": 1.3535,
+      "mean_token_accuracy": 0.6579387821257114,
+      "step": 7
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.13060295581817627,
+      "learning_rate": 1e-06,
+      "loss": 1.3479,
+      "mean_token_accuracy": 0.5690887439996004,
+      "step": 8
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.1393515020608902,
+      "learning_rate": 9.99885820390154e-07,
+      "loss": 1.2587,
+      "mean_token_accuracy": 0.6720512602478266,
+      "step": 9
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.16962018609046936,
+      "learning_rate": 9.99543333708549e-07,
+      "loss": 1.3991,
+      "mean_token_accuracy": 0.6091120541095734,
+      "step": 10
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.15573781728744507,
+      "learning_rate": 9.989726963751682e-07,
+      "loss": 1.4038,
+      "mean_token_accuracy": 0.6495454851537943,
+      "step": 11
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.15279562771320343,
+      "learning_rate": 9.981741690106034e-07,
+      "loss": 1.3373,
+      "mean_token_accuracy": 0.6401338074356318,
+      "step": 12
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.16574503481388092,
+      "learning_rate": 9.971481163170269e-07,
+      "loss": 1.3758,
+      "mean_token_accuracy": 0.6352494675666094,
+      "step": 13
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.13780593872070312,
+      "learning_rate": 9.95895006911623e-07,
+      "loss": 1.3048,
+      "mean_token_accuracy": 0.5853612590581179,
+      "step": 14
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1259261965751648,
+      "learning_rate": 9.944154131125642e-07,
+      "loss": 1.2597,
+      "mean_token_accuracy": 0.6512391604483128,
+      "step": 15
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.1961268186569214,
+      "learning_rate": 9.927100106776212e-07,
+      "loss": 1.4922,
+      "mean_token_accuracy": 0.6155038736760616,
+      "step": 16
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.14302682876586914,
+      "learning_rate": 9.907795784955326e-07,
+      "loss": 1.3348,
+      "mean_token_accuracy": 0.6203473694622517,
+      "step": 17
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.1777554601430893,
+      "learning_rate": 9.886249982302718e-07,
+      "loss": 1.4322,
+      "mean_token_accuracy": 0.550493486225605,
+      "step": 18
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.13362129032611847,
+      "learning_rate": 9.862472539183755e-07,
+      "loss": 1.2716,
+      "mean_token_accuracy": 0.626600993797183,
+      "step": 19
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.16535401344299316,
+      "learning_rate": 9.836474315195147e-07,
+      "loss": 1.3826,
+      "mean_token_accuracy": 0.5930238626897335,
+      "step": 20
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 0.14859405159950256,
+      "learning_rate": 9.808267184205181e-07,
+      "loss": 1.2569,
+      "mean_token_accuracy": 0.5700501259416342,
+      "step": 21
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 0.1697828620672226,
+      "learning_rate": 9.777864028930705e-07,
+      "loss": 1.399,
+      "mean_token_accuracy": 0.6273653991520405,
+      "step": 22
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.13974109292030334,
+      "learning_rate": 9.745278735053343e-07,
+      "loss": 1.2999,
+      "mean_token_accuracy": 0.5806958097964525,
+      "step": 23
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.15478695929050446,
+      "learning_rate": 9.710526184877666e-07,
+      "loss": 1.3069,
+      "mean_token_accuracy": 0.6579883405938745,
+      "step": 24
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.15213146805763245,
+      "learning_rate": 9.673622250534155e-07,
+      "loss": 1.2778,
+      "mean_token_accuracy": 0.6076383553445339,
+      "step": 25
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 0.19709664583206177,
+      "learning_rate": 9.634583786730108e-07,
+      "loss": 1.4392,
+      "mean_token_accuracy": 0.5983579363673925,
+      "step": 26
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 0.12600693106651306,
+      "learning_rate": 9.593428623051791e-07,
+      "loss": 1.2201,
+      "mean_token_accuracy": 0.6514951223507524,
+      "step": 27
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.12962694466114044,
+      "learning_rate": 9.550175555821334e-07,
+      "loss": 1.2186,
+      "mean_token_accuracy": 0.6816060952842236,
+      "step": 28
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 0.1610107123851776,
+      "learning_rate": 9.504844339512094e-07,
+      "loss": 1.3459,
+      "mean_token_accuracy": 0.5962021965533495,
+      "step": 29
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.16483569145202637,
+      "learning_rate": 9.457455677726447e-07,
+      "loss": 1.2996,
+      "mean_token_accuracy": 0.593426201492548,
+      "step": 30
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.17700010538101196,
+      "learning_rate": 9.408031213740044e-07,
+      "loss": 1.4252,
+      "mean_token_accuracy": 0.6455631647258997,
+      "step": 31
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1746721863746643,
+      "learning_rate": 9.356593520616946e-07,
+      "loss": 1.3499,
+      "mean_token_accuracy": 0.658152773976326,
+      "step": 32
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 0.16630540788173676,
+      "learning_rate": 9.303166090900081e-07,
+      "loss": 1.4491,
+      "mean_token_accuracy": 0.5885015754029155,
+      "step": 33
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.1478070318698883,
+      "learning_rate": 9.247773325881769e-07,
+      "loss": 1.3426,
+      "mean_token_accuracy": 0.5941693857312202,
+      "step": 34
+    },
+    {
+      "epoch": 1.096,
+      "grad_norm": 0.15770336985588074,
+      "learning_rate": 9.190440524459202e-07,
+      "loss": 1.333,
+      "mean_token_accuracy": 0.6370699312537909,
+      "step": 35
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.13676655292510986,
+      "learning_rate": 9.131193871579974e-07,
+      "loss": 1.251,
+      "mean_token_accuracy": 0.6350114401429892,
+      "step": 36
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.14811713993549347,
+      "learning_rate": 9.070060426282924e-07,
+      "loss": 1.2536,
+      "mean_token_accuracy": 0.6008631493896246,
+      "step": 37
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 0.18470925092697144,
+      "learning_rate": 9.007068109339783e-07,
+      "loss": 1.4298,
+      "mean_token_accuracy": 0.6056210417300463,
+      "step": 38
+    },
+    {
+      "epoch": 1.224,
+      "grad_norm": 0.1423710435628891,
+      "learning_rate": 8.942245690503238e-07,
+      "loss": 1.3186,
+      "mean_token_accuracy": 0.5917444098740816,
+      "step": 39
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.13407811522483826,
+      "learning_rate": 8.875622775367259e-07,
+      "loss": 1.1799,
+      "mean_token_accuracy": 0.5821504034101963,
+      "step": 40
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.14558961987495422,
+      "learning_rate": 8.807229791845671e-07,
+      "loss": 1.2497,
+      "mean_token_accuracy": 0.6792742777615786,
+      "step": 41
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.16922399401664734,
+      "learning_rate": 8.737097976275176e-07,
+      "loss": 1.3662,
+      "mean_token_accuracy": 0.5913250017911196,
+      "step": 42
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 0.16981720924377441,
+      "learning_rate": 8.66525935914913e-07,
+      "loss": 1.3475,
+      "mean_token_accuracy": 0.6231703050434589,
+      "step": 43
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.16315869987010956,
+      "learning_rate": 8.591746750488637e-07,
+      "loss": 1.3429,
+      "mean_token_accuracy": 0.620381923392415,
+      "step": 44
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 0.1753516048192978,
+      "learning_rate": 8.516593724857597e-07,
+      "loss": 1.3794,
+      "mean_token_accuracy": 0.549949249252677,
+      "step": 45
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.1639939397573471,
+      "learning_rate": 8.439834606028593e-07,
+      "loss": 1.2901,
+      "mean_token_accuracy": 0.6702132746577263,
+      "step": 46
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.19329439103603363,
+      "learning_rate": 8.361504451306584e-07,
+      "loss": 1.4451,
+      "mean_token_accuracy": 0.6442436445504427,
+      "step": 47
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.17812158167362213,
+      "learning_rate": 8.281639035517591e-07,
+      "loss": 1.3771,
+      "mean_token_accuracy": 0.6258155256509781,
+      "step": 48
+    },
+    {
+      "epoch": 1.544,
+      "grad_norm": 0.16681429743766785,
+      "learning_rate": 8.200274834669675e-07,
+      "loss": 1.3343,
+      "mean_token_accuracy": 0.6598525494337082,
+      "step": 49
+    },
+    {
+      "epoch": 1.576,
+      "grad_norm": 0.18308602273464203,
+      "learning_rate": 8.117449009293668e-07,
+      "loss": 1.344,
+      "mean_token_accuracy": 0.6113573648035526,
+      "step": 50
+    },
+    {
+      "epoch": 1.608,
+      "grad_norm": 0.1643531769514084,
+      "learning_rate": 8.033199387471276e-07,
+      "loss": 1.2833,
+      "mean_token_accuracy": 0.6205067224800587,
+      "step": 51
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.14075644314289093,
+      "learning_rate": 7.947564447558299e-07,
+      "loss": 1.2727,
+      "mean_token_accuracy": 0.5858373213559389,
+      "step": 52
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 0.14337188005447388,
+      "learning_rate": 7.860583300610847e-07,
+      "loss": 1.2624,
+      "mean_token_accuracy": 0.6472346428781748,
+      "step": 53
+    },
+    {
+      "epoch": 1.704,
+      "grad_norm": 0.21596047282218933,
+      "learning_rate": 7.772295672522614e-07,
+      "loss": 1.4666,
+      "mean_token_accuracy": 0.6246221140027046,
+      "step": 54
+    },
+    {
+      "epoch": 1.736,
+      "grad_norm": 0.16021616756916046,
+      "learning_rate": 7.682741885881314e-07,
+      "loss": 1.3046,
+      "mean_token_accuracy": 0.6231255643069744,
+      "step": 55
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.16690893471240997,
+      "learning_rate": 7.591962841552626e-07,
+      "loss": 1.3555,
+      "mean_token_accuracy": 0.5934528838843107,
+      "step": 56
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.14958776533603668,
+      "learning_rate": 7.5e-07,
+      "loss": 1.3334,
+      "mean_token_accuracy": 0.6392526440322399,
+      "step": 57
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 0.14908351004123688,
+      "learning_rate": 7.406895362348915e-07,
+      "loss": 1.2467,
+      "mean_token_accuracy": 0.6652953112497926,
+      "step": 58
+    },
+    {
+      "epoch": 1.8639999999999999,
+      "grad_norm": 0.1505044549703598,
+      "learning_rate": 7.312691451204177e-07,
+      "loss": 1.2971,
+      "mean_token_accuracy": 0.6052623130381107,
+      "step": 59
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.16675080358982086,
+      "learning_rate": 7.217431291229067e-07,
+      "loss": 1.3255,
+      "mean_token_accuracy": 0.6600492112338543,
+      "step": 60
+    },
+    {
+      "epoch": 1.928,
+      "grad_norm": 0.18784397840499878,
+      "learning_rate": 7.121158389495185e-07,
+      "loss": 1.3422,
+      "mean_token_accuracy": 0.5918417889624834,
+      "step": 61
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.2011607587337494,
+      "learning_rate": 7.023916715611968e-07,
+      "loss": 1.3881,
+      "mean_token_accuracy": 0.6488993614912033,
+      "step": 62
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 0.16768693923950195,
+      "learning_rate": 6.925750681644953e-07,
+      "loss": 1.3326,
+      "mean_token_accuracy": 0.5926820989698172,
+      "step": 63
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.18448856472969055,
+      "learning_rate": 6.826705121831976e-07,
+      "loss": 1.282,
+      "mean_token_accuracy": 0.5813425332307816,
+      "step": 64
+    },
+    {
+      "epoch": 2.032,
+      "grad_norm": 0.19288884103298187,
+      "learning_rate": 6.726825272106538e-07,
+      "loss": 1.3491,
+      "mean_token_accuracy": 0.6006451118737459,
+      "step": 65
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 0.1677255481481552,
+      "learning_rate": 6.626156749437736e-07,
+      "loss": 1.3456,
+      "mean_token_accuracy": 0.6299659917131066,
+      "step": 66
+    },
+    {
+      "epoch": 2.096,
+      "grad_norm": 0.17888876795768738,
+      "learning_rate": 6.524745530996136e-07,
+      "loss": 1.3076,
+      "mean_token_accuracy": 0.651242658495903,
+      "step": 67
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.17528152465820312,
+      "learning_rate": 6.422637933155162e-07,
+      "loss": 1.3864,
+      "mean_token_accuracy": 0.6238404139876366,
+      "step": 68
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.181106299161911,
+      "learning_rate": 6.319880590337548e-07,
+      "loss": 1.356,
+      "mean_token_accuracy": 0.6091099604964256,
+      "step": 69
+    },
+    {
+      "epoch": 2.192,
+      "grad_norm": 0.15103061497211456,
+      "learning_rate": 6.216520433716544e-07,
+      "loss": 1.2593,
+      "mean_token_accuracy": 0.6407290436327457,
+      "step": 70
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 0.17606258392333984,
+      "learning_rate": 6.112604669781572e-07,
+      "loss": 1.3577,
+      "mean_token_accuracy": 0.5931300763040781,
+      "step": 71
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.1658383011817932,
+      "learning_rate": 6.008180758778166e-07,
+      "loss": 1.3541,
+      "mean_token_accuracy": 0.6121810097247362,
+      "step": 72
+    },
+    {
+      "epoch": 2.288,
+      "grad_norm": 0.18109431862831116,
+      "learning_rate": 5.903296393031995e-07,
+      "loss": 1.358,
+      "mean_token_accuracy": 0.6371448449790478,
+      "step": 73
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.18086610734462738,
+      "learning_rate": 5.797999475166896e-07,
+      "loss": 1.3915,
+      "mean_token_accuracy": 0.6093144360929728,
+      "step": 74
+    },
+    {
+      "epoch": 2.352,
+      "grad_norm": 0.18899185955524445,
+      "learning_rate": 5.69233809622687e-07,
+      "loss": 1.3463,
+      "mean_token_accuracy": 0.5968983750790358,
+      "step": 75
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.21237416565418243,
+      "learning_rate": 5.586360513712009e-07,
+      "loss": 1.4334,
+      "mean_token_accuracy": 0.6205319594591856,
+      "step": 76
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 0.14537544548511505,
+      "learning_rate": 5.480115129538409e-07,
+      "loss": 1.2203,
+      "mean_token_accuracy": 0.6319131031632423,
+      "step": 77
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 0.19504985213279724,
+      "learning_rate": 5.373650467932121e-07,
+      "loss": 1.3345,
+      "mean_token_accuracy": 0.5869994098320603,
+      "step": 78
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.24016834795475006,
+      "learning_rate": 5.267015153267245e-07,
+      "loss": 1.431,
+      "mean_token_accuracy": 0.5670944191515446,
+      "step": 79
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.18104156851768494,
+      "learning_rate": 5.160257887858277e-07,
+      "loss": 1.35,
+      "mean_token_accuracy": 0.5843236483633518,
+      "step": 80
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 0.1659788340330124,
+      "learning_rate": 5.053427429716866e-07,
+      "loss": 1.2807,
+      "mean_token_accuracy": 0.6326946448534727,
+      "step": 81
+    },
+    {
+      "epoch": 2.576,
+      "grad_norm": 0.1744644045829773,
+      "learning_rate": 4.946572570283134e-07,
+      "loss": 1.3162,
+      "mean_token_accuracy": 0.6193619854748249,
+      "step": 82
+    },
+    {
+      "epoch": 2.608,
+      "grad_norm": 0.20078222453594208,
+      "learning_rate": 4.839742112141724e-07,
+      "loss": 1.3542,
+      "mean_token_accuracy": 0.6239021811634302,
+      "step": 83
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.2332882434129715,
+      "learning_rate": 4.732984846732755e-07,
+      "loss": 1.4963,
+      "mean_token_accuracy": 0.5505349785089493,
+      "step": 84
+    },
+    {
+      "epoch": 2.672,
+      "grad_norm": 0.18425388634204865,
+      "learning_rate": 4.626349532067879e-07,
+      "loss": 1.3295,
+      "mean_token_accuracy": 0.6658568903803825,
+      "step": 85
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.18373511731624603,
+      "learning_rate": 4.519884870461591e-07,
+      "loss": 1.3761,
+      "mean_token_accuracy": 0.5894478112459183,
+      "step": 86
+    },
+    {
+      "epoch": 2.7359999999999998,
+      "grad_norm": 0.17059756815433502,
+      "learning_rate": 4.413639486287991e-07,
+      "loss": 1.2973,
+      "mean_token_accuracy": 0.6026603356003761,
+      "step": 87
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.17997656762599945,
+      "learning_rate": 4.3076619037731287e-07,
+      "loss": 1.344,
+      "mean_token_accuracy": 0.6407478991895914,
+      "step": 88
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.1454860121011734,
+      "learning_rate": 4.202000524833105e-07,
+      "loss": 1.1717,
+      "mean_token_accuracy": 0.6442389395087957,
+      "step": 89
+    },
+    {
+      "epoch": 2.832,
+      "grad_norm": 0.17520418763160706,
+      "learning_rate": 4.096703606968006e-07,
+      "loss": 1.3194,
+      "mean_token_accuracy": 0.6408489886671305,
+      "step": 90
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 0.12832075357437134,
+      "learning_rate": 3.991819241221835e-07,
+      "loss": 1.1475,
+      "mean_token_accuracy": 0.6956498101353645,
+      "step": 91
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 0.147433802485466,
+      "learning_rate": 3.8873953302184283e-07,
+      "loss": 1.2002,
+      "mean_token_accuracy": 0.6504368893802166,
+      "step": 92
+    },
+    {
+      "epoch": 2.928,
+      "grad_norm": 0.17667551338672638,
+      "learning_rate": 3.7834795662834566e-07,
+      "loss": 1.3643,
+      "mean_token_accuracy": 0.6086995024234056,
+      "step": 93
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.14905673265457153,
+      "learning_rate": 3.680119409662451e-07,
+      "loss": 1.2617,
+      "mean_token_accuracy": 0.5955792907625437,
+      "step": 94
+    },
+    {
+      "epoch": 2.992,
+      "grad_norm": 0.17350907623767853,
+      "learning_rate": 3.577362066844838e-07,
+      "loss": 1.2767,
+      "mean_token_accuracy": 0.646933751180768,
+      "step": 95
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19295324385166168,
+      "learning_rate": 3.4752544690038643e-07,
+      "loss": 1.3758,
+      "mean_token_accuracy": 0.6523182988166809,
+      "step": 96
+    },
+    {
+      "epoch": 3.032,
+      "grad_norm": 0.16096548736095428,
+      "learning_rate": 3.373843250562265e-07,
+      "loss": 1.2794,
+      "mean_token_accuracy": 0.6272456049919128,
+      "step": 97
+    },
+    {
+      "epoch": 3.064,
+      "grad_norm": 0.18685175478458405,
+      "learning_rate": 3.2731747278934623e-07,
+      "loss": 1.351,
+      "mean_token_accuracy": 0.6150259431451559,
+      "step": 98
+    },
+    {
+      "epoch": 3.096,
+      "grad_norm": 0.1742366999387741,
+      "learning_rate": 3.173294878168025e-07,
+      "loss": 1.3057,
+      "mean_token_accuracy": 0.6239325478672981,
+      "step": 99
+    },
+    {
+      "epoch": 3.128,
+      "grad_norm": 0.1615077257156372,
+      "learning_rate": 3.0742493183550454e-07,
+      "loss": 1.2822,
+      "mean_token_accuracy": 0.6322898715734482,
+      "step": 100
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 0.16552382707595825,
+      "learning_rate": 2.976083284388031e-07,
+      "loss": 1.3186,
+      "mean_token_accuracy": 0.5596373975276947,
+      "step": 101
+    },
+    {
+      "epoch": 3.192,
+      "grad_norm": 0.21563158929347992,
+      "learning_rate": 2.8788416105048117e-07,
+      "loss": 1.4503,
+      "mean_token_accuracy": 0.5805225949734449,
+      "step": 102
+    },
+    {
+      "epoch": 3.224,
+      "grad_norm": 0.16944873332977295,
+      "learning_rate": 2.782568708770933e-07,
+      "loss": 1.2583,
+      "mean_token_accuracy": 0.6507091373205185,
+      "step": 103
+    },
+    {
+      "epoch": 3.2560000000000002,
+      "grad_norm": 0.21833890676498413,
+      "learning_rate": 2.687308548795825e-07,
+      "loss": 1.4354,
+      "mean_token_accuracy": 0.6083431597799063,
+      "step": 104
+    },
+    {
+      "epoch": 3.288,
+      "grad_norm": 0.19507203996181488,
+      "learning_rate": 2.593104637651087e-07,
+      "loss": 1.4135,
+      "mean_token_accuracy": 0.6250948756933212,
+      "step": 105
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 0.20593255758285522,
+      "learning_rate": 2.500000000000001e-07,
+      "loss": 1.444,
+      "mean_token_accuracy": 0.5796275865286589,
+      "step": 106
+    },
+    {
+      "epoch": 3.352,
+      "grad_norm": 0.1837187558412552,
+      "learning_rate": 2.4080371584473745e-07,
+      "loss": 1.2909,
+      "mean_token_accuracy": 0.5766554772853851,
+      "step": 107
+    },
+    {
+      "epoch": 3.384,
+      "grad_norm": 0.18467815220355988,
+      "learning_rate": 2.3172581141186858e-07,
+      "loss": 1.3002,
+      "mean_token_accuracy": 0.6195548623800278,
+      "step": 108
+    },
+    {
+      "epoch": 3.416,
+      "grad_norm": 0.16379927098751068,
+      "learning_rate": 2.2277043274773854e-07,
+      "loss": 1.2523,
+      "mean_token_accuracy": 0.6432230100035667,
+      "step": 109
+    },
+    {
+      "epoch": 3.448,
+      "grad_norm": 0.17220264673233032,
+      "learning_rate": 2.1394166993891526e-07,
+      "loss": 1.2624,
+      "mean_token_accuracy": 0.676148321479559,
+      "step": 110
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 0.20385392010211945,
+      "learning_rate": 2.0524355524417015e-07,
+      "loss": 1.4015,
+      "mean_token_accuracy": 0.569313595071435,
+      "step": 111
+    },
+    {
+      "epoch": 3.512,
+      "grad_norm": 0.19238685071468353,
+      "learning_rate": 1.9668006125287228e-07,
+      "loss": 1.3489,
+      "mean_token_accuracy": 0.6104420125484467,
+      "step": 112
+    },
+    {
+      "epoch": 3.544,
+      "grad_norm": 0.1462380737066269,
+      "learning_rate": 1.8825509907063326e-07,
+      "loss": 1.2374,
+      "mean_token_accuracy": 0.626643180847168,
+      "step": 113
+    },
+    {
+      "epoch": 3.576,
+      "grad_norm": 0.15827052295207977,
+      "learning_rate": 1.7997251653303247e-07,
+      "loss": 1.1597,
+      "mean_token_accuracy": 0.6438571754842997,
+      "step": 114
+    },
+    {
+      "epoch": 3.608,
+      "grad_norm": 0.16454024612903595,
+      "learning_rate": 1.7183609644824092e-07,
+      "loss": 1.2748,
+      "mean_token_accuracy": 0.6228565536439419,
+      "step": 115
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.16890259087085724,
+      "learning_rate": 1.6384955486934154e-07,
+      "loss": 1.3156,
+      "mean_token_accuracy": 0.588938326574862,
+      "step": 116
+    },
+    {
+      "epoch": 3.672,
+      "grad_norm": 0.17300599813461304,
+      "learning_rate": 1.5601653939714072e-07,
+      "loss": 1.3535,
+      "mean_token_accuracy": 0.6365364268422127,
+      "step": 117
+    },
+    {
+      "epoch": 3.7039999999999997,
+      "grad_norm": 0.22110649943351746,
+      "learning_rate": 1.4834062751424015e-07,
+      "loss": 1.3965,
+      "mean_token_accuracy": 0.6131392857059836,
+      "step": 118
+    },
+    {
+      "epoch": 3.7359999999999998,
+      "grad_norm": 0.19601286947727203,
+      "learning_rate": 1.4082532495113624e-07,
+      "loss": 1.3234,
+      "mean_token_accuracy": 0.6324682310223579,
+      "step": 119
+    },
+    {
+      "epoch": 3.768,
+      "grad_norm": 0.1628580242395401,
+      "learning_rate": 1.3347406408508694e-07,
+      "loss": 1.1884,
+      "mean_token_accuracy": 0.6473836526274681,
+      "step": 120
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.20353291928768158,
+      "learning_rate": 1.262902023724824e-07,
+      "loss": 1.3896,
+      "mean_token_accuracy": 0.6374777723103762,
+      "step": 121
+    },
+    {
+      "epoch": 3.832,
+      "grad_norm": 0.18527667224407196,
+      "learning_rate": 1.1927702081543278e-07,
+      "loss": 1.2929,
+      "mean_token_accuracy": 0.6312173195183277,
+      "step": 122
+    },
+    {
+      "epoch": 3.864,
+      "grad_norm": 0.16761651635169983,
+      "learning_rate": 1.1243772246327415e-07,
+      "loss": 1.3631,
+      "mean_token_accuracy": 0.6534990258514881,
+      "step": 123
+    },
+    {
+      "epoch": 3.896,
+      "grad_norm": 0.1755058467388153,
+      "learning_rate": 1.0577543094967611e-07,
+      "loss": 1.2384,
+      "mean_token_accuracy": 0.6377339977771044,
+      "step": 124
+    },
+    {
+      "epoch": 3.928,
+      "grad_norm": 0.20673754811286926,
+      "learning_rate": 9.929318906602174e-08,
+      "loss": 1.3858,
+      "mean_token_accuracy": 0.5756818056106567,
+      "step": 125
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.17421787977218628,
+      "learning_rate": 9.299395737170757e-08,
+      "loss": 1.2774,
+      "mean_token_accuracy": 0.6454885508865118,
+      "step": 126
+    },
+    {
+      "epoch": 3.992,
+      "grad_norm": 0.20643050968647003,
+      "learning_rate": 8.688061284200265e-08,
+      "loss": 1.3525,
+      "mean_token_accuracy": 0.6394242160022259,
+      "step": 127
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.17338000237941742,
+      "learning_rate": 8.09559475540797e-08,
+      "loss": 1.3937,
+      "mean_token_accuracy": 0.5597065314650536,
+      "step": 128
+    },
+    {
+      "epoch": 4.032,
+      "grad_norm": 0.1463482528924942,
+      "learning_rate": 7.522266741182303e-08,
+      "loss": 1.1315,
+      "mean_token_accuracy": 0.649242352694273,
+      "step": 129
+    },
+    {
+      "epoch": 4.064,
+      "grad_norm": 0.2163277119398117,
+      "learning_rate": 6.968339090999186e-08,
+      "loss": 1.4269,
+      "mean_token_accuracy": 0.634560807608068,
+      "step": 130
+    },
+    {
+      "epoch": 4.096,
+      "grad_norm": 0.17108990252017975,
+      "learning_rate": 6.43406479383053e-08,
+      "loss": 1.3165,
+      "mean_token_accuracy": 0.5961530804634094,
+      "step": 131
+    },
+    {
+      "epoch": 4.128,
+      "grad_norm": 0.1974373757839203,
+      "learning_rate": 5.919687862599548e-08,
+      "loss": 1.3713,
+      "mean_token_accuracy": 0.5586186666041613,
+      "step": 132
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.17057853937149048,
+      "learning_rate": 5.425443222735526e-08,
+      "loss": 1.3471,
+      "mean_token_accuracy": 0.6344096027314663,
+      "step": 133
+    },
+    {
+      "epoch": 4.192,
+      "grad_norm": 0.1691618710756302,
+      "learning_rate": 4.951556604879048e-08,
+      "loss": 1.2531,
+      "mean_token_accuracy": 0.6311138197779655,
+      "step": 134
+    },
+    {
+      "epoch": 4.224,
+      "grad_norm": 0.18795742094516754,
+      "learning_rate": 4.498244441786675e-08,
+      "loss": 1.3348,
+      "mean_token_accuracy": 0.6147874612361193,
+      "step": 135
+    },
+    {
+      "epoch": 4.256,
+      "grad_norm": 0.18473310768604279,
+      "learning_rate": 4.065713769482082e-08,
+      "loss": 1.3594,
+      "mean_token_accuracy": 0.6315212519839406,
+      "step": 136
+    },
+    {
+      "epoch": 4.288,
+      "grad_norm": 0.18850365281105042,
+      "learning_rate": 3.654162132698918e-08,
+      "loss": 1.3012,
+      "mean_token_accuracy": 0.6255831960588694,
+      "step": 137
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.19047574698925018,
+      "learning_rate": 3.263777494658448e-08,
+      "loss": 1.3478,
+      "mean_token_accuracy": 0.5791074689477682,
+      "step": 138
+    },
+    {
+      "epoch": 4.352,
+      "grad_norm": 0.22570978105068207,
+      "learning_rate": 2.8947381512233305e-08,
+      "loss": 1.4639,
+      "mean_token_accuracy": 0.5423976201564074,
+      "step": 139
+    },
+    {
+      "epoch": 4.384,
+      "grad_norm": 0.162257581949234,
+      "learning_rate": 2.547212649466568e-08,
+      "loss": 1.2686,
+      "mean_token_accuracy": 0.6436207182705402,
+      "step": 140
+    },
+    {
+      "epoch": 4.416,
+      "grad_norm": 0.20653210580348969,
+      "learning_rate": 2.2213597106929605e-08,
+      "loss": 1.3962,
+      "mean_token_accuracy": 0.5815993268042803,
+      "step": 141
+    },
+    {
+      "epoch": 4.448,
+      "grad_norm": 0.16526532173156738,
+      "learning_rate": 1.9173281579481894e-08,
+      "loss": 1.3247,
+      "mean_token_accuracy": 0.6123546808958054,
+      "step": 142
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.19798213243484497,
+      "learning_rate": 1.6352568480485275e-08,
+      "loss": 1.3239,
+      "mean_token_accuracy": 0.6149218156933784,
+      "step": 143
+    },
+    {
+      "epoch": 4.5120000000000005,
+      "grad_norm": 0.19573239982128143,
+      "learning_rate": 1.3752746081624467e-08,
+      "loss": 1.3472,
+      "mean_token_accuracy": 0.6294556017965078,
+      "step": 144
+    },
+    {
+      "epoch": 4.5440000000000005,
+      "grad_norm": 0.18135203421115875,
+      "learning_rate": 1.1375001769727999e-08,
+      "loss": 1.2707,
+      "mean_token_accuracy": 0.6723539214581251,
+      "step": 145
+    },
+    {
+      "epoch": 4.576,
+      "grad_norm": 0.18120311200618744,
+      "learning_rate": 9.22042150446728e-09,
+      "loss": 1.2967,
+      "mean_token_accuracy": 0.6158712729811668,
+      "step": 146
+    },
+    {
+      "epoch": 4.608,
+      "grad_norm": 0.16739554703235626,
+      "learning_rate": 7.289989322378731e-09,
+      "loss": 1.2461,
+      "mean_token_accuracy": 0.6281041856855154,
+      "step": 147
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.1697273850440979,
+      "learning_rate": 5.5845868874357385e-09,
+      "loss": 1.2701,
+      "mean_token_accuracy": 0.6115036550909281,
+      "step": 148
+    },
+    {
+      "epoch": 4.672,
+      "grad_norm": 0.15502643585205078,
+      "learning_rate": 4.104993088376974e-09,
+      "loss": 1.2564,
+      "mean_token_accuracy": 0.6539264917373657,
+      "step": 149
+    },
+    {
+      "epoch": 4.704,
+      "grad_norm": 0.1558866798877716,
+      "learning_rate": 2.851883682973233e-09,
+      "loss": 1.1912,
+      "mean_token_accuracy": 0.6610716730356216,
+      "step": 150
+    },
+    {
+      "epoch": 4.736,
+      "grad_norm": 0.1858009248971939,
+      "learning_rate": 1.8258309893965374e-09,
+      "loss": 1.3801,
+      "mean_token_accuracy": 0.5909676998853683,
+      "step": 151
+    },
+    {
+      "epoch": 4.768,
+      "grad_norm": 0.1638512909412384,
+      "learning_rate": 1.0273036248318324e-09,
+      "loss": 1.282,
+      "mean_token_accuracy": 0.6404366474598646,
+      "step": 152
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.19918660819530487,
+      "learning_rate": 4.566662914508579e-10,
+      "loss": 1.2965,
+      "mean_token_accuracy": 0.6221714857965708,
+      "step": 153
+    },
+    {
+      "epoch": 4.832,
+      "grad_norm": 0.179250568151474,
+      "learning_rate": 1.1417960984605457e-10,
+      "loss": 1.3462,
+      "mean_token_accuracy": 0.6342775598168373,
+      "step": 154
+    },
+    {
+      "epoch": 4.864,
+      "grad_norm": 0.17288900911808014,
+      "learning_rate": 0.0,
+      "loss": 1.2734,
+      "mean_token_accuracy": 0.6538417730480433,
+      "step": 155
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 155,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.598544023790592e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ece07d8cccf7c785225570f970339a144946a89640ad7c13cc70d8f39506847
+size 5763