Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,14 @@ 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
+checkpoint-851/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-888/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-222/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-259/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-74/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-296/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-370/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-407/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-185/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-333/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-444/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-111/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-111/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-111/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
+}

checkpoint-111/special_tokens_map.json

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

checkpoint-111/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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 12000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-111/trainer_state.json

@@ -0,0 +1,921 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9395973154362416,
+  "eval_steps": 500,
+  "global_step": 111,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.026845637583892617,
+      "grad_norm": 0.04068412259221077,
+      "learning_rate": 4.9999899870162604e-05,
+      "loss": 0.5189,
+      "num_input_tokens_seen": 58440,
+      "step": 1
+    },
+    {
+      "epoch": 0.053691275167785234,
+      "grad_norm": 0.03802767023444176,
+      "learning_rate": 4.999959948145249e-05,
+      "loss": 0.5061,
+      "num_input_tokens_seen": 112800,
+      "step": 2
+    },
+    {
+      "epoch": 0.08053691275167785,
+      "grad_norm": 0.0524083748459816,
+      "learning_rate": 4.999909883627587e-05,
+      "loss": 0.5956,
+      "num_input_tokens_seen": 156704,
+      "step": 3
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 0.050608448684215546,
+      "learning_rate": 4.999839793864313e-05,
+      "loss": 0.5222,
+      "num_input_tokens_seen": 213952,
+      "step": 4
+    },
+    {
+      "epoch": 0.1342281879194631,
+      "grad_norm": 0.04771890118718147,
+      "learning_rate": 4.9997496794168726e-05,
+      "loss": 0.4761,
+      "num_input_tokens_seen": 266920,
+      "step": 5
+    },
+    {
+      "epoch": 0.1610738255033557,
+      "grad_norm": 0.05538628622889519,
+      "learning_rate": 4.999639541007116e-05,
+      "loss": 0.5221,
+      "num_input_tokens_seen": 313560,
+      "step": 6
+    },
+    {
+      "epoch": 0.18791946308724833,
+      "grad_norm": 0.053944796323776245,
+      "learning_rate": 4.999509379517297e-05,
+      "loss": 0.4738,
+      "num_input_tokens_seen": 349544,
+      "step": 7
+    },
+    {
+      "epoch": 0.21476510067114093,
+      "grad_norm": 0.05679492652416229,
+      "learning_rate": 4.9993591959900566e-05,
+      "loss": 0.5576,
+      "num_input_tokens_seen": 397952,
+      "step": 8
+    },
+    {
+      "epoch": 0.24161073825503357,
+      "grad_norm": 0.05358556658029556,
+      "learning_rate": 4.999188991628425e-05,
+      "loss": 0.4803,
+      "num_input_tokens_seen": 452568,
+      "step": 9
+    },
+    {
+      "epoch": 0.2684563758389262,
+      "grad_norm": 0.05667557194828987,
+      "learning_rate": 4.998998767795805e-05,
+      "loss": 0.4735,
+      "num_input_tokens_seen": 494400,
+      "step": 10
+    },
+    {
+      "epoch": 0.2953020134228188,
+      "grad_norm": 0.048348862677812576,
+      "learning_rate": 4.998788526015961e-05,
+      "loss": 0.5054,
+      "num_input_tokens_seen": 569352,
+      "step": 11
+    },
+    {
+      "epoch": 0.3221476510067114,
+      "grad_norm": 0.055022645741701126,
+      "learning_rate": 4.998558267973014e-05,
+      "loss": 0.494,
+      "num_input_tokens_seen": 623680,
+      "step": 12
+    },
+    {
+      "epoch": 0.348993288590604,
+      "grad_norm": 0.05279555916786194,
+      "learning_rate": 4.998307995511418e-05,
+      "loss": 0.4411,
+      "num_input_tokens_seen": 675784,
+      "step": 13
+    },
+    {
+      "epoch": 0.37583892617449666,
+      "grad_norm": 0.06557705253362656,
+      "learning_rate": 4.998037710635952e-05,
+      "loss": 0.5778,
+      "num_input_tokens_seen": 728120,
+      "step": 14
+    },
+    {
+      "epoch": 0.40268456375838924,
+      "grad_norm": 0.06649675220251083,
+      "learning_rate": 4.9977474155117045e-05,
+      "loss": 0.5217,
+      "num_input_tokens_seen": 780392,
+      "step": 15
+    },
+    {
+      "epoch": 0.42953020134228187,
+      "grad_norm": 0.05616322159767151,
+      "learning_rate": 4.997437112464049e-05,
+      "loss": 0.4175,
+      "num_input_tokens_seen": 841192,
+      "step": 16
+    },
+    {
+      "epoch": 0.4563758389261745,
+      "grad_norm": 0.07165056467056274,
+      "learning_rate": 4.997106803978636e-05,
+      "loss": 0.5109,
+      "num_input_tokens_seen": 899368,
+      "step": 17
+    },
+    {
+      "epoch": 0.48322147651006714,
+      "grad_norm": 0.06656442582607269,
+      "learning_rate": 4.996756492701362e-05,
+      "loss": 0.4066,
+      "num_input_tokens_seen": 944400,
+      "step": 18
+    },
+    {
+      "epoch": 0.5100671140939598,
+      "grad_norm": 0.0628059059381485,
+      "learning_rate": 4.996386181438357e-05,
+      "loss": 0.4501,
+      "num_input_tokens_seen": 997024,
+      "step": 19
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 0.06418219953775406,
+      "learning_rate": 4.995995873155958e-05,
+      "loss": 0.4632,
+      "num_input_tokens_seen": 1057264,
+      "step": 20
+    },
+    {
+      "epoch": 0.5637583892617449,
+      "grad_norm": 0.08489955216646194,
+      "learning_rate": 4.9955855709806845e-05,
+      "loss": 0.4224,
+      "num_input_tokens_seen": 1094144,
+      "step": 21
+    },
+    {
+      "epoch": 0.5906040268456376,
+      "grad_norm": 0.06560485810041428,
+      "learning_rate": 4.9951552781992154e-05,
+      "loss": 0.4084,
+      "num_input_tokens_seen": 1144376,
+      "step": 22
+    },
+    {
+      "epoch": 0.6174496644295302,
+      "grad_norm": 0.05338270589709282,
+      "learning_rate": 4.9947049982583625e-05,
+      "loss": 0.3925,
+      "num_input_tokens_seen": 1206272,
+      "step": 23
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 0.06893228739500046,
+      "learning_rate": 4.994234734765043e-05,
+      "loss": 0.3666,
+      "num_input_tokens_seen": 1252464,
+      "step": 24
+    },
+    {
+      "epoch": 0.6711409395973155,
+      "grad_norm": 0.07986386865377426,
+      "learning_rate": 4.99374449148625e-05,
+      "loss": 0.4105,
+      "num_input_tokens_seen": 1295560,
+      "step": 25
+    },
+    {
+      "epoch": 0.697986577181208,
+      "grad_norm": 0.0721018984913826,
+      "learning_rate": 4.99323427234902e-05,
+      "loss": 0.3965,
+      "num_input_tokens_seen": 1356792,
+      "step": 26
+    },
+    {
+      "epoch": 0.7248322147651006,
+      "grad_norm": 0.08186662942171097,
+      "learning_rate": 4.992704081440407e-05,
+      "loss": 0.3867,
+      "num_input_tokens_seen": 1408568,
+      "step": 27
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 0.07936503738164902,
+      "learning_rate": 4.992153923007446e-05,
+      "loss": 0.4272,
+      "num_input_tokens_seen": 1465984,
+      "step": 28
+    },
+    {
+      "epoch": 0.7785234899328859,
+      "grad_norm": 0.0778949186205864,
+      "learning_rate": 4.9915838014571174e-05,
+      "loss": 0.3499,
+      "num_input_tokens_seen": 1522568,
+      "step": 29
+    },
+    {
+      "epoch": 0.8053691275167785,
+      "grad_norm": 0.07632329314947128,
+      "learning_rate": 4.9909937213563165e-05,
+      "loss": 0.3536,
+      "num_input_tokens_seen": 1576592,
+      "step": 30
+    },
+    {
+      "epoch": 0.8322147651006712,
+      "grad_norm": 0.0791730061173439,
+      "learning_rate": 4.9903836874318135e-05,
+      "loss": 0.3416,
+      "num_input_tokens_seen": 1625336,
+      "step": 31
+    },
+    {
+      "epoch": 0.8590604026845637,
+      "grad_norm": 0.08963429927825928,
+      "learning_rate": 4.9897537045702146e-05,
+      "loss": 0.3559,
+      "num_input_tokens_seen": 1668736,
+      "step": 32
+    },
+    {
+      "epoch": 0.8859060402684564,
+      "grad_norm": 0.06969798356294632,
+      "learning_rate": 4.989103777817928e-05,
+      "loss": 0.358,
+      "num_input_tokens_seen": 1725096,
+      "step": 33
+    },
+    {
+      "epoch": 0.912751677852349,
+      "grad_norm": 0.09034521877765656,
+      "learning_rate": 4.988433912381117e-05,
+      "loss": 0.354,
+      "num_input_tokens_seen": 1768400,
+      "step": 34
+    },
+    {
+      "epoch": 0.9395973154362416,
+      "grad_norm": 0.07854894548654556,
+      "learning_rate": 4.987744113625665e-05,
+      "loss": 0.3553,
+      "num_input_tokens_seen": 1829224,
+      "step": 35
+    },
+    {
+      "epoch": 0.9664429530201343,
+      "grad_norm": 0.06981746852397919,
+      "learning_rate": 4.9870343870771256e-05,
+      "loss": 0.3651,
+      "num_input_tokens_seen": 1895440,
+      "step": 36
+    },
+    {
+      "epoch": 0.9932885906040269,
+      "grad_norm": 1.1971335411071777,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.3117,
+      "num_input_tokens_seen": 1948776,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13761547207832336,
+      "learning_rate": 4.985555173501106e-05,
+      "loss": 0.3247,
+      "num_input_tokens_seen": 1961808,
+      "step": 38
+    },
+    {
+      "epoch": 1.0268456375838926,
+      "grad_norm": 0.08985067158937454,
+      "learning_rate": 4.9847856983226996e-05,
+      "loss": 0.3328,
+      "num_input_tokens_seen": 2020584,
+      "step": 39
+    },
+    {
+      "epoch": 1.0536912751677852,
+      "grad_norm": 0.08735290169715881,
+      "learning_rate": 4.9839963190492576e-05,
+      "loss": 0.3809,
+      "num_input_tokens_seen": 2077264,
+      "step": 40
+    },
+    {
+      "epoch": 1.0805369127516777,
+      "grad_norm": 0.08123548328876495,
+      "learning_rate": 4.9831870420040126e-05,
+      "loss": 0.296,
+      "num_input_tokens_seen": 2117808,
+      "step": 41
+    },
+    {
+      "epoch": 1.1073825503355705,
+      "grad_norm": 0.09133706986904144,
+      "learning_rate": 4.982357873669589e-05,
+      "loss": 0.3045,
+      "num_input_tokens_seen": 2157928,
+      "step": 42
+    },
+    {
+      "epoch": 1.1342281879194631,
+      "grad_norm": 0.07161358743906021,
+      "learning_rate": 4.981508820687943e-05,
+      "loss": 0.3037,
+      "num_input_tokens_seen": 2215144,
+      "step": 43
+    },
+    {
+      "epoch": 1.1610738255033557,
+      "grad_norm": 0.07848912477493286,
+      "learning_rate": 4.9806398898603206e-05,
+      "loss": 0.308,
+      "num_input_tokens_seen": 2268776,
+      "step": 44
+    },
+    {
+      "epoch": 1.1879194630872483,
+      "grad_norm": 0.07580725848674774,
+      "learning_rate": 4.979751088147192e-05,
+      "loss": 0.3095,
+      "num_input_tokens_seen": 2316136,
+      "step": 45
+    },
+    {
+      "epoch": 1.2147651006711409,
+      "grad_norm": 0.13087698817253113,
+      "learning_rate": 4.978842422668204e-05,
+      "loss": 0.3144,
+      "num_input_tokens_seen": 2370888,
+      "step": 46
+    },
+    {
+      "epoch": 1.2416107382550337,
+      "grad_norm": 0.07428968697786331,
+      "learning_rate": 4.9779139007021184e-05,
+      "loss": 0.3084,
+      "num_input_tokens_seen": 2426656,
+      "step": 47
+    },
+    {
+      "epoch": 1.2684563758389262,
+      "grad_norm": 0.08130094408988953,
+      "learning_rate": 4.9769655296867554e-05,
+      "loss": 0.2861,
+      "num_input_tokens_seen": 2471944,
+      "step": 48
+    },
+    {
+      "epoch": 1.2953020134228188,
+      "grad_norm": 0.16188324987888336,
+      "learning_rate": 4.9759973172189334e-05,
+      "loss": 0.3136,
+      "num_input_tokens_seen": 2539888,
+      "step": 49
+    },
+    {
+      "epoch": 1.3221476510067114,
+      "grad_norm": 0.08185111731290817,
+      "learning_rate": 4.975009271054409e-05,
+      "loss": 0.26,
+      "num_input_tokens_seen": 2581936,
+      "step": 50
+    },
+    {
+      "epoch": 1.348993288590604,
+      "grad_norm": 0.07140379399061203,
+      "learning_rate": 4.974001399107816e-05,
+      "loss": 0.3178,
+      "num_input_tokens_seen": 2647016,
+      "step": 51
+    },
+    {
+      "epoch": 1.3758389261744965,
+      "grad_norm": 0.08086609840393066,
+      "learning_rate": 4.972973709452597e-05,
+      "loss": 0.2853,
+      "num_input_tokens_seen": 2694512,
+      "step": 52
+    },
+    {
+      "epoch": 1.4026845637583891,
+      "grad_norm": 0.08030746877193451,
+      "learning_rate": 4.971926210320944e-05,
+      "loss": 0.3009,
+      "num_input_tokens_seen": 2735672,
+      "step": 53
+    },
+    {
+      "epoch": 1.429530201342282,
+      "grad_norm": 0.07996731996536255,
+      "learning_rate": 4.9708589101037306e-05,
+      "loss": 0.2967,
+      "num_input_tokens_seen": 2789104,
+      "step": 54
+    },
+    {
+      "epoch": 1.4563758389261745,
+      "grad_norm": 0.0722445398569107,
+      "learning_rate": 4.969771817350445e-05,
+      "loss": 0.2741,
+      "num_input_tokens_seen": 2836960,
+      "step": 55
+    },
+    {
+      "epoch": 1.483221476510067,
+      "grad_norm": 0.08382672816514969,
+      "learning_rate": 4.968664940769121e-05,
+      "loss": 0.3276,
+      "num_input_tokens_seen": 2900208,
+      "step": 56
+    },
+    {
+      "epoch": 1.5100671140939599,
+      "grad_norm": 0.07235248386859894,
+      "learning_rate": 4.967538289226267e-05,
+      "loss": 0.2721,
+      "num_input_tokens_seen": 2964720,
+      "step": 57
+    },
+    {
+      "epoch": 1.5369127516778525,
+      "grad_norm": 0.07382500171661377,
+      "learning_rate": 4.9663918717467996e-05,
+      "loss": 0.3084,
+      "num_input_tokens_seen": 3029912,
+      "step": 58
+    },
+    {
+      "epoch": 1.563758389261745,
+      "grad_norm": 0.07173939794301987,
+      "learning_rate": 4.965225697513965e-05,
+      "loss": 0.2752,
+      "num_input_tokens_seen": 3081216,
+      "step": 59
+    },
+    {
+      "epoch": 1.5906040268456376,
+      "grad_norm": 0.07698569446802139,
+      "learning_rate": 4.9640397758692715e-05,
+      "loss": 0.2684,
+      "num_input_tokens_seen": 3131424,
+      "step": 60
+    },
+    {
+      "epoch": 1.6174496644295302,
+      "grad_norm": 0.07956692576408386,
+      "learning_rate": 4.962834116312409e-05,
+      "loss": 0.2663,
+      "num_input_tokens_seen": 3183240,
+      "step": 61
+    },
+    {
+      "epoch": 1.6442953020134228,
+      "grad_norm": 0.09150110185146332,
+      "learning_rate": 4.961608728501178e-05,
+      "loss": 0.2845,
+      "num_input_tokens_seen": 3231192,
+      "step": 62
+    },
+    {
+      "epoch": 1.6711409395973154,
+      "grad_norm": 0.07471323758363724,
+      "learning_rate": 4.960363622251409e-05,
+      "loss": 0.2873,
+      "num_input_tokens_seen": 3290616,
+      "step": 63
+    },
+    {
+      "epoch": 1.697986577181208,
+      "grad_norm": 0.08185286819934845,
+      "learning_rate": 4.959098807536885e-05,
+      "loss": 0.2858,
+      "num_input_tokens_seen": 3342512,
+      "step": 64
+    },
+    {
+      "epoch": 1.7248322147651005,
+      "grad_norm": 0.07076375931501389,
+      "learning_rate": 4.957814294489261e-05,
+      "loss": 0.2813,
+      "num_input_tokens_seen": 3404912,
+      "step": 65
+    },
+    {
+      "epoch": 1.7516778523489933,
+      "grad_norm": 0.08946257829666138,
+      "learning_rate": 4.956510093397983e-05,
+      "loss": 0.2417,
+      "num_input_tokens_seen": 3444648,
+      "step": 66
+    },
+    {
+      "epoch": 1.778523489932886,
+      "grad_norm": 0.08985330909490585,
+      "learning_rate": 4.955186214710208e-05,
+      "loss": 0.303,
+      "num_input_tokens_seen": 3493584,
+      "step": 67
+    },
+    {
+      "epoch": 1.8053691275167785,
+      "grad_norm": 0.0905148983001709,
+      "learning_rate": 4.953842669030716e-05,
+      "loss": 0.259,
+      "num_input_tokens_seen": 3544904,
+      "step": 68
+    },
+    {
+      "epoch": 1.8322147651006713,
+      "grad_norm": 0.08572433143854141,
+      "learning_rate": 4.952479467121827e-05,
+      "loss": 0.2709,
+      "num_input_tokens_seen": 3591296,
+      "step": 69
+    },
+    {
+      "epoch": 1.8590604026845639,
+      "grad_norm": 0.09188525378704071,
+      "learning_rate": 4.9510966199033174e-05,
+      "loss": 0.2615,
+      "num_input_tokens_seen": 3655368,
+      "step": 70
+    },
+    {
+      "epoch": 1.8859060402684564,
+      "grad_norm": 0.0810374766588211,
+      "learning_rate": 4.949694138452327e-05,
+      "loss": 0.2607,
+      "num_input_tokens_seen": 3707872,
+      "step": 71
+    },
+    {
+      "epoch": 1.912751677852349,
+      "grad_norm": 0.09255556017160416,
+      "learning_rate": 4.948272034003275e-05,
+      "loss": 0.2876,
+      "num_input_tokens_seen": 3755824,
+      "step": 72
+    },
+    {
+      "epoch": 1.9395973154362416,
+      "grad_norm": 0.07975213974714279,
+      "learning_rate": 4.9468303179477706e-05,
+      "loss": 0.2429,
+      "num_input_tokens_seen": 3810712,
+      "step": 73
+    },
+    {
+      "epoch": 1.9664429530201342,
+      "grad_norm": 0.09419341385364532,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.2672,
+      "num_input_tokens_seen": 3861920,
+      "step": 74
+    },
+    {
+      "epoch": 1.9932885906040267,
+      "grad_norm": 0.10117878019809723,
+      "learning_rate": 4.943888097369216e-05,
+      "loss": 0.2764,
+      "num_input_tokens_seen": 3909768,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.16053622961044312,
+      "learning_rate": 4.942387616414492e-05,
+      "loss": 0.2707,
+      "num_input_tokens_seen": 3923616,
+      "step": 76
+    },
+    {
+      "epoch": 2.0268456375838926,
+      "grad_norm": 0.14125753939151764,
+      "learning_rate": 4.940867570989777e-05,
+      "loss": 0.2517,
+      "num_input_tokens_seen": 3978224,
+      "step": 77
+    },
+    {
+      "epoch": 2.053691275167785,
+      "grad_norm": 0.08800158649682999,
+      "learning_rate": 4.939327973271221e-05,
+      "loss": 0.2821,
+      "num_input_tokens_seen": 4024096,
+      "step": 78
+    },
+    {
+      "epoch": 2.0805369127516777,
+      "grad_norm": 0.08880551159381866,
+      "learning_rate": 4.9377688355915994e-05,
+      "loss": 0.2396,
+      "num_input_tokens_seen": 4080656,
+      "step": 79
+    },
+    {
+      "epoch": 2.1073825503355703,
+      "grad_norm": 0.09785644710063934,
+      "learning_rate": 4.936190170440208e-05,
+      "loss": 0.2564,
+      "num_input_tokens_seen": 4122248,
+      "step": 80
+    },
+    {
+      "epoch": 2.134228187919463,
+      "grad_norm": 0.10203557461500168,
+      "learning_rate": 4.934591990462766e-05,
+      "loss": 0.2663,
+      "num_input_tokens_seen": 4183624,
+      "step": 81
+    },
+    {
+      "epoch": 2.1610738255033555,
+      "grad_norm": 0.09022527933120728,
+      "learning_rate": 4.932974308461311e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 4223696,
+      "step": 82
+    },
+    {
+      "epoch": 2.1879194630872485,
+      "grad_norm": 0.08529677987098694,
+      "learning_rate": 4.931337137394105e-05,
+      "loss": 0.2743,
+      "num_input_tokens_seen": 4282504,
+      "step": 83
+    },
+    {
+      "epoch": 2.214765100671141,
+      "grad_norm": 0.10522245615720749,
+      "learning_rate": 4.92968049037552e-05,
+      "loss": 0.2516,
+      "num_input_tokens_seen": 4338600,
+      "step": 84
+    },
+    {
+      "epoch": 2.2416107382550337,
+      "grad_norm": 0.09364143013954163,
+      "learning_rate": 4.928004380675941e-05,
+      "loss": 0.2463,
+      "num_input_tokens_seen": 4385840,
+      "step": 85
+    },
+    {
+      "epoch": 2.2684563758389262,
+      "grad_norm": 0.10501237958669662,
+      "learning_rate": 4.9263088217216544e-05,
+      "loss": 0.2578,
+      "num_input_tokens_seen": 4440368,
+      "step": 86
+    },
+    {
+      "epoch": 2.295302013422819,
+      "grad_norm": 0.09559391438961029,
+      "learning_rate": 4.9245938270947435e-05,
+      "loss": 0.2369,
+      "num_input_tokens_seen": 4502040,
+      "step": 87
+    },
+    {
+      "epoch": 2.3221476510067114,
+      "grad_norm": 0.08705922961235046,
+      "learning_rate": 4.922859410532978e-05,
+      "loss": 0.3009,
+      "num_input_tokens_seen": 4563296,
+      "step": 88
+    },
+    {
+      "epoch": 2.348993288590604,
+      "grad_norm": 0.08942529559135437,
+      "learning_rate": 4.921105585929709e-05,
+      "loss": 0.211,
+      "num_input_tokens_seen": 4620344,
+      "step": 89
+    },
+    {
+      "epoch": 2.3758389261744965,
+      "grad_norm": 0.088467076420784,
+      "learning_rate": 4.9193323673337476e-05,
+      "loss": 0.2463,
+      "num_input_tokens_seen": 4675400,
+      "step": 90
+    },
+    {
+      "epoch": 2.402684563758389,
+      "grad_norm": 0.08302924036979675,
+      "learning_rate": 4.9175397689492614e-05,
+      "loss": 0.2536,
+      "num_input_tokens_seen": 4734696,
+      "step": 91
+    },
+    {
+      "epoch": 2.4295302013422817,
+      "grad_norm": 0.10511067509651184,
+      "learning_rate": 4.915727805135657e-05,
+      "loss": 0.2538,
+      "num_input_tokens_seen": 4782448,
+      "step": 92
+    },
+    {
+      "epoch": 2.4563758389261743,
+      "grad_norm": 0.09681275486946106,
+      "learning_rate": 4.9138964904074667e-05,
+      "loss": 0.2243,
+      "num_input_tokens_seen": 4830504,
+      "step": 93
+    },
+    {
+      "epoch": 2.4832214765100673,
+      "grad_norm": 0.10118114203214645,
+      "learning_rate": 4.91204583943423e-05,
+      "loss": 0.2701,
+      "num_input_tokens_seen": 4886040,
+      "step": 94
+    },
+    {
+      "epoch": 2.51006711409396,
+      "grad_norm": 0.11683424562215805,
+      "learning_rate": 4.910175867040377e-05,
+      "loss": 0.2292,
+      "num_input_tokens_seen": 4934448,
+      "step": 95
+    },
+    {
+      "epoch": 2.5369127516778525,
+      "grad_norm": 0.09783443063497543,
+      "learning_rate": 4.90828658820511e-05,
+      "loss": 0.2398,
+      "num_input_tokens_seen": 4987040,
+      "step": 96
+    },
+    {
+      "epoch": 2.563758389261745,
+      "grad_norm": 0.10438188165426254,
+      "learning_rate": 4.9063780180622845e-05,
+      "loss": 0.2355,
+      "num_input_tokens_seen": 5037360,
+      "step": 97
+    },
+    {
+      "epoch": 2.5906040268456376,
+      "grad_norm": 0.1034293919801712,
+      "learning_rate": 4.9044501719002844e-05,
+      "loss": 0.2554,
+      "num_input_tokens_seen": 5091640,
+      "step": 98
+    },
+    {
+      "epoch": 2.61744966442953,
+      "grad_norm": 0.09722857177257538,
+      "learning_rate": 4.9025030651619046e-05,
+      "loss": 0.2176,
+      "num_input_tokens_seen": 5149232,
+      "step": 99
+    },
+    {
+      "epoch": 2.6442953020134228,
+      "grad_norm": 0.1010555699467659,
+      "learning_rate": 4.9005367134442235e-05,
+      "loss": 0.2191,
+      "num_input_tokens_seen": 5196648,
+      "step": 100
+    },
+    {
+      "epoch": 2.6711409395973154,
+      "grad_norm": 0.085463747382164,
+      "learning_rate": 4.89855113249848e-05,
+      "loss": 0.2283,
+      "num_input_tokens_seen": 5261568,
+      "step": 101
+    },
+    {
+      "epoch": 2.697986577181208,
+      "grad_norm": 0.10148970782756805,
+      "learning_rate": 4.896546338229945e-05,
+      "loss": 0.234,
+      "num_input_tokens_seen": 5312104,
+      "step": 102
+    },
+    {
+      "epoch": 2.7248322147651005,
+      "grad_norm": 0.12468232959508896,
+      "learning_rate": 4.894522346697796e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 5360104,
+      "step": 103
+    },
+    {
+      "epoch": 2.751677852348993,
+      "grad_norm": 0.11668706685304642,
+      "learning_rate": 4.892479174114989e-05,
+      "loss": 0.2291,
+      "num_input_tokens_seen": 5402856,
+      "step": 104
+    },
+    {
+      "epoch": 2.778523489932886,
+      "grad_norm": 0.11586510390043259,
+      "learning_rate": 4.890416836848127e-05,
+      "loss": 0.2297,
+      "num_input_tokens_seen": 5445040,
+      "step": 105
+    },
+    {
+      "epoch": 2.8053691275167782,
+      "grad_norm": 0.09793268144130707,
+      "learning_rate": 4.888335351417331e-05,
+      "loss": 0.2271,
+      "num_input_tokens_seen": 5497368,
+      "step": 106
+    },
+    {
+      "epoch": 2.8322147651006713,
+      "grad_norm": 0.1202295795083046,
+      "learning_rate": 4.886234734496102e-05,
+      "loss": 0.261,
+      "num_input_tokens_seen": 5560720,
+      "step": 107
+    },
+    {
+      "epoch": 2.859060402684564,
+      "grad_norm": 0.10316886752843857,
+      "learning_rate": 4.884115002911197e-05,
+      "loss": 0.2532,
+      "num_input_tokens_seen": 5616592,
+      "step": 108
+    },
+    {
+      "epoch": 2.8859060402684564,
+      "grad_norm": 0.10972882062196732,
+      "learning_rate": 4.8819761736424854e-05,
+      "loss": 0.2265,
+      "num_input_tokens_seen": 5674352,
+      "step": 109
+    },
+    {
+      "epoch": 2.912751677852349,
+      "grad_norm": 0.11267542093992233,
+      "learning_rate": 4.8798182638228166e-05,
+      "loss": 0.2356,
+      "num_input_tokens_seen": 5710912,
+      "step": 110
+    },
+    {
+      "epoch": 2.9395973154362416,
+      "grad_norm": 0.11448722332715988,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.2381,
+      "num_input_tokens_seen": 5757920,
+      "step": 111
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1110,
+  "num_input_tokens_seen": 5757920,
+  "num_train_epochs": 30,
+  "save_steps": 37,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.857477605831475e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-148/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-148/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-148/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
+}

checkpoint-148/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8051c45c1e2443a15399f0030b29e1a053773f5e7b3f7b93770621eceb9a9e
+size 551070514

checkpoint-148/special_tokens_map.json

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

checkpoint-148/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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 12000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-148/trainer_state.json

@@ -0,0 +1,1217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.912751677852349,
+  "eval_steps": 500,
+  "global_step": 148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.026845637583892617,
+      "grad_norm": 0.04068412259221077,
+      "learning_rate": 4.9999899870162604e-05,
+      "loss": 0.5189,
+      "num_input_tokens_seen": 58440,
+      "step": 1
+    },
+    {
+      "epoch": 0.053691275167785234,
+      "grad_norm": 0.03802767023444176,
+      "learning_rate": 4.999959948145249e-05,
+      "loss": 0.5061,
+      "num_input_tokens_seen": 112800,
+      "step": 2
+    },
+    {
+      "epoch": 0.08053691275167785,
+      "grad_norm": 0.0524083748459816,
+      "learning_rate": 4.999909883627587e-05,
+      "loss": 0.5956,
+      "num_input_tokens_seen": 156704,
+      "step": 3
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 0.050608448684215546,
+      "learning_rate": 4.999839793864313e-05,
+      "loss": 0.5222,
+      "num_input_tokens_seen": 213952,
+      "step": 4
+    },
+    {
+      "epoch": 0.1342281879194631,
+      "grad_norm": 0.04771890118718147,
+      "learning_rate": 4.9997496794168726e-05,
+      "loss": 0.4761,
+      "num_input_tokens_seen": 266920,
+      "step": 5
+    },
+    {
+      "epoch": 0.1610738255033557,
+      "grad_norm": 0.05538628622889519,
+      "learning_rate": 4.999639541007116e-05,
+      "loss": 0.5221,
+      "num_input_tokens_seen": 313560,
+      "step": 6
+    },
+    {
+      "epoch": 0.18791946308724833,
+      "grad_norm": 0.053944796323776245,
+      "learning_rate": 4.999509379517297e-05,
+      "loss": 0.4738,
+      "num_input_tokens_seen": 349544,
+      "step": 7
+    },
+    {
+      "epoch": 0.21476510067114093,
+      "grad_norm": 0.05679492652416229,
+      "learning_rate": 4.9993591959900566e-05,
+      "loss": 0.5576,
+      "num_input_tokens_seen": 397952,
+      "step": 8
+    },
+    {
+      "epoch": 0.24161073825503357,
+      "grad_norm": 0.05358556658029556,
+      "learning_rate": 4.999188991628425e-05,
+      "loss": 0.4803,
+      "num_input_tokens_seen": 452568,
+      "step": 9
+    },
+    {
+      "epoch": 0.2684563758389262,
+      "grad_norm": 0.05667557194828987,
+      "learning_rate": 4.998998767795805e-05,
+      "loss": 0.4735,
+      "num_input_tokens_seen": 494400,
+      "step": 10
+    },
+    {
+      "epoch": 0.2953020134228188,
+      "grad_norm": 0.048348862677812576,
+      "learning_rate": 4.998788526015961e-05,
+      "loss": 0.5054,
+      "num_input_tokens_seen": 569352,
+      "step": 11
+    },
+    {
+      "epoch": 0.3221476510067114,
+      "grad_norm": 0.055022645741701126,
+      "learning_rate": 4.998558267973014e-05,
+      "loss": 0.494,
+      "num_input_tokens_seen": 623680,
+      "step": 12
+    },
+    {
+      "epoch": 0.348993288590604,
+      "grad_norm": 0.05279555916786194,
+      "learning_rate": 4.998307995511418e-05,
+      "loss": 0.4411,
+      "num_input_tokens_seen": 675784,
+      "step": 13
+    },
+    {
+      "epoch": 0.37583892617449666,
+      "grad_norm": 0.06557705253362656,
+      "learning_rate": 4.998037710635952e-05,
+      "loss": 0.5778,
+      "num_input_tokens_seen": 728120,
+      "step": 14
+    },
+    {
+      "epoch": 0.40268456375838924,
+      "grad_norm": 0.06649675220251083,
+      "learning_rate": 4.9977474155117045e-05,
+      "loss": 0.5217,
+      "num_input_tokens_seen": 780392,
+      "step": 15
+    },
+    {
+      "epoch": 0.42953020134228187,
+      "grad_norm": 0.05616322159767151,
+      "learning_rate": 4.997437112464049e-05,
+      "loss": 0.4175,
+      "num_input_tokens_seen": 841192,
+      "step": 16
+    },
+    {
+      "epoch": 0.4563758389261745,
+      "grad_norm": 0.07165056467056274,
+      "learning_rate": 4.997106803978636e-05,
+      "loss": 0.5109,
+      "num_input_tokens_seen": 899368,
+      "step": 17
+    },
+    {
+      "epoch": 0.48322147651006714,
+      "grad_norm": 0.06656442582607269,
+      "learning_rate": 4.996756492701362e-05,
+      "loss": 0.4066,
+      "num_input_tokens_seen": 944400,
+      "step": 18
+    },
+    {
+      "epoch": 0.5100671140939598,
+      "grad_norm": 0.0628059059381485,
+      "learning_rate": 4.996386181438357e-05,
+      "loss": 0.4501,
+      "num_input_tokens_seen": 997024,
+      "step": 19
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 0.06418219953775406,
+      "learning_rate": 4.995995873155958e-05,
+      "loss": 0.4632,
+      "num_input_tokens_seen": 1057264,
+      "step": 20
+    },
+    {
+      "epoch": 0.5637583892617449,
+      "grad_norm": 0.08489955216646194,
+      "learning_rate": 4.9955855709806845e-05,
+      "loss": 0.4224,
+      "num_input_tokens_seen": 1094144,
+      "step": 21
+    },
+    {
+      "epoch": 0.5906040268456376,
+      "grad_norm": 0.06560485810041428,
+      "learning_rate": 4.9951552781992154e-05,
+      "loss": 0.4084,
+      "num_input_tokens_seen": 1144376,
+      "step": 22
+    },
+    {
+      "epoch": 0.6174496644295302,
+      "grad_norm": 0.05338270589709282,
+      "learning_rate": 4.9947049982583625e-05,
+      "loss": 0.3925,
+      "num_input_tokens_seen": 1206272,
+      "step": 23
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 0.06893228739500046,
+      "learning_rate": 4.994234734765043e-05,
+      "loss": 0.3666,
+      "num_input_tokens_seen": 1252464,
+      "step": 24
+    },
+    {
+      "epoch": 0.6711409395973155,
+      "grad_norm": 0.07986386865377426,
+      "learning_rate": 4.99374449148625e-05,
+      "loss": 0.4105,
+      "num_input_tokens_seen": 1295560,
+      "step": 25
+    },
+    {
+      "epoch": 0.697986577181208,
+      "grad_norm": 0.0721018984913826,
+      "learning_rate": 4.99323427234902e-05,
+      "loss": 0.3965,
+      "num_input_tokens_seen": 1356792,
+      "step": 26
+    },
+    {
+      "epoch": 0.7248322147651006,
+      "grad_norm": 0.08186662942171097,
+      "learning_rate": 4.992704081440407e-05,
+      "loss": 0.3867,
+      "num_input_tokens_seen": 1408568,
+      "step": 27
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 0.07936503738164902,
+      "learning_rate": 4.992153923007446e-05,
+      "loss": 0.4272,
+      "num_input_tokens_seen": 1465984,
+      "step": 28
+    },
+    {
+      "epoch": 0.7785234899328859,
+      "grad_norm": 0.0778949186205864,
+      "learning_rate": 4.9915838014571174e-05,
+      "loss": 0.3499,
+      "num_input_tokens_seen": 1522568,
+      "step": 29
+    },
+    {
+      "epoch": 0.8053691275167785,
+      "grad_norm": 0.07632329314947128,
+      "learning_rate": 4.9909937213563165e-05,
+      "loss": 0.3536,
+      "num_input_tokens_seen": 1576592,
+      "step": 30
+    },
+    {
+      "epoch": 0.8322147651006712,
+      "grad_norm": 0.0791730061173439,
+      "learning_rate": 4.9903836874318135e-05,
+      "loss": 0.3416,
+      "num_input_tokens_seen": 1625336,
+      "step": 31
+    },
+    {
+      "epoch": 0.8590604026845637,
+      "grad_norm": 0.08963429927825928,
+      "learning_rate": 4.9897537045702146e-05,
+      "loss": 0.3559,
+      "num_input_tokens_seen": 1668736,
+      "step": 32
+    },
+    {
+      "epoch": 0.8859060402684564,
+      "grad_norm": 0.06969798356294632,
+      "learning_rate": 4.989103777817928e-05,
+      "loss": 0.358,
+      "num_input_tokens_seen": 1725096,
+      "step": 33
+    },
+    {
+      "epoch": 0.912751677852349,
+      "grad_norm": 0.09034521877765656,
+      "learning_rate": 4.988433912381117e-05,
+      "loss": 0.354,
+      "num_input_tokens_seen": 1768400,
+      "step": 34
+    },
+    {
+      "epoch": 0.9395973154362416,
+      "grad_norm": 0.07854894548654556,
+      "learning_rate": 4.987744113625665e-05,
+      "loss": 0.3553,
+      "num_input_tokens_seen": 1829224,
+      "step": 35
+    },
+    {
+      "epoch": 0.9664429530201343,
+      "grad_norm": 0.06981746852397919,
+      "learning_rate": 4.9870343870771256e-05,
+      "loss": 0.3651,
+      "num_input_tokens_seen": 1895440,
+      "step": 36
+    },
+    {
+      "epoch": 0.9932885906040269,
+      "grad_norm": 1.1971335411071777,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.3117,
+      "num_input_tokens_seen": 1948776,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13761547207832336,
+      "learning_rate": 4.985555173501106e-05,
+      "loss": 0.3247,
+      "num_input_tokens_seen": 1961808,
+      "step": 38
+    },
+    {
+      "epoch": 1.0268456375838926,
+      "grad_norm": 0.08985067158937454,
+      "learning_rate": 4.9847856983226996e-05,
+      "loss": 0.3328,
+      "num_input_tokens_seen": 2020584,
+      "step": 39
+    },
+    {
+      "epoch": 1.0536912751677852,
+      "grad_norm": 0.08735290169715881,
+      "learning_rate": 4.9839963190492576e-05,
+      "loss": 0.3809,
+      "num_input_tokens_seen": 2077264,
+      "step": 40
+    },
+    {
+      "epoch": 1.0805369127516777,
+      "grad_norm": 0.08123548328876495,
+      "learning_rate": 4.9831870420040126e-05,
+      "loss": 0.296,
+      "num_input_tokens_seen": 2117808,
+      "step": 41
+    },
+    {
+      "epoch": 1.1073825503355705,
+      "grad_norm": 0.09133706986904144,
+      "learning_rate": 4.982357873669589e-05,
+      "loss": 0.3045,
+      "num_input_tokens_seen": 2157928,
+      "step": 42
+    },
+    {
+      "epoch": 1.1342281879194631,
+      "grad_norm": 0.07161358743906021,
+      "learning_rate": 4.981508820687943e-05,
+      "loss": 0.3037,
+      "num_input_tokens_seen": 2215144,
+      "step": 43
+    },
+    {
+      "epoch": 1.1610738255033557,
+      "grad_norm": 0.07848912477493286,
+      "learning_rate": 4.9806398898603206e-05,
+      "loss": 0.308,
+      "num_input_tokens_seen": 2268776,
+      "step": 44
+    },
+    {
+      "epoch": 1.1879194630872483,
+      "grad_norm": 0.07580725848674774,
+      "learning_rate": 4.979751088147192e-05,
+      "loss": 0.3095,
+      "num_input_tokens_seen": 2316136,
+      "step": 45
+    },
+    {
+      "epoch": 1.2147651006711409,
+      "grad_norm": 0.13087698817253113,
+      "learning_rate": 4.978842422668204e-05,
+      "loss": 0.3144,
+      "num_input_tokens_seen": 2370888,
+      "step": 46
+    },
+    {
+      "epoch": 1.2416107382550337,
+      "grad_norm": 0.07428968697786331,
+      "learning_rate": 4.9779139007021184e-05,
+      "loss": 0.3084,
+      "num_input_tokens_seen": 2426656,
+      "step": 47
+    },
+    {
+      "epoch": 1.2684563758389262,
+      "grad_norm": 0.08130094408988953,
+      "learning_rate": 4.9769655296867554e-05,
+      "loss": 0.2861,
+      "num_input_tokens_seen": 2471944,
+      "step": 48
+    },
+    {
+      "epoch": 1.2953020134228188,
+      "grad_norm": 0.16188324987888336,
+      "learning_rate": 4.9759973172189334e-05,
+      "loss": 0.3136,
+      "num_input_tokens_seen": 2539888,
+      "step": 49
+    },
+    {
+      "epoch": 1.3221476510067114,
+      "grad_norm": 0.08185111731290817,
+      "learning_rate": 4.975009271054409e-05,
+      "loss": 0.26,
+      "num_input_tokens_seen": 2581936,
+      "step": 50
+    },
+    {
+      "epoch": 1.348993288590604,
+      "grad_norm": 0.07140379399061203,
+      "learning_rate": 4.974001399107816e-05,
+      "loss": 0.3178,
+      "num_input_tokens_seen": 2647016,
+      "step": 51
+    },
+    {
+      "epoch": 1.3758389261744965,
+      "grad_norm": 0.08086609840393066,
+      "learning_rate": 4.972973709452597e-05,
+      "loss": 0.2853,
+      "num_input_tokens_seen": 2694512,
+      "step": 52
+    },
+    {
+      "epoch": 1.4026845637583891,
+      "grad_norm": 0.08030746877193451,
+      "learning_rate": 4.971926210320944e-05,
+      "loss": 0.3009,
+      "num_input_tokens_seen": 2735672,
+      "step": 53
+    },
+    {
+      "epoch": 1.429530201342282,
+      "grad_norm": 0.07996731996536255,
+      "learning_rate": 4.9708589101037306e-05,
+      "loss": 0.2967,
+      "num_input_tokens_seen": 2789104,
+      "step": 54
+    },
+    {
+      "epoch": 1.4563758389261745,
+      "grad_norm": 0.0722445398569107,
+      "learning_rate": 4.969771817350445e-05,
+      "loss": 0.2741,
+      "num_input_tokens_seen": 2836960,
+      "step": 55
+    },
+    {
+      "epoch": 1.483221476510067,
+      "grad_norm": 0.08382672816514969,
+      "learning_rate": 4.968664940769121e-05,
+      "loss": 0.3276,
+      "num_input_tokens_seen": 2900208,
+      "step": 56
+    },
+    {
+      "epoch": 1.5100671140939599,
+      "grad_norm": 0.07235248386859894,
+      "learning_rate": 4.967538289226267e-05,
+      "loss": 0.2721,
+      "num_input_tokens_seen": 2964720,
+      "step": 57
+    },
+    {
+      "epoch": 1.5369127516778525,
+      "grad_norm": 0.07382500171661377,
+      "learning_rate": 4.9663918717467996e-05,
+      "loss": 0.3084,
+      "num_input_tokens_seen": 3029912,
+      "step": 58
+    },
+    {
+      "epoch": 1.563758389261745,
+      "grad_norm": 0.07173939794301987,
+      "learning_rate": 4.965225697513965e-05,
+      "loss": 0.2752,
+      "num_input_tokens_seen": 3081216,
+      "step": 59
+    },
+    {
+      "epoch": 1.5906040268456376,
+      "grad_norm": 0.07698569446802139,
+      "learning_rate": 4.9640397758692715e-05,
+      "loss": 0.2684,
+      "num_input_tokens_seen": 3131424,
+      "step": 60
+    },
+    {
+      "epoch": 1.6174496644295302,
+      "grad_norm": 0.07956692576408386,
+      "learning_rate": 4.962834116312409e-05,
+      "loss": 0.2663,
+      "num_input_tokens_seen": 3183240,
+      "step": 61
+    },
+    {
+      "epoch": 1.6442953020134228,
+      "grad_norm": 0.09150110185146332,
+      "learning_rate": 4.961608728501178e-05,
+      "loss": 0.2845,
+      "num_input_tokens_seen": 3231192,
+      "step": 62
+    },
+    {
+      "epoch": 1.6711409395973154,
+      "grad_norm": 0.07471323758363724,
+      "learning_rate": 4.960363622251409e-05,
+      "loss": 0.2873,
+      "num_input_tokens_seen": 3290616,
+      "step": 63
+    },
+    {
+      "epoch": 1.697986577181208,
+      "grad_norm": 0.08185286819934845,
+      "learning_rate": 4.959098807536885e-05,
+      "loss": 0.2858,
+      "num_input_tokens_seen": 3342512,
+      "step": 64
+    },
+    {
+      "epoch": 1.7248322147651005,
+      "grad_norm": 0.07076375931501389,
+      "learning_rate": 4.957814294489261e-05,
+      "loss": 0.2813,
+      "num_input_tokens_seen": 3404912,
+      "step": 65
+    },
+    {
+      "epoch": 1.7516778523489933,
+      "grad_norm": 0.08946257829666138,
+      "learning_rate": 4.956510093397983e-05,
+      "loss": 0.2417,
+      "num_input_tokens_seen": 3444648,
+      "step": 66
+    },
+    {
+      "epoch": 1.778523489932886,
+      "grad_norm": 0.08985330909490585,
+      "learning_rate": 4.955186214710208e-05,
+      "loss": 0.303,
+      "num_input_tokens_seen": 3493584,
+      "step": 67
+    },
+    {
+      "epoch": 1.8053691275167785,
+      "grad_norm": 0.0905148983001709,
+      "learning_rate": 4.953842669030716e-05,
+      "loss": 0.259,
+      "num_input_tokens_seen": 3544904,
+      "step": 68
+    },
+    {
+      "epoch": 1.8322147651006713,
+      "grad_norm": 0.08572433143854141,
+      "learning_rate": 4.952479467121827e-05,
+      "loss": 0.2709,
+      "num_input_tokens_seen": 3591296,
+      "step": 69
+    },
+    {
+      "epoch": 1.8590604026845639,
+      "grad_norm": 0.09188525378704071,
+      "learning_rate": 4.9510966199033174e-05,
+      "loss": 0.2615,
+      "num_input_tokens_seen": 3655368,
+      "step": 70
+    },
+    {
+      "epoch": 1.8859060402684564,
+      "grad_norm": 0.0810374766588211,
+      "learning_rate": 4.949694138452327e-05,
+      "loss": 0.2607,
+      "num_input_tokens_seen": 3707872,
+      "step": 71
+    },
+    {
+      "epoch": 1.912751677852349,
+      "grad_norm": 0.09255556017160416,
+      "learning_rate": 4.948272034003275e-05,
+      "loss": 0.2876,
+      "num_input_tokens_seen": 3755824,
+      "step": 72
+    },
+    {
+      "epoch": 1.9395973154362416,
+      "grad_norm": 0.07975213974714279,
+      "learning_rate": 4.9468303179477706e-05,
+      "loss": 0.2429,
+      "num_input_tokens_seen": 3810712,
+      "step": 73
+    },
+    {
+      "epoch": 1.9664429530201342,
+      "grad_norm": 0.09419341385364532,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.2672,
+      "num_input_tokens_seen": 3861920,
+      "step": 74
+    },
+    {
+      "epoch": 1.9932885906040267,
+      "grad_norm": 0.10117878019809723,
+      "learning_rate": 4.943888097369216e-05,
+      "loss": 0.2764,
+      "num_input_tokens_seen": 3909768,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.16053622961044312,
+      "learning_rate": 4.942387616414492e-05,
+      "loss": 0.2707,
+      "num_input_tokens_seen": 3923616,
+      "step": 76
+    },
+    {
+      "epoch": 2.0268456375838926,
+      "grad_norm": 0.14125753939151764,
+      "learning_rate": 4.940867570989777e-05,
+      "loss": 0.2517,
+      "num_input_tokens_seen": 3978224,
+      "step": 77
+    },
+    {
+      "epoch": 2.053691275167785,
+      "grad_norm": 0.08800158649682999,
+      "learning_rate": 4.939327973271221e-05,
+      "loss": 0.2821,
+      "num_input_tokens_seen": 4024096,
+      "step": 78
+    },
+    {
+      "epoch": 2.0805369127516777,
+      "grad_norm": 0.08880551159381866,
+      "learning_rate": 4.9377688355915994e-05,
+      "loss": 0.2396,
+      "num_input_tokens_seen": 4080656,
+      "step": 79
+    },
+    {
+      "epoch": 2.1073825503355703,
+      "grad_norm": 0.09785644710063934,
+      "learning_rate": 4.936190170440208e-05,
+      "loss": 0.2564,
+      "num_input_tokens_seen": 4122248,
+      "step": 80
+    },
+    {
+      "epoch": 2.134228187919463,
+      "grad_norm": 0.10203557461500168,
+      "learning_rate": 4.934591990462766e-05,
+      "loss": 0.2663,
+      "num_input_tokens_seen": 4183624,
+      "step": 81
+    },
+    {
+      "epoch": 2.1610738255033555,
+      "grad_norm": 0.09022527933120728,
+      "learning_rate": 4.932974308461311e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 4223696,
+      "step": 82
+    },
+    {
+      "epoch": 2.1879194630872485,
+      "grad_norm": 0.08529677987098694,
+      "learning_rate": 4.931337137394105e-05,
+      "loss": 0.2743,
+      "num_input_tokens_seen": 4282504,
+      "step": 83
+    },
+    {
+      "epoch": 2.214765100671141,
+      "grad_norm": 0.10522245615720749,
+      "learning_rate": 4.92968049037552e-05,
+      "loss": 0.2516,
+      "num_input_tokens_seen": 4338600,
+      "step": 84
+    },
+    {
+      "epoch": 2.2416107382550337,
+      "grad_norm": 0.09364143013954163,
+      "learning_rate": 4.928004380675941e-05,
+      "loss": 0.2463,
+      "num_input_tokens_seen": 4385840,
+      "step": 85
+    },
+    {
+      "epoch": 2.2684563758389262,
+      "grad_norm": 0.10501237958669662,
+      "learning_rate": 4.9263088217216544e-05,
+      "loss": 0.2578,
+      "num_input_tokens_seen": 4440368,
+      "step": 86
+    },
+    {
+      "epoch": 2.295302013422819,
+      "grad_norm": 0.09559391438961029,
+      "learning_rate": 4.9245938270947435e-05,
+      "loss": 0.2369,
+      "num_input_tokens_seen": 4502040,
+      "step": 87
+    },
+    {
+      "epoch": 2.3221476510067114,
+      "grad_norm": 0.08705922961235046,
+      "learning_rate": 4.922859410532978e-05,
+      "loss": 0.3009,
+      "num_input_tokens_seen": 4563296,
+      "step": 88
+    },
+    {
+      "epoch": 2.348993288590604,
+      "grad_norm": 0.08942529559135437,
+      "learning_rate": 4.921105585929709e-05,
+      "loss": 0.211,
+      "num_input_tokens_seen": 4620344,
+      "step": 89
+    },
+    {
+      "epoch": 2.3758389261744965,
+      "grad_norm": 0.088467076420784,
+      "learning_rate": 4.9193323673337476e-05,
+      "loss": 0.2463,
+      "num_input_tokens_seen": 4675400,
+      "step": 90
+    },
+    {
+      "epoch": 2.402684563758389,
+      "grad_norm": 0.08302924036979675,
+      "learning_rate": 4.9175397689492614e-05,
+      "loss": 0.2536,
+      "num_input_tokens_seen": 4734696,
+      "step": 91
+    },
+    {
+      "epoch": 2.4295302013422817,
+      "grad_norm": 0.10511067509651184,
+      "learning_rate": 4.915727805135657e-05,
+      "loss": 0.2538,
+      "num_input_tokens_seen": 4782448,
+      "step": 92
+    },
+    {
+      "epoch": 2.4563758389261743,
+      "grad_norm": 0.09681275486946106,
+      "learning_rate": 4.9138964904074667e-05,
+      "loss": 0.2243,
+      "num_input_tokens_seen": 4830504,
+      "step": 93
+    },
+    {
+      "epoch": 2.4832214765100673,
+      "grad_norm": 0.10118114203214645,
+      "learning_rate": 4.91204583943423e-05,
+      "loss": 0.2701,
+      "num_input_tokens_seen": 4886040,
+      "step": 94
+    },
+    {
+      "epoch": 2.51006711409396,
+      "grad_norm": 0.11683424562215805,
+      "learning_rate": 4.910175867040377e-05,
+      "loss": 0.2292,
+      "num_input_tokens_seen": 4934448,
+      "step": 95
+    },
+    {
+      "epoch": 2.5369127516778525,
+      "grad_norm": 0.09783443063497543,
+      "learning_rate": 4.90828658820511e-05,
+      "loss": 0.2398,
+      "num_input_tokens_seen": 4987040,
+      "step": 96
+    },
+    {
+      "epoch": 2.563758389261745,
+      "grad_norm": 0.10438188165426254,
+      "learning_rate": 4.9063780180622845e-05,
+      "loss": 0.2355,
+      "num_input_tokens_seen": 5037360,
+      "step": 97
+    },
+    {
+      "epoch": 2.5906040268456376,
+      "grad_norm": 0.1034293919801712,
+      "learning_rate": 4.9044501719002844e-05,
+      "loss": 0.2554,
+      "num_input_tokens_seen": 5091640,
+      "step": 98
+    },
+    {
+      "epoch": 2.61744966442953,
+      "grad_norm": 0.09722857177257538,
+      "learning_rate": 4.9025030651619046e-05,
+      "loss": 0.2176,
+      "num_input_tokens_seen": 5149232,
+      "step": 99
+    },
+    {
+      "epoch": 2.6442953020134228,
+      "grad_norm": 0.1010555699467659,
+      "learning_rate": 4.9005367134442235e-05,
+      "loss": 0.2191,
+      "num_input_tokens_seen": 5196648,
+      "step": 100
+    },
+    {
+      "epoch": 2.6711409395973154,
+      "grad_norm": 0.085463747382164,
+      "learning_rate": 4.89855113249848e-05,
+      "loss": 0.2283,
+      "num_input_tokens_seen": 5261568,
+      "step": 101
+    },
+    {
+      "epoch": 2.697986577181208,
+      "grad_norm": 0.10148970782756805,
+      "learning_rate": 4.896546338229945e-05,
+      "loss": 0.234,
+      "num_input_tokens_seen": 5312104,
+      "step": 102
+    },
+    {
+      "epoch": 2.7248322147651005,
+      "grad_norm": 0.12468232959508896,
+      "learning_rate": 4.894522346697796e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 5360104,
+      "step": 103
+    },
+    {
+      "epoch": 2.751677852348993,
+      "grad_norm": 0.11668706685304642,
+      "learning_rate": 4.892479174114989e-05,
+      "loss": 0.2291,
+      "num_input_tokens_seen": 5402856,
+      "step": 104
+    },
+    {
+      "epoch": 2.778523489932886,
+      "grad_norm": 0.11586510390043259,
+      "learning_rate": 4.890416836848127e-05,
+      "loss": 0.2297,
+      "num_input_tokens_seen": 5445040,
+      "step": 105
+    },
+    {
+      "epoch": 2.8053691275167782,
+      "grad_norm": 0.09793268144130707,
+      "learning_rate": 4.888335351417331e-05,
+      "loss": 0.2271,
+      "num_input_tokens_seen": 5497368,
+      "step": 106
+    },
+    {
+      "epoch": 2.8322147651006713,
+      "grad_norm": 0.1202295795083046,
+      "learning_rate": 4.886234734496102e-05,
+      "loss": 0.261,
+      "num_input_tokens_seen": 5560720,
+      "step": 107
+    },
+    {
+      "epoch": 2.859060402684564,
+      "grad_norm": 0.10316886752843857,
+      "learning_rate": 4.884115002911197e-05,
+      "loss": 0.2532,
+      "num_input_tokens_seen": 5616592,
+      "step": 108
+    },
+    {
+      "epoch": 2.8859060402684564,
+      "grad_norm": 0.10972882062196732,
+      "learning_rate": 4.8819761736424854e-05,
+      "loss": 0.2265,
+      "num_input_tokens_seen": 5674352,
+      "step": 109
+    },
+    {
+      "epoch": 2.912751677852349,
+      "grad_norm": 0.11267542093992233,
+      "learning_rate": 4.8798182638228166e-05,
+      "loss": 0.2356,
+      "num_input_tokens_seen": 5710912,
+      "step": 110
+    },
+    {
+      "epoch": 2.9395973154362416,
+      "grad_norm": 0.11448722332715988,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.2381,
+      "num_input_tokens_seen": 5757920,
+      "step": 111
+    },
+    {
+      "epoch": 2.966442953020134,
+      "grad_norm": 0.11678655445575714,
+      "learning_rate": 4.875445271826084e-05,
+      "loss": 0.2288,
+      "num_input_tokens_seen": 5802192,
+      "step": 112
+    },
+    {
+      "epoch": 2.9932885906040267,
+      "grad_norm": 0.11252844333648682,
+      "learning_rate": 4.87323022467838e-05,
+      "loss": 0.2264,
+      "num_input_tokens_seen": 5867304,
+      "step": 113
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19352872669696808,
+      "learning_rate": 4.870996167038154e-05,
+      "loss": 0.2352,
+      "num_input_tokens_seen": 5885424,
+      "step": 114
+    },
+    {
+      "epoch": 3.0268456375838926,
+      "grad_norm": 0.1173228845000267,
+      "learning_rate": 4.868743116801074e-05,
+      "loss": 0.2164,
+      "num_input_tokens_seen": 5944528,
+      "step": 115
+    },
+    {
+      "epoch": 3.053691275167785,
+      "grad_norm": 0.11860992014408112,
+      "learning_rate": 4.866471092014945e-05,
+      "loss": 0.2329,
+      "num_input_tokens_seen": 6003480,
+      "step": 116
+    },
+    {
+      "epoch": 3.0805369127516777,
+      "grad_norm": 0.10296034812927246,
+      "learning_rate": 4.864180110879562e-05,
+      "loss": 0.2318,
+      "num_input_tokens_seen": 6059304,
+      "step": 117
+    },
+    {
+      "epoch": 3.1073825503355703,
+      "grad_norm": 0.11512338370084763,
+      "learning_rate": 4.861870191746573e-05,
+      "loss": 0.2054,
+      "num_input_tokens_seen": 6117288,
+      "step": 118
+    },
+    {
+      "epoch": 3.134228187919463,
+      "grad_norm": 0.13150866329669952,
+      "learning_rate": 4.859541353119322e-05,
+      "loss": 0.2086,
+      "num_input_tokens_seen": 6164008,
+      "step": 119
+    },
+    {
+      "epoch": 3.1610738255033555,
+      "grad_norm": 0.11846304684877396,
+      "learning_rate": 4.857193613652711e-05,
+      "loss": 0.2353,
+      "num_input_tokens_seen": 6224560,
+      "step": 120
+    },
+    {
+      "epoch": 3.1879194630872485,
+      "grad_norm": 0.12476348876953125,
+      "learning_rate": 4.854826992153038e-05,
+      "loss": 0.2295,
+      "num_input_tokens_seen": 6273248,
+      "step": 121
+    },
+    {
+      "epoch": 3.214765100671141,
+      "grad_norm": 0.11604316532611847,
+      "learning_rate": 4.8524415075778597e-05,
+      "loss": 0.1945,
+      "num_input_tokens_seen": 6327592,
+      "step": 122
+    },
+    {
+      "epoch": 3.2416107382550337,
+      "grad_norm": 0.12193804979324341,
+      "learning_rate": 4.850037179035829e-05,
+      "loss": 0.2389,
+      "num_input_tokens_seen": 6389680,
+      "step": 123
+    },
+    {
+      "epoch": 3.2684563758389262,
+      "grad_norm": 0.12192777544260025,
+      "learning_rate": 4.847614025786549e-05,
+      "loss": 0.2083,
+      "num_input_tokens_seen": 6441392,
+      "step": 124
+    },
+    {
+      "epoch": 3.295302013422819,
+      "grad_norm": 0.13284096121788025,
+      "learning_rate": 4.845172067240415e-05,
+      "loss": 0.2497,
+      "num_input_tokens_seen": 6483464,
+      "step": 125
+    },
+    {
+      "epoch": 3.3221476510067114,
+      "grad_norm": 0.10930957645177841,
+      "learning_rate": 4.842711322958459e-05,
+      "loss": 0.188,
+      "num_input_tokens_seen": 6536056,
+      "step": 126
+    },
+    {
+      "epoch": 3.348993288590604,
+      "grad_norm": 0.12303247302770615,
+      "learning_rate": 4.840231812652196e-05,
+      "loss": 0.1913,
+      "num_input_tokens_seen": 6583768,
+      "step": 127
+    },
+    {
+      "epoch": 3.3758389261744965,
+      "grad_norm": 0.12305760383605957,
+      "learning_rate": 4.837733556183463e-05,
+      "loss": 0.1926,
+      "num_input_tokens_seen": 6639048,
+      "step": 128
+    },
+    {
+      "epoch": 3.402684563758389,
+      "grad_norm": 0.13311812281608582,
+      "learning_rate": 4.8352165735642604e-05,
+      "loss": 0.2234,
+      "num_input_tokens_seen": 6691360,
+      "step": 129
+    },
+    {
+      "epoch": 3.4295302013422817,
+      "grad_norm": 0.12300640344619751,
+      "learning_rate": 4.8326808849565936e-05,
+      "loss": 0.2332,
+      "num_input_tokens_seen": 6743408,
+      "step": 130
+    },
+    {
+      "epoch": 3.4563758389261743,
+      "grad_norm": 0.1301521509885788,
+      "learning_rate": 4.830126510672309e-05,
+      "loss": 0.18,
+      "num_input_tokens_seen": 6790704,
+      "step": 131
+    },
+    {
+      "epoch": 3.4832214765100673,
+      "grad_norm": 0.1255597174167633,
+      "learning_rate": 4.827553471172935e-05,
+      "loss": 0.1964,
+      "num_input_tokens_seen": 6839200,
+      "step": 132
+    },
+    {
+      "epoch": 3.51006711409396,
+      "grad_norm": 0.13288290798664093,
+      "learning_rate": 4.824961787069511e-05,
+      "loss": 0.2116,
+      "num_input_tokens_seen": 6892832,
+      "step": 133
+    },
+    {
+      "epoch": 3.5369127516778525,
+      "grad_norm": 0.11485302448272705,
+      "learning_rate": 4.822351479122432e-05,
+      "loss": 0.2071,
+      "num_input_tokens_seen": 6949464,
+      "step": 134
+    },
+    {
+      "epoch": 3.563758389261745,
+      "grad_norm": 0.11960192024707794,
+      "learning_rate": 4.819722568241274e-05,
+      "loss": 0.175,
+      "num_input_tokens_seen": 6996480,
+      "step": 135
+    },
+    {
+      "epoch": 3.5906040268456376,
+      "grad_norm": 0.14381754398345947,
+      "learning_rate": 4.817075075484629e-05,
+      "loss": 0.237,
+      "num_input_tokens_seen": 7053720,
+      "step": 136
+    },
+    {
+      "epoch": 3.61744966442953,
+      "grad_norm": 0.1209937036037445,
+      "learning_rate": 4.8144090220599416e-05,
+      "loss": 0.2176,
+      "num_input_tokens_seen": 7111480,
+      "step": 137
+    },
+    {
+      "epoch": 3.6442953020134228,
+      "grad_norm": 0.13339534401893616,
+      "learning_rate": 4.811724429323329e-05,
+      "loss": 0.2164,
+      "num_input_tokens_seen": 7165728,
+      "step": 138
+    },
+    {
+      "epoch": 3.6711409395973154,
+      "grad_norm": 0.14351628720760345,
+      "learning_rate": 4.809021318779419e-05,
+      "loss": 0.1876,
+      "num_input_tokens_seen": 7207648,
+      "step": 139
+    },
+    {
+      "epoch": 3.697986577181208,
+      "grad_norm": 0.1557406485080719,
+      "learning_rate": 4.806299712081172e-05,
+      "loss": 0.2697,
+      "num_input_tokens_seen": 7254280,
+      "step": 140
+    },
+    {
+      "epoch": 3.7248322147651005,
+      "grad_norm": 0.14036628603935242,
+      "learning_rate": 4.8035596310297124e-05,
+      "loss": 0.1955,
+      "num_input_tokens_seen": 7297912,
+      "step": 141
+    },
+    {
+      "epoch": 3.751677852348993,
+      "grad_norm": 0.1406165212392807,
+      "learning_rate": 4.800801097574149e-05,
+      "loss": 0.2048,
+      "num_input_tokens_seen": 7343304,
+      "step": 142
+    },
+    {
+      "epoch": 3.778523489932886,
+      "grad_norm": 0.1484479159116745,
+      "learning_rate": 4.798024133811403e-05,
+      "loss": 0.2062,
+      "num_input_tokens_seen": 7391688,
+      "step": 143
+    },
+    {
+      "epoch": 3.8053691275167782,
+      "grad_norm": 0.15288512408733368,
+      "learning_rate": 4.795228761986028e-05,
+      "loss": 0.2123,
+      "num_input_tokens_seen": 7448016,
+      "step": 144
+    },
+    {
+      "epoch": 3.8322147651006713,
+      "grad_norm": 0.1407124102115631,
+      "learning_rate": 4.792415004490034e-05,
+      "loss": 0.2128,
+      "num_input_tokens_seen": 7495312,
+      "step": 145
+    },
+    {
+      "epoch": 3.859060402684564,
+      "grad_norm": 0.1452370434999466,
+      "learning_rate": 4.789582883862708e-05,
+      "loss": 0.207,
+      "num_input_tokens_seen": 7552600,
+      "step": 146
+    },
+    {
+      "epoch": 3.8859060402684564,
+      "grad_norm": 0.16543127596378326,
+      "learning_rate": 4.786732422790432e-05,
+      "loss": 0.2227,
+      "num_input_tokens_seen": 7615064,
+      "step": 147
+    },
+    {
+      "epoch": 3.912751677852349,
+      "grad_norm": 0.15252095460891724,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.2296,
+      "num_input_tokens_seen": 7671712,
+      "step": 148
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1110,
+  "num_input_tokens_seen": 7671712,
+  "num_train_epochs": 30,
+  "save_steps": 37,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.471984530965135e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-185/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-185/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-185/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea0fdc1108a55f6b65035db5112aa0a7266c2f98185455464f1ad0184ce8b36
+size 275341720

checkpoint-185/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
+}

checkpoint-185/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:187ed4085724cd6925ecf7c9bf747641ee35912fc4de247e3ae3d6380d7f05d1
+size 551070514

checkpoint-185/tokenizer.json

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

checkpoint-222/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-222/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12611d4a7e1d83a39793b0c227123e83ecc23e84553be501ddf26a29d187bbdc
+size 275341720

checkpoint-222/tokenizer.json

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

checkpoint-259/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-259/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad9df7aad858cb5d95cfc16c940f5ae2c9a76b38d0b0cfd37706357aeed26a1
+size 275341720

checkpoint-259/special_tokens_map.json

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

checkpoint-259/tokenizer.json

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

checkpoint-259/trainer_state.json

@@ -0,0 +1,2105 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.832214765100671,
+  "eval_steps": 500,
+  "global_step": 259,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.026845637583892617,
+      "grad_norm": 0.04068412259221077,
+      "learning_rate": 4.9999899870162604e-05,
+      "loss": 0.5189,
+      "num_input_tokens_seen": 58440,
+      "step": 1
+    },
+    {
+      "epoch": 0.053691275167785234,
+      "grad_norm": 0.03802767023444176,
+      "learning_rate": 4.999959948145249e-05,
+      "loss": 0.5061,
+      "num_input_tokens_seen": 112800,
+      "step": 2
+    },
+    {
+      "epoch": 0.08053691275167785,
+      "grad_norm": 0.0524083748459816,
+      "learning_rate": 4.999909883627587e-05,
+      "loss": 0.5956,
+      "num_input_tokens_seen": 156704,
+      "step": 3
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 0.050608448684215546,
+      "learning_rate": 4.999839793864313e-05,
+      "loss": 0.5222,
+      "num_input_tokens_seen": 213952,
+      "step": 4
+    },
+    {
+      "epoch": 0.1342281879194631,
+      "grad_norm": 0.04771890118718147,
+      "learning_rate": 4.9997496794168726e-05,
+      "loss": 0.4761,
+      "num_input_tokens_seen": 266920,
+      "step": 5
+    },
+    {
+      "epoch": 0.1610738255033557,
+      "grad_norm": 0.05538628622889519,
+      "learning_rate": 4.999639541007116e-05,
+      "loss": 0.5221,
+      "num_input_tokens_seen": 313560,
+      "step": 6
+    },
+    {
+      "epoch": 0.18791946308724833,
+      "grad_norm": 0.053944796323776245,
+      "learning_rate": 4.999509379517297e-05,
+      "loss": 0.4738,
+      "num_input_tokens_seen": 349544,
+      "step": 7
+    },
+    {
+      "epoch": 0.21476510067114093,
+      "grad_norm": 0.05679492652416229,
+      "learning_rate": 4.9993591959900566e-05,
+      "loss": 0.5576,
+      "num_input_tokens_seen": 397952,
+      "step": 8
+    },
+    {
+      "epoch": 0.24161073825503357,
+      "grad_norm": 0.05358556658029556,
+      "learning_rate": 4.999188991628425e-05,
+      "loss": 0.4803,
+      "num_input_tokens_seen": 452568,
+      "step": 9
+    },
+    {
+      "epoch": 0.2684563758389262,
+      "grad_norm": 0.05667557194828987,
+      "learning_rate": 4.998998767795805e-05,
+      "loss": 0.4735,
+      "num_input_tokens_seen": 494400,
+      "step": 10
+    },
+    {
+      "epoch": 0.2953020134228188,
+      "grad_norm": 0.048348862677812576,
+      "learning_rate": 4.998788526015961e-05,
+      "loss": 0.5054,
+      "num_input_tokens_seen": 569352,
+      "step": 11
+    },
+    {
+      "epoch": 0.3221476510067114,
+      "grad_norm": 0.055022645741701126,
+      "learning_rate": 4.998558267973014e-05,
+      "loss": 0.494,
+      "num_input_tokens_seen": 623680,
+      "step": 12
+    },
+    {
+      "epoch": 0.348993288590604,
+      "grad_norm": 0.05279555916786194,
+      "learning_rate": 4.998307995511418e-05,
+      "loss": 0.4411,
+      "num_input_tokens_seen": 675784,
+      "step": 13
+    },
+    {
+      "epoch": 0.37583892617449666,
+      "grad_norm": 0.06557705253362656,
+      "learning_rate": 4.998037710635952e-05,
+      "loss": 0.5778,
+      "num_input_tokens_seen": 728120,
+      "step": 14
+    },
+    {
+      "epoch": 0.40268456375838924,
+      "grad_norm": 0.06649675220251083,
+      "learning_rate": 4.9977474155117045e-05,
+      "loss": 0.5217,
+      "num_input_tokens_seen": 780392,
+      "step": 15
+    },
+    {
+      "epoch": 0.42953020134228187,
+      "grad_norm": 0.05616322159767151,
+      "learning_rate": 4.997437112464049e-05,
+      "loss": 0.4175,
+      "num_input_tokens_seen": 841192,
+      "step": 16
+    },
+    {
+      "epoch": 0.4563758389261745,
+      "grad_norm": 0.07165056467056274,
+      "learning_rate": 4.997106803978636e-05,
+      "loss": 0.5109,
+      "num_input_tokens_seen": 899368,
+      "step": 17
+    },
+    {
+      "epoch": 0.48322147651006714,
+      "grad_norm": 0.06656442582607269,
+      "learning_rate": 4.996756492701362e-05,
+      "loss": 0.4066,
+      "num_input_tokens_seen": 944400,
+      "step": 18
+    },
+    {
+      "epoch": 0.5100671140939598,
+      "grad_norm": 0.0628059059381485,
+      "learning_rate": 4.996386181438357e-05,
+      "loss": 0.4501,
+      "num_input_tokens_seen": 997024,
+      "step": 19
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 0.06418219953775406,
+      "learning_rate": 4.995995873155958e-05,
+      "loss": 0.4632,
+      "num_input_tokens_seen": 1057264,
+      "step": 20
+    },
+    {
+      "epoch": 0.5637583892617449,
+      "grad_norm": 0.08489955216646194,
+      "learning_rate": 4.9955855709806845e-05,
+      "loss": 0.4224,
+      "num_input_tokens_seen": 1094144,
+      "step": 21
+    },
+    {
+      "epoch": 0.5906040268456376,
+      "grad_norm": 0.06560485810041428,
+      "learning_rate": 4.9951552781992154e-05,
+      "loss": 0.4084,
+      "num_input_tokens_seen": 1144376,
+      "step": 22
+    },
+    {
+      "epoch": 0.6174496644295302,
+      "grad_norm": 0.05338270589709282,
+      "learning_rate": 4.9947049982583625e-05,
+      "loss": 0.3925,
+      "num_input_tokens_seen": 1206272,
+      "step": 23
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 0.06893228739500046,
+      "learning_rate": 4.994234734765043e-05,
+      "loss": 0.3666,
+      "num_input_tokens_seen": 1252464,
+      "step": 24
+    },
+    {
+      "epoch": 0.6711409395973155,
+      "grad_norm": 0.07986386865377426,
+      "learning_rate": 4.99374449148625e-05,
+      "loss": 0.4105,
+      "num_input_tokens_seen": 1295560,
+      "step": 25
+    },
+    {
+      "epoch": 0.697986577181208,
+      "grad_norm": 0.0721018984913826,
+      "learning_rate": 4.99323427234902e-05,
+      "loss": 0.3965,
+      "num_input_tokens_seen": 1356792,
+      "step": 26
+    },
+    {
+      "epoch": 0.7248322147651006,
+      "grad_norm": 0.08186662942171097,
+      "learning_rate": 4.992704081440407e-05,
+      "loss": 0.3867,
+      "num_input_tokens_seen": 1408568,
+      "step": 27
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 0.07936503738164902,
+      "learning_rate": 4.992153923007446e-05,
+      "loss": 0.4272,
+      "num_input_tokens_seen": 1465984,
+      "step": 28
+    },
+    {
+      "epoch": 0.7785234899328859,
+      "grad_norm": 0.0778949186205864,
+      "learning_rate": 4.9915838014571174e-05,
+      "loss": 0.3499,
+      "num_input_tokens_seen": 1522568,
+      "step": 29
+    },
+    {
+      "epoch": 0.8053691275167785,
+      "grad_norm": 0.07632329314947128,
+      "learning_rate": 4.9909937213563165e-05,
+      "loss": 0.3536,
+      "num_input_tokens_seen": 1576592,
+      "step": 30
+    },
+    {
+      "epoch": 0.8322147651006712,
+      "grad_norm": 0.0791730061173439,
+      "learning_rate": 4.9903836874318135e-05,
+      "loss": 0.3416,
+      "num_input_tokens_seen": 1625336,
+      "step": 31
+    },
+    {
+      "epoch": 0.8590604026845637,
+      "grad_norm": 0.08963429927825928,
+      "learning_rate": 4.9897537045702146e-05,
+      "loss": 0.3559,
+      "num_input_tokens_seen": 1668736,
+      "step": 32
+    },
+    {
+      "epoch": 0.8859060402684564,
+      "grad_norm": 0.06969798356294632,
+      "learning_rate": 4.989103777817928e-05,
+      "loss": 0.358,
+      "num_input_tokens_seen": 1725096,
+      "step": 33
+    },
+    {
+      "epoch": 0.912751677852349,
+      "grad_norm": 0.09034521877765656,
+      "learning_rate": 4.988433912381117e-05,
+      "loss": 0.354,
+      "num_input_tokens_seen": 1768400,
+      "step": 34
+    },
+    {
+      "epoch": 0.9395973154362416,
+      "grad_norm": 0.07854894548654556,
+      "learning_rate": 4.987744113625665e-05,
+      "loss": 0.3553,
+      "num_input_tokens_seen": 1829224,
+      "step": 35
+    },
+    {
+      "epoch": 0.9664429530201343,
+      "grad_norm": 0.06981746852397919,
+      "learning_rate": 4.9870343870771256e-05,
+      "loss": 0.3651,
+      "num_input_tokens_seen": 1895440,
+      "step": 36
+    },
+    {
+      "epoch": 0.9932885906040269,
+      "grad_norm": 1.1971335411071777,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.3117,
+      "num_input_tokens_seen": 1948776,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13761547207832336,
+      "learning_rate": 4.985555173501106e-05,
+      "loss": 0.3247,
+      "num_input_tokens_seen": 1961808,
+      "step": 38
+    },
+    {
+      "epoch": 1.0268456375838926,
+      "grad_norm": 0.08985067158937454,
+      "learning_rate": 4.9847856983226996e-05,
+      "loss": 0.3328,
+      "num_input_tokens_seen": 2020584,
+      "step": 39
+    },
+    {
+      "epoch": 1.0536912751677852,
+      "grad_norm": 0.08735290169715881,
+      "learning_rate": 4.9839963190492576e-05,
+      "loss": 0.3809,
+      "num_input_tokens_seen": 2077264,
+      "step": 40
+    },
+    {
+      "epoch": 1.0805369127516777,
+      "grad_norm": 0.08123548328876495,
+      "learning_rate": 4.9831870420040126e-05,
+      "loss": 0.296,
+      "num_input_tokens_seen": 2117808,
+      "step": 41
+    },
+    {
+      "epoch": 1.1073825503355705,
+      "grad_norm": 0.09133706986904144,
+      "learning_rate": 4.982357873669589e-05,
+      "loss": 0.3045,
+      "num_input_tokens_seen": 2157928,
+      "step": 42
+    },
+    {
+      "epoch": 1.1342281879194631,
+      "grad_norm": 0.07161358743906021,
+      "learning_rate": 4.981508820687943e-05,
+      "loss": 0.3037,
+      "num_input_tokens_seen": 2215144,
+      "step": 43
+    },
+    {
+      "epoch": 1.1610738255033557,
+      "grad_norm": 0.07848912477493286,
+      "learning_rate": 4.9806398898603206e-05,
+      "loss": 0.308,
+      "num_input_tokens_seen": 2268776,
+      "step": 44
+    },
+    {
+      "epoch": 1.1879194630872483,
+      "grad_norm": 0.07580725848674774,
+      "learning_rate": 4.979751088147192e-05,
+      "loss": 0.3095,
+      "num_input_tokens_seen": 2316136,
+      "step": 45
+    },
+    {
+      "epoch": 1.2147651006711409,
+      "grad_norm": 0.13087698817253113,
+      "learning_rate": 4.978842422668204e-05,
+      "loss": 0.3144,
+      "num_input_tokens_seen": 2370888,
+      "step": 46
+    },
+    {
+      "epoch": 1.2416107382550337,
+      "grad_norm": 0.07428968697786331,
+      "learning_rate": 4.9779139007021184e-05,
+      "loss": 0.3084,
+      "num_input_tokens_seen": 2426656,
+      "step": 47
+    },
+    {
+      "epoch": 1.2684563758389262,
+      "grad_norm": 0.08130094408988953,
+      "learning_rate": 4.9769655296867554e-05,
+      "loss": 0.2861,
+      "num_input_tokens_seen": 2471944,
+      "step": 48
+    },
+    {
+      "epoch": 1.2953020134228188,
+      "grad_norm": 0.16188324987888336,
+      "learning_rate": 4.9759973172189334e-05,
+      "loss": 0.3136,
+      "num_input_tokens_seen": 2539888,
+      "step": 49
+    },
+    {
+      "epoch": 1.3221476510067114,
+      "grad_norm": 0.08185111731290817,
+      "learning_rate": 4.975009271054409e-05,
+      "loss": 0.26,
+      "num_input_tokens_seen": 2581936,
+      "step": 50
+    },
+    {
+      "epoch": 1.348993288590604,
+      "grad_norm": 0.07140379399061203,
+      "learning_rate": 4.974001399107816e-05,
+      "loss": 0.3178,
+      "num_input_tokens_seen": 2647016,
+      "step": 51
+    },
+    {
+      "epoch": 1.3758389261744965,
+      "grad_norm": 0.08086609840393066,
+      "learning_rate": 4.972973709452597e-05,
+      "loss": 0.2853,
+      "num_input_tokens_seen": 2694512,
+      "step": 52
+    },
+    {
+      "epoch": 1.4026845637583891,
+      "grad_norm": 0.08030746877193451,
+      "learning_rate": 4.971926210320944e-05,
+      "loss": 0.3009,
+      "num_input_tokens_seen": 2735672,
+      "step": 53
+    },
+    {
+      "epoch": 1.429530201342282,
+      "grad_norm": 0.07996731996536255,
+      "learning_rate": 4.9708589101037306e-05,
+      "loss": 0.2967,
+      "num_input_tokens_seen": 2789104,
+      "step": 54
+    },
+    {
+      "epoch": 1.4563758389261745,
+      "grad_norm": 0.0722445398569107,
+      "learning_rate": 4.969771817350445e-05,
+      "loss": 0.2741,
+      "num_input_tokens_seen": 2836960,
+      "step": 55
+    },
+    {
+      "epoch": 1.483221476510067,
+      "grad_norm": 0.08382672816514969,
+      "learning_rate": 4.968664940769121e-05,
+      "loss": 0.3276,
+      "num_input_tokens_seen": 2900208,
+      "step": 56
+    },
+    {
+      "epoch": 1.5100671140939599,
+      "grad_norm": 0.07235248386859894,
+      "learning_rate": 4.967538289226267e-05,
+      "loss": 0.2721,
+      "num_input_tokens_seen": 2964720,
+      "step": 57
+    },
+    {
+      "epoch": 1.5369127516778525,
+      "grad_norm": 0.07382500171661377,
+      "learning_rate": 4.9663918717467996e-05,
+      "loss": 0.3084,
+      "num_input_tokens_seen": 3029912,
+      "step": 58
+    },
+    {
+      "epoch": 1.563758389261745,
+      "grad_norm": 0.07173939794301987,
+      "learning_rate": 4.965225697513965e-05,
+      "loss": 0.2752,
+      "num_input_tokens_seen": 3081216,
+      "step": 59
+    },
+    {
+      "epoch": 1.5906040268456376,
+      "grad_norm": 0.07698569446802139,
+      "learning_rate": 4.9640397758692715e-05,
+      "loss": 0.2684,
+      "num_input_tokens_seen": 3131424,
+      "step": 60
+    },
+    {
+      "epoch": 1.6174496644295302,
+      "grad_norm": 0.07956692576408386,
+      "learning_rate": 4.962834116312409e-05,
+      "loss": 0.2663,
+      "num_input_tokens_seen": 3183240,
+      "step": 61
+    },
+    {
+      "epoch": 1.6442953020134228,
+      "grad_norm": 0.09150110185146332,
+      "learning_rate": 4.961608728501178e-05,
+      "loss": 0.2845,
+      "num_input_tokens_seen": 3231192,
+      "step": 62
+    },
+    {
+      "epoch": 1.6711409395973154,
+      "grad_norm": 0.07471323758363724,
+      "learning_rate": 4.960363622251409e-05,
+      "loss": 0.2873,
+      "num_input_tokens_seen": 3290616,
+      "step": 63
+    },
+    {
+      "epoch": 1.697986577181208,
+      "grad_norm": 0.08185286819934845,
+      "learning_rate": 4.959098807536885e-05,
+      "loss": 0.2858,
+      "num_input_tokens_seen": 3342512,
+      "step": 64
+    },
+    {
+      "epoch": 1.7248322147651005,
+      "grad_norm": 0.07076375931501389,
+      "learning_rate": 4.957814294489261e-05,
+      "loss": 0.2813,
+      "num_input_tokens_seen": 3404912,
+      "step": 65
+    },
+    {
+      "epoch": 1.7516778523489933,
+      "grad_norm": 0.08946257829666138,
+      "learning_rate": 4.956510093397983e-05,
+      "loss": 0.2417,
+      "num_input_tokens_seen": 3444648,
+      "step": 66
+    },
+    {
+      "epoch": 1.778523489932886,
+      "grad_norm": 0.08985330909490585,
+      "learning_rate": 4.955186214710208e-05,
+      "loss": 0.303,
+      "num_input_tokens_seen": 3493584,
+      "step": 67
+    },
+    {
+      "epoch": 1.8053691275167785,
+      "grad_norm": 0.0905148983001709,
+      "learning_rate": 4.953842669030716e-05,
+      "loss": 0.259,
+      "num_input_tokens_seen": 3544904,
+      "step": 68
+    },
+    {
+      "epoch": 1.8322147651006713,
+      "grad_norm": 0.08572433143854141,
+      "learning_rate": 4.952479467121827e-05,
+      "loss": 0.2709,
+      "num_input_tokens_seen": 3591296,
+      "step": 69
+    },
+    {
+      "epoch": 1.8590604026845639,
+      "grad_norm": 0.09188525378704071,
+      "learning_rate": 4.9510966199033174e-05,
+      "loss": 0.2615,
+      "num_input_tokens_seen": 3655368,
+      "step": 70
+    },
+    {
+      "epoch": 1.8859060402684564,
+      "grad_norm": 0.0810374766588211,
+      "learning_rate": 4.949694138452327e-05,
+      "loss": 0.2607,
+      "num_input_tokens_seen": 3707872,
+      "step": 71
+    },
+    {
+      "epoch": 1.912751677852349,
+      "grad_norm": 0.09255556017160416,
+      "learning_rate": 4.948272034003275e-05,
+      "loss": 0.2876,
+      "num_input_tokens_seen": 3755824,
+      "step": 72
+    },
+    {
+      "epoch": 1.9395973154362416,
+      "grad_norm": 0.07975213974714279,
+      "learning_rate": 4.9468303179477706e-05,
+      "loss": 0.2429,
+      "num_input_tokens_seen": 3810712,
+      "step": 73
+    },
+    {
+      "epoch": 1.9664429530201342,
+      "grad_norm": 0.09419341385364532,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.2672,
+      "num_input_tokens_seen": 3861920,
+      "step": 74
+    },
+    {
+      "epoch": 1.9932885906040267,
+      "grad_norm": 0.10117878019809723,
+      "learning_rate": 4.943888097369216e-05,
+      "loss": 0.2764,
+      "num_input_tokens_seen": 3909768,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.16053622961044312,
+      "learning_rate": 4.942387616414492e-05,
+      "loss": 0.2707,
+      "num_input_tokens_seen": 3923616,
+      "step": 76
+    },
+    {
+      "epoch": 2.0268456375838926,
+      "grad_norm": 0.14125753939151764,
+      "learning_rate": 4.940867570989777e-05,
+      "loss": 0.2517,
+      "num_input_tokens_seen": 3978224,
+      "step": 77
+    },
+    {
+      "epoch": 2.053691275167785,
+      "grad_norm": 0.08800158649682999,
+      "learning_rate": 4.939327973271221e-05,
+      "loss": 0.2821,
+      "num_input_tokens_seen": 4024096,
+      "step": 78
+    },
+    {
+      "epoch": 2.0805369127516777,
+      "grad_norm": 0.08880551159381866,
+      "learning_rate": 4.9377688355915994e-05,
+      "loss": 0.2396,
+      "num_input_tokens_seen": 4080656,
+      "step": 79
+    },
+    {
+      "epoch": 2.1073825503355703,
+      "grad_norm": 0.09785644710063934,
+      "learning_rate": 4.936190170440208e-05,
+      "loss": 0.2564,
+      "num_input_tokens_seen": 4122248,
+      "step": 80
+    },
+    {
+      "epoch": 2.134228187919463,
+      "grad_norm": 0.10203557461500168,
+      "learning_rate": 4.934591990462766e-05,
+      "loss": 0.2663,
+      "num_input_tokens_seen": 4183624,
+      "step": 81
+    },
+    {
+      "epoch": 2.1610738255033555,
+      "grad_norm": 0.09022527933120728,
+      "learning_rate": 4.932974308461311e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 4223696,
+      "step": 82
+    },
+    {
+      "epoch": 2.1879194630872485,
+      "grad_norm": 0.08529677987098694,
+      "learning_rate": 4.931337137394105e-05,
+      "loss": 0.2743,
+      "num_input_tokens_seen": 4282504,
+      "step": 83
+    },
+    {
+      "epoch": 2.214765100671141,
+      "grad_norm": 0.10522245615720749,
+      "learning_rate": 4.92968049037552e-05,
+      "loss": 0.2516,
+      "num_input_tokens_seen": 4338600,
+      "step": 84
+    },
+    {
+      "epoch": 2.2416107382550337,
+      "grad_norm": 0.09364143013954163,
+      "learning_rate": 4.928004380675941e-05,
+      "loss": 0.2463,
+      "num_input_tokens_seen": 4385840,
+      "step": 85
+    },
+    {
+      "epoch": 2.2684563758389262,
+      "grad_norm": 0.10501237958669662,
+      "learning_rate": 4.9263088217216544e-05,
+      "loss": 0.2578,
+      "num_input_tokens_seen": 4440368,
+      "step": 86
+    },
+    {
+      "epoch": 2.295302013422819,
+      "grad_norm": 0.09559391438961029,
+      "learning_rate": 4.9245938270947435e-05,
+      "loss": 0.2369,
+      "num_input_tokens_seen": 4502040,
+      "step": 87
+    },
+    {
+      "epoch": 2.3221476510067114,
+      "grad_norm": 0.08705922961235046,
+      "learning_rate": 4.922859410532978e-05,
+      "loss": 0.3009,
+      "num_input_tokens_seen": 4563296,
+      "step": 88
+    },
+    {
+      "epoch": 2.348993288590604,
+      "grad_norm": 0.08942529559135437,
+      "learning_rate": 4.921105585929709e-05,
+      "loss": 0.211,
+      "num_input_tokens_seen": 4620344,
+      "step": 89
+    },
+    {
+      "epoch": 2.3758389261744965,
+      "grad_norm": 0.088467076420784,
+      "learning_rate": 4.9193323673337476e-05,
+      "loss": 0.2463,
+      "num_input_tokens_seen": 4675400,
+      "step": 90
+    },
+    {
+      "epoch": 2.402684563758389,
+      "grad_norm": 0.08302924036979675,
+      "learning_rate": 4.9175397689492614e-05,
+      "loss": 0.2536,
+      "num_input_tokens_seen": 4734696,
+      "step": 91
+    },
+    {
+      "epoch": 2.4295302013422817,
+      "grad_norm": 0.10511067509651184,
+      "learning_rate": 4.915727805135657e-05,
+      "loss": 0.2538,
+      "num_input_tokens_seen": 4782448,
+      "step": 92
+    },
+    {
+      "epoch": 2.4563758389261743,
+      "grad_norm": 0.09681275486946106,
+      "learning_rate": 4.9138964904074667e-05,
+      "loss": 0.2243,
+      "num_input_tokens_seen": 4830504,
+      "step": 93
+    },
+    {
+      "epoch": 2.4832214765100673,
+      "grad_norm": 0.10118114203214645,
+      "learning_rate": 4.91204583943423e-05,
+      "loss": 0.2701,
+      "num_input_tokens_seen": 4886040,
+      "step": 94
+    },
+    {
+      "epoch": 2.51006711409396,
+      "grad_norm": 0.11683424562215805,
+      "learning_rate": 4.910175867040377e-05,
+      "loss": 0.2292,
+      "num_input_tokens_seen": 4934448,
+      "step": 95
+    },
+    {
+      "epoch": 2.5369127516778525,
+      "grad_norm": 0.09783443063497543,
+      "learning_rate": 4.90828658820511e-05,
+      "loss": 0.2398,
+      "num_input_tokens_seen": 4987040,
+      "step": 96
+    },
+    {
+      "epoch": 2.563758389261745,
+      "grad_norm": 0.10438188165426254,
+      "learning_rate": 4.9063780180622845e-05,
+      "loss": 0.2355,
+      "num_input_tokens_seen": 5037360,
+      "step": 97
+    },
+    {
+      "epoch": 2.5906040268456376,
+      "grad_norm": 0.1034293919801712,
+      "learning_rate": 4.9044501719002844e-05,
+      "loss": 0.2554,
+      "num_input_tokens_seen": 5091640,
+      "step": 98
+    },
+    {
+      "epoch": 2.61744966442953,
+      "grad_norm": 0.09722857177257538,
+      "learning_rate": 4.9025030651619046e-05,
+      "loss": 0.2176,
+      "num_input_tokens_seen": 5149232,
+      "step": 99
+    },
+    {
+      "epoch": 2.6442953020134228,
+      "grad_norm": 0.1010555699467659,
+      "learning_rate": 4.9005367134442235e-05,
+      "loss": 0.2191,
+      "num_input_tokens_seen": 5196648,
+      "step": 100
+    },
+    {
+      "epoch": 2.6711409395973154,
+      "grad_norm": 0.085463747382164,
+      "learning_rate": 4.89855113249848e-05,
+      "loss": 0.2283,
+      "num_input_tokens_seen": 5261568,
+      "step": 101
+    },
+    {
+      "epoch": 2.697986577181208,
+      "grad_norm": 0.10148970782756805,
+      "learning_rate": 4.896546338229945e-05,
+      "loss": 0.234,
+      "num_input_tokens_seen": 5312104,
+      "step": 102
+    },
+    {
+      "epoch": 2.7248322147651005,
+      "grad_norm": 0.12468232959508896,
+      "learning_rate": 4.894522346697796e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 5360104,
+      "step": 103
+    },
+    {
+      "epoch": 2.751677852348993,
+      "grad_norm": 0.11668706685304642,
+      "learning_rate": 4.892479174114989e-05,
+      "loss": 0.2291,
+      "num_input_tokens_seen": 5402856,
+      "step": 104
+    },
+    {
+      "epoch": 2.778523489932886,
+      "grad_norm": 0.11586510390043259,
+      "learning_rate": 4.890416836848127e-05,
+      "loss": 0.2297,
+      "num_input_tokens_seen": 5445040,
+      "step": 105
+    },
+    {
+      "epoch": 2.8053691275167782,
+      "grad_norm": 0.09793268144130707,
+      "learning_rate": 4.888335351417331e-05,
+      "loss": 0.2271,
+      "num_input_tokens_seen": 5497368,
+      "step": 106
+    },
+    {
+      "epoch": 2.8322147651006713,
+      "grad_norm": 0.1202295795083046,
+      "learning_rate": 4.886234734496102e-05,
+      "loss": 0.261,
+      "num_input_tokens_seen": 5560720,
+      "step": 107
+    },
+    {
+      "epoch": 2.859060402684564,
+      "grad_norm": 0.10316886752843857,
+      "learning_rate": 4.884115002911197e-05,
+      "loss": 0.2532,
+      "num_input_tokens_seen": 5616592,
+      "step": 108
+    },
+    {
+      "epoch": 2.8859060402684564,
+      "grad_norm": 0.10972882062196732,
+      "learning_rate": 4.8819761736424854e-05,
+      "loss": 0.2265,
+      "num_input_tokens_seen": 5674352,
+      "step": 109
+    },
+    {
+      "epoch": 2.912751677852349,
+      "grad_norm": 0.11267542093992233,
+      "learning_rate": 4.8798182638228166e-05,
+      "loss": 0.2356,
+      "num_input_tokens_seen": 5710912,
+      "step": 110
+    },
+    {
+      "epoch": 2.9395973154362416,
+      "grad_norm": 0.11448722332715988,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.2381,
+      "num_input_tokens_seen": 5757920,
+      "step": 111
+    },
+    {
+      "epoch": 2.966442953020134,
+      "grad_norm": 0.11678655445575714,
+      "learning_rate": 4.875445271826084e-05,
+      "loss": 0.2288,
+      "num_input_tokens_seen": 5802192,
+      "step": 112
+    },
+    {
+      "epoch": 2.9932885906040267,
+      "grad_norm": 0.11252844333648682,
+      "learning_rate": 4.87323022467838e-05,
+      "loss": 0.2264,
+      "num_input_tokens_seen": 5867304,
+      "step": 113
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19352872669696808,
+      "learning_rate": 4.870996167038154e-05,
+      "loss": 0.2352,
+      "num_input_tokens_seen": 5885424,
+      "step": 114
+    },
+    {
+      "epoch": 3.0268456375838926,
+      "grad_norm": 0.1173228845000267,
+      "learning_rate": 4.868743116801074e-05,
+      "loss": 0.2164,
+      "num_input_tokens_seen": 5944528,
+      "step": 115
+    },
+    {
+      "epoch": 3.053691275167785,
+      "grad_norm": 0.11860992014408112,
+      "learning_rate": 4.866471092014945e-05,
+      "loss": 0.2329,
+      "num_input_tokens_seen": 6003480,
+      "step": 116
+    },
+    {
+      "epoch": 3.0805369127516777,
+      "grad_norm": 0.10296034812927246,
+      "learning_rate": 4.864180110879562e-05,
+      "loss": 0.2318,
+      "num_input_tokens_seen": 6059304,
+      "step": 117
+    },
+    {
+      "epoch": 3.1073825503355703,
+      "grad_norm": 0.11512338370084763,
+      "learning_rate": 4.861870191746573e-05,
+      "loss": 0.2054,
+      "num_input_tokens_seen": 6117288,
+      "step": 118
+    },
+    {
+      "epoch": 3.134228187919463,
+      "grad_norm": 0.13150866329669952,
+      "learning_rate": 4.859541353119322e-05,
+      "loss": 0.2086,
+      "num_input_tokens_seen": 6164008,
+      "step": 119
+    },
+    {
+      "epoch": 3.1610738255033555,
+      "grad_norm": 0.11846304684877396,
+      "learning_rate": 4.857193613652711e-05,
+      "loss": 0.2353,
+      "num_input_tokens_seen": 6224560,
+      "step": 120
+    },
+    {
+      "epoch": 3.1879194630872485,
+      "grad_norm": 0.12476348876953125,
+      "learning_rate": 4.854826992153038e-05,
+      "loss": 0.2295,
+      "num_input_tokens_seen": 6273248,
+      "step": 121
+    },
+    {
+      "epoch": 3.214765100671141,
+      "grad_norm": 0.11604316532611847,
+      "learning_rate": 4.8524415075778597e-05,
+      "loss": 0.1945,
+      "num_input_tokens_seen": 6327592,
+      "step": 122
+    },
+    {
+      "epoch": 3.2416107382550337,
+      "grad_norm": 0.12193804979324341,
+      "learning_rate": 4.850037179035829e-05,
+      "loss": 0.2389,
+      "num_input_tokens_seen": 6389680,
+      "step": 123
+    },
+    {
+      "epoch": 3.2684563758389262,
+      "grad_norm": 0.12192777544260025,
+      "learning_rate": 4.847614025786549e-05,
+      "loss": 0.2083,
+      "num_input_tokens_seen": 6441392,
+      "step": 124
+    },
+    {
+      "epoch": 3.295302013422819,
+      "grad_norm": 0.13284096121788025,
+      "learning_rate": 4.845172067240415e-05,
+      "loss": 0.2497,
+      "num_input_tokens_seen": 6483464,
+      "step": 125
+    },
+    {
+      "epoch": 3.3221476510067114,
+      "grad_norm": 0.10930957645177841,
+      "learning_rate": 4.842711322958459e-05,
+      "loss": 0.188,
+      "num_input_tokens_seen": 6536056,
+      "step": 126
+    },
+    {
+      "epoch": 3.348993288590604,
+      "grad_norm": 0.12303247302770615,
+      "learning_rate": 4.840231812652196e-05,
+      "loss": 0.1913,
+      "num_input_tokens_seen": 6583768,
+      "step": 127
+    },
+    {
+      "epoch": 3.3758389261744965,
+      "grad_norm": 0.12305760383605957,
+      "learning_rate": 4.837733556183463e-05,
+      "loss": 0.1926,
+      "num_input_tokens_seen": 6639048,
+      "step": 128
+    },
+    {
+      "epoch": 3.402684563758389,
+      "grad_norm": 0.13311812281608582,
+      "learning_rate": 4.8352165735642604e-05,
+      "loss": 0.2234,
+      "num_input_tokens_seen": 6691360,
+      "step": 129
+    },
+    {
+      "epoch": 3.4295302013422817,
+      "grad_norm": 0.12300640344619751,
+      "learning_rate": 4.8326808849565936e-05,
+      "loss": 0.2332,
+      "num_input_tokens_seen": 6743408,
+      "step": 130
+    },
+    {
+      "epoch": 3.4563758389261743,
+      "grad_norm": 0.1301521509885788,
+      "learning_rate": 4.830126510672309e-05,
+      "loss": 0.18,
+      "num_input_tokens_seen": 6790704,
+      "step": 131
+    },
+    {
+      "epoch": 3.4832214765100673,
+      "grad_norm": 0.1255597174167633,
+      "learning_rate": 4.827553471172935e-05,
+      "loss": 0.1964,
+      "num_input_tokens_seen": 6839200,
+      "step": 132
+    },
+    {
+      "epoch": 3.51006711409396,
+      "grad_norm": 0.13288290798664093,
+      "learning_rate": 4.824961787069511e-05,
+      "loss": 0.2116,
+      "num_input_tokens_seen": 6892832,
+      "step": 133
+    },
+    {
+      "epoch": 3.5369127516778525,
+      "grad_norm": 0.11485302448272705,
+      "learning_rate": 4.822351479122432e-05,
+      "loss": 0.2071,
+      "num_input_tokens_seen": 6949464,
+      "step": 134
+    },
+    {
+      "epoch": 3.563758389261745,
+      "grad_norm": 0.11960192024707794,
+      "learning_rate": 4.819722568241274e-05,
+      "loss": 0.175,
+      "num_input_tokens_seen": 6996480,
+      "step": 135
+    },
+    {
+      "epoch": 3.5906040268456376,
+      "grad_norm": 0.14381754398345947,
+      "learning_rate": 4.817075075484629e-05,
+      "loss": 0.237,
+      "num_input_tokens_seen": 7053720,
+      "step": 136
+    },
+    {
+      "epoch": 3.61744966442953,
+      "grad_norm": 0.1209937036037445,
+      "learning_rate": 4.8144090220599416e-05,
+      "loss": 0.2176,
+      "num_input_tokens_seen": 7111480,
+      "step": 137
+    },
+    {
+      "epoch": 3.6442953020134228,
+      "grad_norm": 0.13339534401893616,
+      "learning_rate": 4.811724429323329e-05,
+      "loss": 0.2164,
+      "num_input_tokens_seen": 7165728,
+      "step": 138
+    },
+    {
+      "epoch": 3.6711409395973154,
+      "grad_norm": 0.14351628720760345,
+      "learning_rate": 4.809021318779419e-05,
+      "loss": 0.1876,
+      "num_input_tokens_seen": 7207648,
+      "step": 139
+    },
+    {
+      "epoch": 3.697986577181208,
+      "grad_norm": 0.1557406485080719,
+      "learning_rate": 4.806299712081172e-05,
+      "loss": 0.2697,
+      "num_input_tokens_seen": 7254280,
+      "step": 140
+    },
+    {
+      "epoch": 3.7248322147651005,
+      "grad_norm": 0.14036628603935242,
+      "learning_rate": 4.8035596310297124e-05,
+      "loss": 0.1955,
+      "num_input_tokens_seen": 7297912,
+      "step": 141
+    },
+    {
+      "epoch": 3.751677852348993,
+      "grad_norm": 0.1406165212392807,
+      "learning_rate": 4.800801097574149e-05,
+      "loss": 0.2048,
+      "num_input_tokens_seen": 7343304,
+      "step": 142
+    },
+    {
+      "epoch": 3.778523489932886,
+      "grad_norm": 0.1484479159116745,
+      "learning_rate": 4.798024133811403e-05,
+      "loss": 0.2062,
+      "num_input_tokens_seen": 7391688,
+      "step": 143
+    },
+    {
+      "epoch": 3.8053691275167782,
+      "grad_norm": 0.15288512408733368,
+      "learning_rate": 4.795228761986028e-05,
+      "loss": 0.2123,
+      "num_input_tokens_seen": 7448016,
+      "step": 144
+    },
+    {
+      "epoch": 3.8322147651006713,
+      "grad_norm": 0.1407124102115631,
+      "learning_rate": 4.792415004490034e-05,
+      "loss": 0.2128,
+      "num_input_tokens_seen": 7495312,
+      "step": 145
+    },
+    {
+      "epoch": 3.859060402684564,
+      "grad_norm": 0.1452370434999466,
+      "learning_rate": 4.789582883862708e-05,
+      "loss": 0.207,
+      "num_input_tokens_seen": 7552600,
+      "step": 146
+    },
+    {
+      "epoch": 3.8859060402684564,
+      "grad_norm": 0.16543127596378326,
+      "learning_rate": 4.786732422790432e-05,
+      "loss": 0.2227,
+      "num_input_tokens_seen": 7615064,
+      "step": 147
+    },
+    {
+      "epoch": 3.912751677852349,
+      "grad_norm": 0.15252095460891724,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.2296,
+      "num_input_tokens_seen": 7671712,
+      "step": 148
+    },
+    {
+      "epoch": 3.9395973154362416,
+      "grad_norm": 0.1682525873184204,
+      "learning_rate": 4.780976570790947e-05,
+      "loss": 0.1989,
+      "num_input_tokens_seen": 7713880,
+      "step": 149
+    },
+    {
+      "epoch": 3.966442953020134,
+      "grad_norm": 0.15517935156822205,
+      "learning_rate": 4.77807122597034e-05,
+      "loss": 0.2485,
+      "num_input_tokens_seen": 7766672,
+      "step": 150
+    },
+    {
+      "epoch": 3.9932885906040267,
+      "grad_norm": 0.13144247233867645,
+      "learning_rate": 4.775147632917617e-05,
+      "loss": 0.1962,
+      "num_input_tokens_seen": 7835800,
+      "step": 151
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.3006974160671234,
+      "learning_rate": 4.7722058150518914e-05,
+      "loss": 0.2309,
+      "num_input_tokens_seen": 7847232,
+      "step": 152
+    },
+    {
+      "epoch": 4.026845637583893,
+      "grad_norm": 0.1415897011756897,
+      "learning_rate": 4.769245795938261e-05,
+      "loss": 0.2234,
+      "num_input_tokens_seen": 7894656,
+      "step": 153
+    },
+    {
+      "epoch": 4.053691275167785,
+      "grad_norm": 0.15622243285179138,
+      "learning_rate": 4.766267599287625e-05,
+      "loss": 0.1936,
+      "num_input_tokens_seen": 7957712,
+      "step": 154
+    },
+    {
+      "epoch": 4.080536912751678,
+      "grad_norm": 0.152387797832489,
+      "learning_rate": 4.7632712489564926e-05,
+      "loss": 0.1859,
+      "num_input_tokens_seen": 8005344,
+      "step": 155
+    },
+    {
+      "epoch": 4.10738255033557,
+      "grad_norm": 0.13995884358882904,
+      "learning_rate": 4.760256768946787e-05,
+      "loss": 0.1705,
+      "num_input_tokens_seen": 8065064,
+      "step": 156
+    },
+    {
+      "epoch": 4.134228187919463,
+      "grad_norm": 0.15024860203266144,
+      "learning_rate": 4.7572241834056616e-05,
+      "loss": 0.1845,
+      "num_input_tokens_seen": 8122464,
+      "step": 157
+    },
+    {
+      "epoch": 4.1610738255033555,
+      "grad_norm": 0.16085512936115265,
+      "learning_rate": 4.7541735166252986e-05,
+      "loss": 0.2019,
+      "num_input_tokens_seen": 8169408,
+      "step": 158
+    },
+    {
+      "epoch": 4.1879194630872485,
+      "grad_norm": 0.15862515568733215,
+      "learning_rate": 4.751104793042722e-05,
+      "loss": 0.2003,
+      "num_input_tokens_seen": 8226728,
+      "step": 159
+    },
+    {
+      "epoch": 4.214765100671141,
+      "grad_norm": 0.1638798713684082,
+      "learning_rate": 4.748018037239592e-05,
+      "loss": 0.1931,
+      "num_input_tokens_seen": 8285288,
+      "step": 160
+    },
+    {
+      "epoch": 4.241610738255034,
+      "grad_norm": 0.16194795072078705,
+      "learning_rate": 4.74491327394202e-05,
+      "loss": 0.2145,
+      "num_input_tokens_seen": 8329624,
+      "step": 161
+    },
+    {
+      "epoch": 4.268456375838926,
+      "grad_norm": 0.14317141473293304,
+      "learning_rate": 4.7417905280203594e-05,
+      "loss": 0.1892,
+      "num_input_tokens_seen": 8375536,
+      "step": 162
+    },
+    {
+      "epoch": 4.295302013422819,
+      "grad_norm": 0.174782857298851,
+      "learning_rate": 4.7386498244890146e-05,
+      "loss": 0.206,
+      "num_input_tokens_seen": 8433088,
+      "step": 163
+    },
+    {
+      "epoch": 4.322147651006711,
+      "grad_norm": 0.1592899113893509,
+      "learning_rate": 4.735491188506237e-05,
+      "loss": 0.1692,
+      "num_input_tokens_seen": 8480984,
+      "step": 164
+    },
+    {
+      "epoch": 4.348993288590604,
+      "grad_norm": 0.17513258755207062,
+      "learning_rate": 4.732314645373921e-05,
+      "loss": 0.2201,
+      "num_input_tokens_seen": 8532168,
+      "step": 165
+    },
+    {
+      "epoch": 4.375838926174497,
+      "grad_norm": 0.1629508137702942,
+      "learning_rate": 4.7291202205374086e-05,
+      "loss": 0.1763,
+      "num_input_tokens_seen": 8579384,
+      "step": 166
+    },
+    {
+      "epoch": 4.402684563758389,
+      "grad_norm": 0.15738122165203094,
+      "learning_rate": 4.7259079395852776e-05,
+      "loss": 0.1781,
+      "num_input_tokens_seen": 8626592,
+      "step": 167
+    },
+    {
+      "epoch": 4.429530201342282,
+      "grad_norm": 0.18833334743976593,
+      "learning_rate": 4.7226778282491424e-05,
+      "loss": 0.2067,
+      "num_input_tokens_seen": 8680320,
+      "step": 168
+    },
+    {
+      "epoch": 4.456375838926174,
+      "grad_norm": 0.14375615119934082,
+      "learning_rate": 4.719429912403445e-05,
+      "loss": 0.1795,
+      "num_input_tokens_seen": 8740824,
+      "step": 169
+    },
+    {
+      "epoch": 4.483221476510067,
+      "grad_norm": 0.17458012700080872,
+      "learning_rate": 4.7161642180652464e-05,
+      "loss": 0.2021,
+      "num_input_tokens_seen": 8789312,
+      "step": 170
+    },
+    {
+      "epoch": 4.510067114093959,
+      "grad_norm": 0.17704319953918457,
+      "learning_rate": 4.712880771394024e-05,
+      "loss": 0.1916,
+      "num_input_tokens_seen": 8838400,
+      "step": 171
+    },
+    {
+      "epoch": 4.5369127516778525,
+      "grad_norm": 0.1582602709531784,
+      "learning_rate": 4.709579598691456e-05,
+      "loss": 0.1852,
+      "num_input_tokens_seen": 8883320,
+      "step": 172
+    },
+    {
+      "epoch": 4.563758389261745,
+      "grad_norm": 0.16678012907505035,
+      "learning_rate": 4.7062607264012124e-05,
+      "loss": 0.162,
+      "num_input_tokens_seen": 8931240,
+      "step": 173
+    },
+    {
+      "epoch": 4.590604026845638,
+      "grad_norm": 0.15457355976104736,
+      "learning_rate": 4.7029241811087457e-05,
+      "loss": 0.1763,
+      "num_input_tokens_seen": 8982280,
+      "step": 174
+    },
+    {
+      "epoch": 4.617449664429531,
+      "grad_norm": 0.16706790030002594,
+      "learning_rate": 4.699569989541074e-05,
+      "loss": 0.2005,
+      "num_input_tokens_seen": 9027824,
+      "step": 175
+    },
+    {
+      "epoch": 4.644295302013423,
+      "grad_norm": 0.16770173609256744,
+      "learning_rate": 4.69619817856657e-05,
+      "loss": 0.1985,
+      "num_input_tokens_seen": 9081584,
+      "step": 176
+    },
+    {
+      "epoch": 4.671140939597316,
+      "grad_norm": 0.19141702353954315,
+      "learning_rate": 4.692808775194745e-05,
+      "loss": 0.1963,
+      "num_input_tokens_seen": 9142112,
+      "step": 177
+    },
+    {
+      "epoch": 4.697986577181208,
+      "grad_norm": 0.15951097011566162,
+      "learning_rate": 4.68940180657603e-05,
+      "loss": 0.1691,
+      "num_input_tokens_seen": 9190280,
+      "step": 178
+    },
+    {
+      "epoch": 4.724832214765101,
+      "grad_norm": 0.16681668162345886,
+      "learning_rate": 4.685977300001565e-05,
+      "loss": 0.1896,
+      "num_input_tokens_seen": 9240592,
+      "step": 179
+    },
+    {
+      "epoch": 4.751677852348993,
+      "grad_norm": 0.16679206490516663,
+      "learning_rate": 4.6825352829029705e-05,
+      "loss": 0.1724,
+      "num_input_tokens_seen": 9294464,
+      "step": 180
+    },
+    {
+      "epoch": 4.778523489932886,
+      "grad_norm": 0.16181506216526031,
+      "learning_rate": 4.679075782852137e-05,
+      "loss": 0.1698,
+      "num_input_tokens_seen": 9349552,
+      "step": 181
+    },
+    {
+      "epoch": 4.805369127516778,
+      "grad_norm": 0.16370564699172974,
+      "learning_rate": 4.675598827560998e-05,
+      "loss": 0.2092,
+      "num_input_tokens_seen": 9409136,
+      "step": 182
+    },
+    {
+      "epoch": 4.832214765100671,
+      "grad_norm": 0.18401412665843964,
+      "learning_rate": 4.67210444488131e-05,
+      "loss": 0.1763,
+      "num_input_tokens_seen": 9444096,
+      "step": 183
+    },
+    {
+      "epoch": 4.859060402684563,
+      "grad_norm": 0.21891450881958008,
+      "learning_rate": 4.668592662804432e-05,
+      "loss": 0.219,
+      "num_input_tokens_seen": 9508552,
+      "step": 184
+    },
+    {
+      "epoch": 4.885906040268456,
+      "grad_norm": 0.19035810232162476,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.1856,
+      "num_input_tokens_seen": 9564224,
+      "step": 185
+    },
+    {
+      "epoch": 4.912751677852349,
+      "grad_norm": 0.16957947611808777,
+      "learning_rate": 4.661517013121189e-05,
+      "loss": 0.1747,
+      "num_input_tokens_seen": 9620384,
+      "step": 186
+    },
+    {
+      "epoch": 4.939597315436242,
+      "grad_norm": 0.16003385186195374,
+      "learning_rate": 4.657953202193516e-05,
+      "loss": 0.1685,
+      "num_input_tokens_seen": 9679824,
+      "step": 187
+    },
+    {
+      "epoch": 4.966442953020135,
+      "grad_norm": 0.1679641157388687,
+      "learning_rate": 4.654372105225583e-05,
+      "loss": 0.1636,
+      "num_input_tokens_seen": 9732328,
+      "step": 188
+    },
+    {
+      "epoch": 4.993288590604027,
+      "grad_norm": 0.15429595112800598,
+      "learning_rate": 4.650773750903363e-05,
+      "loss": 0.1429,
+      "num_input_tokens_seen": 9793456,
+      "step": 189
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.30234482884407043,
+      "learning_rate": 4.647158168051066e-05,
+      "loss": 0.1757,
+      "num_input_tokens_seen": 9809040,
+      "step": 190
+    },
+    {
+      "epoch": 5.026845637583893,
+      "grad_norm": 0.19254004955291748,
+      "learning_rate": 4.6435253856309094e-05,
+      "loss": 0.1711,
+      "num_input_tokens_seen": 9863696,
+      "step": 191
+    },
+    {
+      "epoch": 5.053691275167785,
+      "grad_norm": 0.16591961681842804,
+      "learning_rate": 4.639875432742886e-05,
+      "loss": 0.156,
+      "num_input_tokens_seen": 9906912,
+      "step": 192
+    },
+    {
+      "epoch": 5.080536912751678,
+      "grad_norm": 0.18133562803268433,
+      "learning_rate": 4.636208338624533e-05,
+      "loss": 0.17,
+      "num_input_tokens_seen": 9950056,
+      "step": 193
+    },
+    {
+      "epoch": 5.10738255033557,
+      "grad_norm": 0.19608290493488312,
+      "learning_rate": 4.6325241326506915e-05,
+      "loss": 0.1882,
+      "num_input_tokens_seen": 10001296,
+      "step": 194
+    },
+    {
+      "epoch": 5.134228187919463,
+      "grad_norm": 0.2348538637161255,
+      "learning_rate": 4.628822844333278e-05,
+      "loss": 0.1564,
+      "num_input_tokens_seen": 10052888,
+      "step": 195
+    },
+    {
+      "epoch": 5.1610738255033555,
+      "grad_norm": 0.17895568907260895,
+      "learning_rate": 4.625104503321045e-05,
+      "loss": 0.1606,
+      "num_input_tokens_seen": 10109912,
+      "step": 196
+    },
+    {
+      "epoch": 5.1879194630872485,
+      "grad_norm": 0.1882435381412506,
+      "learning_rate": 4.621369139399341e-05,
+      "loss": 0.1722,
+      "num_input_tokens_seen": 10151104,
+      "step": 197
+    },
+    {
+      "epoch": 5.214765100671141,
+      "grad_norm": 0.18267786502838135,
+      "learning_rate": 4.6176167824898773e-05,
+      "loss": 0.1679,
+      "num_input_tokens_seen": 10196304,
+      "step": 198
+    },
+    {
+      "epoch": 5.241610738255034,
+      "grad_norm": 0.16710643470287323,
+      "learning_rate": 4.613847462650486e-05,
+      "loss": 0.1548,
+      "num_input_tokens_seen": 10255152,
+      "step": 199
+    },
+    {
+      "epoch": 5.268456375838926,
+      "grad_norm": 0.19108474254608154,
+      "learning_rate": 4.6100612100748765e-05,
+      "loss": 0.166,
+      "num_input_tokens_seen": 10294912,
+      "step": 200
+    },
+    {
+      "epoch": 5.295302013422819,
+      "grad_norm": 0.16066554188728333,
+      "learning_rate": 4.606258055092397e-05,
+      "loss": 0.1648,
+      "num_input_tokens_seen": 10357248,
+      "step": 201
+    },
+    {
+      "epoch": 5.322147651006711,
+      "grad_norm": 0.18054331839084625,
+      "learning_rate": 4.602438028167792e-05,
+      "loss": 0.1419,
+      "num_input_tokens_seen": 10411456,
+      "step": 202
+    },
+    {
+      "epoch": 5.348993288590604,
+      "grad_norm": 0.22617101669311523,
+      "learning_rate": 4.5986011599009544e-05,
+      "loss": 0.1935,
+      "num_input_tokens_seen": 10462080,
+      "step": 203
+    },
+    {
+      "epoch": 5.375838926174497,
+      "grad_norm": 0.1666952520608902,
+      "learning_rate": 4.594747481026684e-05,
+      "loss": 0.1449,
+      "num_input_tokens_seen": 10530312,
+      "step": 204
+    },
+    {
+      "epoch": 5.402684563758389,
+      "grad_norm": 0.16662774980068207,
+      "learning_rate": 4.59087702241444e-05,
+      "loss": 0.1548,
+      "num_input_tokens_seen": 10593232,
+      "step": 205
+    },
+    {
+      "epoch": 5.429530201342282,
+      "grad_norm": 0.1743718981742859,
+      "learning_rate": 4.586989815068095e-05,
+      "loss": 0.2084,
+      "num_input_tokens_seen": 10661464,
+      "step": 206
+    },
+    {
+      "epoch": 5.456375838926174,
+      "grad_norm": 0.191987544298172,
+      "learning_rate": 4.5830858901256826e-05,
+      "loss": 0.1527,
+      "num_input_tokens_seen": 10704912,
+      "step": 207
+    },
+    {
+      "epoch": 5.483221476510067,
+      "grad_norm": 0.19640536606311798,
+      "learning_rate": 4.579165278859152e-05,
+      "loss": 0.1515,
+      "num_input_tokens_seen": 10750792,
+      "step": 208
+    },
+    {
+      "epoch": 5.510067114093959,
+      "grad_norm": 0.22779090702533722,
+      "learning_rate": 4.575228012674118e-05,
+      "loss": 0.155,
+      "num_input_tokens_seen": 10818288,
+      "step": 209
+    },
+    {
+      "epoch": 5.5369127516778525,
+      "grad_norm": 0.18574051558971405,
+      "learning_rate": 4.571274123109606e-05,
+      "loss": 0.1514,
+      "num_input_tokens_seen": 10871488,
+      "step": 210
+    },
+    {
+      "epoch": 5.563758389261745,
+      "grad_norm": 0.20689000189304352,
+      "learning_rate": 4.5673036418378006e-05,
+      "loss": 0.1645,
+      "num_input_tokens_seen": 10925024,
+      "step": 211
+    },
+    {
+      "epoch": 5.590604026845638,
+      "grad_norm": 0.20517326891422272,
+      "learning_rate": 4.563316600663795e-05,
+      "loss": 0.1532,
+      "num_input_tokens_seen": 10982200,
+      "step": 212
+    },
+    {
+      "epoch": 5.617449664429531,
+      "grad_norm": 0.19169899821281433,
+      "learning_rate": 4.559313031525331e-05,
+      "loss": 0.1754,
+      "num_input_tokens_seen": 11029976,
+      "step": 213
+    },
+    {
+      "epoch": 5.644295302013423,
+      "grad_norm": 0.19880560040473938,
+      "learning_rate": 4.555292966492547e-05,
+      "loss": 0.1611,
+      "num_input_tokens_seen": 11085192,
+      "step": 214
+    },
+    {
+      "epoch": 5.671140939597316,
+      "grad_norm": 0.2045927792787552,
+      "learning_rate": 4.551256437767719e-05,
+      "loss": 0.1856,
+      "num_input_tokens_seen": 11132072,
+      "step": 215
+    },
+    {
+      "epoch": 5.697986577181208,
+      "grad_norm": 0.18255843222141266,
+      "learning_rate": 4.547203477685005e-05,
+      "loss": 0.1658,
+      "num_input_tokens_seen": 11195808,
+      "step": 216
+    },
+    {
+      "epoch": 5.724832214765101,
+      "grad_norm": 0.19551897048950195,
+      "learning_rate": 4.543134118710184e-05,
+      "loss": 0.1649,
+      "num_input_tokens_seen": 11244688,
+      "step": 217
+    },
+    {
+      "epoch": 5.751677852348993,
+      "grad_norm": 0.19608667492866516,
+      "learning_rate": 4.539048393440395e-05,
+      "loss": 0.1582,
+      "num_input_tokens_seen": 11298888,
+      "step": 218
+    },
+    {
+      "epoch": 5.778523489932886,
+      "grad_norm": 0.2286413460969925,
+      "learning_rate": 4.534946334603879e-05,
+      "loss": 0.1624,
+      "num_input_tokens_seen": 11345304,
+      "step": 219
+    },
+    {
+      "epoch": 5.805369127516778,
+      "grad_norm": 0.21048720180988312,
+      "learning_rate": 4.530827975059715e-05,
+      "loss": 0.1548,
+      "num_input_tokens_seen": 11387752,
+      "step": 220
+    },
+    {
+      "epoch": 5.832214765100671,
+      "grad_norm": 0.1970525085926056,
+      "learning_rate": 4.526693347797557e-05,
+      "loss": 0.1478,
+      "num_input_tokens_seen": 11432728,
+      "step": 221
+    },
+    {
+      "epoch": 5.859060402684563,
+      "grad_norm": 0.18459273874759674,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.1313,
+      "num_input_tokens_seen": 11493064,
+      "step": 222
+    },
+    {
+      "epoch": 5.885906040268456,
+      "grad_norm": 0.22195135056972504,
+      "learning_rate": 4.518375422729161e-05,
+      "loss": 0.1719,
+      "num_input_tokens_seen": 11542392,
+      "step": 223
+    },
+    {
+      "epoch": 5.912751677852349,
+      "grad_norm": 0.21980145573616028,
+      "learning_rate": 4.5141921915527216e-05,
+      "loss": 0.1587,
+      "num_input_tokens_seen": 11596408,
+      "step": 224
+    },
+    {
+      "epoch": 5.939597315436242,
+      "grad_norm": 0.21877101063728333,
+      "learning_rate": 4.5099928259173516e-05,
+      "loss": 0.1751,
+      "num_input_tokens_seen": 11657288,
+      "step": 225
+    },
+    {
+      "epoch": 5.966442953020135,
+      "grad_norm": 0.21569234132766724,
+      "learning_rate": 4.505777359461595e-05,
+      "loss": 0.1532,
+      "num_input_tokens_seen": 11714680,
+      "step": 226
+    },
+    {
+      "epoch": 5.993288590604027,
+      "grad_norm": 0.2067164033651352,
+      "learning_rate": 4.50154582595297e-05,
+      "loss": 0.1638,
+      "num_input_tokens_seen": 11751840,
+      "step": 227
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.31630751490592957,
+      "learning_rate": 4.497298259287696e-05,
+      "loss": 0.118,
+      "num_input_tokens_seen": 11770848,
+      "step": 228
+    },
+    {
+      "epoch": 6.026845637583893,
+      "grad_norm": 0.2094467580318451,
+      "learning_rate": 4.493034693490427e-05,
+      "loss": 0.1428,
+      "num_input_tokens_seen": 11821848,
+      "step": 229
+    },
+    {
+      "epoch": 6.053691275167785,
+      "grad_norm": 0.20361250638961792,
+      "learning_rate": 4.488755162713975e-05,
+      "loss": 0.1504,
+      "num_input_tokens_seen": 11869152,
+      "step": 230
+    },
+    {
+      "epoch": 6.080536912751678,
+      "grad_norm": 0.22751058638095856,
+      "learning_rate": 4.484459701239038e-05,
+      "loss": 0.161,
+      "num_input_tokens_seen": 11917464,
+      "step": 231
+    },
+    {
+      "epoch": 6.10738255033557,
+      "grad_norm": 0.21245698630809784,
+      "learning_rate": 4.480148343473923e-05,
+      "loss": 0.1354,
+      "num_input_tokens_seen": 11962184,
+      "step": 232
+    },
+    {
+      "epoch": 6.134228187919463,
+      "grad_norm": 0.2415906935930252,
+      "learning_rate": 4.475821123954275e-05,
+      "loss": 0.1328,
+      "num_input_tokens_seen": 12005088,
+      "step": 233
+    },
+    {
+      "epoch": 6.1610738255033555,
+      "grad_norm": 0.22683894634246826,
+      "learning_rate": 4.471478077342798e-05,
+      "loss": 0.1532,
+      "num_input_tokens_seen": 12058808,
+      "step": 234
+    },
+    {
+      "epoch": 6.1879194630872485,
+      "grad_norm": 0.22128812968730927,
+      "learning_rate": 4.467119238428975e-05,
+      "loss": 0.1316,
+      "num_input_tokens_seen": 12126248,
+      "step": 235
+    },
+    {
+      "epoch": 6.214765100671141,
+      "grad_norm": 0.19066843390464783,
+      "learning_rate": 4.4627446421287935e-05,
+      "loss": 0.1279,
+      "num_input_tokens_seen": 12186960,
+      "step": 236
+    },
+    {
+      "epoch": 6.241610738255034,
+      "grad_norm": 0.21822784841060638,
+      "learning_rate": 4.4583543234844616e-05,
+      "loss": 0.1389,
+      "num_input_tokens_seen": 12246416,
+      "step": 237
+    },
+    {
+      "epoch": 6.268456375838926,
+      "grad_norm": 0.3152228593826294,
+      "learning_rate": 4.4539483176641304e-05,
+      "loss": 0.1439,
+      "num_input_tokens_seen": 12301360,
+      "step": 238
+    },
+    {
+      "epoch": 6.295302013422819,
+      "grad_norm": 0.2345726042985916,
+      "learning_rate": 4.4495266599616136e-05,
+      "loss": 0.1386,
+      "num_input_tokens_seen": 12347960,
+      "step": 239
+    },
+    {
+      "epoch": 6.322147651006711,
+      "grad_norm": 0.27413222193717957,
+      "learning_rate": 4.445089385796099e-05,
+      "loss": 0.1562,
+      "num_input_tokens_seen": 12399640,
+      "step": 240
+    },
+    {
+      "epoch": 6.348993288590604,
+      "grad_norm": 0.21653778851032257,
+      "learning_rate": 4.4406365307118703e-05,
+      "loss": 0.1364,
+      "num_input_tokens_seen": 12451256,
+      "step": 241
+    },
+    {
+      "epoch": 6.375838926174497,
+      "grad_norm": 0.21994851529598236,
+      "learning_rate": 4.4361681303780195e-05,
+      "loss": 0.1404,
+      "num_input_tokens_seen": 12497184,
+      "step": 242
+    },
+    {
+      "epoch": 6.402684563758389,
+      "grad_norm": 0.20164069533348083,
+      "learning_rate": 4.431684220588163e-05,
+      "loss": 0.1622,
+      "num_input_tokens_seen": 12551512,
+      "step": 243
+    },
+    {
+      "epoch": 6.429530201342282,
+      "grad_norm": 0.23192667961120605,
+      "learning_rate": 4.427184837260153e-05,
+      "loss": 0.1497,
+      "num_input_tokens_seen": 12595808,
+      "step": 244
+    },
+    {
+      "epoch": 6.456375838926174,
+      "grad_norm": 0.22512899339199066,
+      "learning_rate": 4.422670016435792e-05,
+      "loss": 0.1504,
+      "num_input_tokens_seen": 12649504,
+      "step": 245
+    },
+    {
+      "epoch": 6.483221476510067,
+      "grad_norm": 0.2125946432352066,
+      "learning_rate": 4.418139794280541e-05,
+      "loss": 0.129,
+      "num_input_tokens_seen": 12694312,
+      "step": 246
+    },
+    {
+      "epoch": 6.510067114093959,
+      "grad_norm": 0.2329980880022049,
+      "learning_rate": 4.413594207083234e-05,
+      "loss": 0.1363,
+      "num_input_tokens_seen": 12741872,
+      "step": 247
+    },
+    {
+      "epoch": 6.5369127516778525,
+      "grad_norm": 0.23576146364212036,
+      "learning_rate": 4.409033291255782e-05,
+      "loss": 0.1325,
+      "num_input_tokens_seen": 12799032,
+      "step": 248
+    },
+    {
+      "epoch": 6.563758389261745,
+      "grad_norm": 0.3069142997264862,
+      "learning_rate": 4.404457083332886e-05,
+      "loss": 0.1501,
+      "num_input_tokens_seen": 12860432,
+      "step": 249
+    },
+    {
+      "epoch": 6.590604026845638,
+      "grad_norm": 0.24110864102840424,
+      "learning_rate": 4.3998656199717435e-05,
+      "loss": 0.1375,
+      "num_input_tokens_seen": 12906592,
+      "step": 250
+    },
+    {
+      "epoch": 6.617449664429531,
+      "grad_norm": 0.2534135580062866,
+      "learning_rate": 4.395258937951753e-05,
+      "loss": 0.1387,
+      "num_input_tokens_seen": 12966808,
+      "step": 251
+    },
+    {
+      "epoch": 6.644295302013423,
+      "grad_norm": 0.20937450230121613,
+      "learning_rate": 4.3906370741742186e-05,
+      "loss": 0.1627,
+      "num_input_tokens_seen": 13026504,
+      "step": 252
+    },
+    {
+      "epoch": 6.671140939597316,
+      "grad_norm": 0.2298954874277115,
+      "learning_rate": 4.386000065662059e-05,
+      "loss": 0.1509,
+      "num_input_tokens_seen": 13070176,
+      "step": 253
+    },
+    {
+      "epoch": 6.697986577181208,
+      "grad_norm": 0.22058549523353577,
+      "learning_rate": 4.381347949559506e-05,
+      "loss": 0.1298,
+      "num_input_tokens_seen": 13126104,
+      "step": 254
+    },
+    {
+      "epoch": 6.724832214765101,
+      "grad_norm": 0.22921989858150482,
+      "learning_rate": 4.3766807631318106e-05,
+      "loss": 0.1396,
+      "num_input_tokens_seen": 13178312,
+      "step": 255
+    },
+    {
+      "epoch": 6.751677852348993,
+      "grad_norm": 0.20291879773139954,
+      "learning_rate": 4.371998543764943e-05,
+      "loss": 0.1206,
+      "num_input_tokens_seen": 13236216,
+      "step": 256
+    },
+    {
+      "epoch": 6.778523489932886,
+      "grad_norm": 0.1957395225763321,
+      "learning_rate": 4.367301328965291e-05,
+      "loss": 0.1168,
+      "num_input_tokens_seen": 13291752,
+      "step": 257
+    },
+    {
+      "epoch": 6.805369127516778,
+      "grad_norm": 0.241806298494339,
+      "learning_rate": 4.3625891563593626e-05,
+      "loss": 0.1435,
+      "num_input_tokens_seen": 13349872,
+      "step": 258
+    },
+    {
+      "epoch": 6.832214765100671,
+      "grad_norm": 0.2894677519798279,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 0.1216,
+      "num_input_tokens_seen": 13406328,
+      "step": 259
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1110,
+  "num_input_tokens_seen": 13406328,
+  "num_train_epochs": 30,
+  "save_steps": 37,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1309802532676567e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-296/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-296/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-296/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42743fafdf4a7ef74e25627697921cb3ba466388ddc69115845c18e5db161c5e
+size 275341720

checkpoint-296/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
+}

checkpoint-296/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3df7dc49d894f4365beb67b537292793540c4cba0e73580a0682cdad27c8bb
+size 551070514

checkpoint-296/special_tokens_map.json

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

checkpoint-296/tokenizer.json

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

checkpoint-296/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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 12000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-296/trainer_state.json

@@ -0,0 +1,2401 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.805369127516778,
+  "eval_steps": 500,
+  "global_step": 296,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.026845637583892617,
+      "grad_norm": 0.04068412259221077,
+      "learning_rate": 4.9999899870162604e-05,
+      "loss": 0.5189,
+      "num_input_tokens_seen": 58440,
+      "step": 1
+    },
+    {
+      "epoch": 0.053691275167785234,
+      "grad_norm": 0.03802767023444176,
+      "learning_rate": 4.999959948145249e-05,
+      "loss": 0.5061,
+      "num_input_tokens_seen": 112800,
+      "step": 2
+    },
+    {
+      "epoch": 0.08053691275167785,
+      "grad_norm": 0.0524083748459816,
+      "learning_rate": 4.999909883627587e-05,
+      "loss": 0.5956,
+      "num_input_tokens_seen": 156704,
+      "step": 3
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 0.050608448684215546,
+      "learning_rate": 4.999839793864313e-05,
+      "loss": 0.5222,
+      "num_input_tokens_seen": 213952,
+      "step": 4
+    },
+    {
+      "epoch": 0.1342281879194631,
+      "grad_norm": 0.04771890118718147,
+      "learning_rate": 4.9997496794168726e-05,
+      "loss": 0.4761,
+      "num_input_tokens_seen": 266920,
+      "step": 5
+    },
+    {
+      "epoch": 0.1610738255033557,
+      "grad_norm": 0.05538628622889519,
+      "learning_rate": 4.999639541007116e-05,
+      "loss": 0.5221,
+      "num_input_tokens_seen": 313560,
+      "step": 6
+    },
+    {
+      "epoch": 0.18791946308724833,
+      "grad_norm": 0.053944796323776245,
+      "learning_rate": 4.999509379517297e-05,
+      "loss": 0.4738,
+      "num_input_tokens_seen": 349544,
+      "step": 7
+    },
+    {
+      "epoch": 0.21476510067114093,
+      "grad_norm": 0.05679492652416229,
+      "learning_rate": 4.9993591959900566e-05,
+      "loss": 0.5576,
+      "num_input_tokens_seen": 397952,
+      "step": 8
+    },
+    {
+      "epoch": 0.24161073825503357,
+      "grad_norm": 0.05358556658029556,
+      "learning_rate": 4.999188991628425e-05,
+      "loss": 0.4803,
+      "num_input_tokens_seen": 452568,
+      "step": 9
+    },
+    {
+      "epoch": 0.2684563758389262,
+      "grad_norm": 0.05667557194828987,
+      "learning_rate": 4.998998767795805e-05,
+      "loss": 0.4735,
+      "num_input_tokens_seen": 494400,
+      "step": 10
+    },
+    {
+      "epoch": 0.2953020134228188,
+      "grad_norm": 0.048348862677812576,
+      "learning_rate": 4.998788526015961e-05,
+      "loss": 0.5054,
+      "num_input_tokens_seen": 569352,
+      "step": 11
+    },
+    {
+      "epoch": 0.3221476510067114,
+      "grad_norm": 0.055022645741701126,
+      "learning_rate": 4.998558267973014e-05,
+      "loss": 0.494,
+      "num_input_tokens_seen": 623680,
+      "step": 12
+    },
+    {
+      "epoch": 0.348993288590604,
+      "grad_norm": 0.05279555916786194,
+      "learning_rate": 4.998307995511418e-05,
+      "loss": 0.4411,
+      "num_input_tokens_seen": 675784,
+      "step": 13
+    },
+    {
+      "epoch": 0.37583892617449666,
+      "grad_norm": 0.06557705253362656,
+      "learning_rate": 4.998037710635952e-05,
+      "loss": 0.5778,
+      "num_input_tokens_seen": 728120,
+      "step": 14
+    },
+    {
+      "epoch": 0.40268456375838924,
+      "grad_norm": 0.06649675220251083,
+      "learning_rate": 4.9977474155117045e-05,
+      "loss": 0.5217,
+      "num_input_tokens_seen": 780392,
+      "step": 15
+    },
+    {
+      "epoch": 0.42953020134228187,
+      "grad_norm": 0.05616322159767151,
+      "learning_rate": 4.997437112464049e-05,
+      "loss": 0.4175,
+      "num_input_tokens_seen": 841192,
+      "step": 16
+    },
+    {
+      "epoch": 0.4563758389261745,
+      "grad_norm": 0.07165056467056274,
+      "learning_rate": 4.997106803978636e-05,
+      "loss": 0.5109,
+      "num_input_tokens_seen": 899368,
+      "step": 17
+    },
+    {
+      "epoch": 0.48322147651006714,
+      "grad_norm": 0.06656442582607269,
+      "learning_rate": 4.996756492701362e-05,
+      "loss": 0.4066,
+      "num_input_tokens_seen": 944400,
+      "step": 18
+    },
+    {
+      "epoch": 0.5100671140939598,
+      "grad_norm": 0.0628059059381485,
+      "learning_rate": 4.996386181438357e-05,
+      "loss": 0.4501,
+      "num_input_tokens_seen": 997024,
+      "step": 19
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 0.06418219953775406,
+      "learning_rate": 4.995995873155958e-05,
+      "loss": 0.4632,
+      "num_input_tokens_seen": 1057264,
+      "step": 20
+    },
+    {
+      "epoch": 0.5637583892617449,
+      "grad_norm": 0.08489955216646194,
+      "learning_rate": 4.9955855709806845e-05,
+      "loss": 0.4224,
+      "num_input_tokens_seen": 1094144,
+      "step": 21
+    },
+    {
+      "epoch": 0.5906040268456376,
+      "grad_norm": 0.06560485810041428,
+      "learning_rate": 4.9951552781992154e-05,
+      "loss": 0.4084,
+      "num_input_tokens_seen": 1144376,
+      "step": 22
+    },
+    {
+      "epoch": 0.6174496644295302,
+      "grad_norm": 0.05338270589709282,
+      "learning_rate": 4.9947049982583625e-05,
+      "loss": 0.3925,
+      "num_input_tokens_seen": 1206272,
+      "step": 23
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 0.06893228739500046,
+      "learning_rate": 4.994234734765043e-05,
+      "loss": 0.3666,
+      "num_input_tokens_seen": 1252464,
+      "step": 24
+    },
+    {
+      "epoch": 0.6711409395973155,
+      "grad_norm": 0.07986386865377426,
+      "learning_rate": 4.99374449148625e-05,
+      "loss": 0.4105,
+      "num_input_tokens_seen": 1295560,
+      "step": 25
+    },
+    {
+      "epoch": 0.697986577181208,
+      "grad_norm": 0.0721018984913826,
+      "learning_rate": 4.99323427234902e-05,
+      "loss": 0.3965,
+      "num_input_tokens_seen": 1356792,
+      "step": 26
+    },
+    {
+      "epoch": 0.7248322147651006,
+      "grad_norm": 0.08186662942171097,
+      "learning_rate": 4.992704081440407e-05,
+      "loss": 0.3867,
+      "num_input_tokens_seen": 1408568,
+      "step": 27
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 0.07936503738164902,
+      "learning_rate": 4.992153923007446e-05,
+      "loss": 0.4272,
+      "num_input_tokens_seen": 1465984,
+      "step": 28
+    },
+    {
+      "epoch": 0.7785234899328859,
+      "grad_norm": 0.0778949186205864,
+      "learning_rate": 4.9915838014571174e-05,
+      "loss": 0.3499,
+      "num_input_tokens_seen": 1522568,
+      "step": 29
+    },
+    {
+      "epoch": 0.8053691275167785,
+      "grad_norm": 0.07632329314947128,
+      "learning_rate": 4.9909937213563165e-05,
+      "loss": 0.3536,
+      "num_input_tokens_seen": 1576592,
+      "step": 30
+    },
+    {
+      "epoch": 0.8322147651006712,
+      "grad_norm": 0.0791730061173439,
+      "learning_rate": 4.9903836874318135e-05,
+      "loss": 0.3416,
+      "num_input_tokens_seen": 1625336,
+      "step": 31
+    },
+    {
+      "epoch": 0.8590604026845637,
+      "grad_norm": 0.08963429927825928,
+      "learning_rate": 4.9897537045702146e-05,
+      "loss": 0.3559,
+      "num_input_tokens_seen": 1668736,
+      "step": 32
+    },
+    {
+      "epoch": 0.8859060402684564,
+      "grad_norm": 0.06969798356294632,
+      "learning_rate": 4.989103777817928e-05,
+      "loss": 0.358,
+      "num_input_tokens_seen": 1725096,
+      "step": 33
+    },
+    {
+      "epoch": 0.912751677852349,
+      "grad_norm": 0.09034521877765656,
+      "learning_rate": 4.988433912381117e-05,
+      "loss": 0.354,
+      "num_input_tokens_seen": 1768400,
+      "step": 34
+    },
+    {
+      "epoch": 0.9395973154362416,
+      "grad_norm": 0.07854894548654556,
+      "learning_rate": 4.987744113625665e-05,
+      "loss": 0.3553,
+      "num_input_tokens_seen": 1829224,
+      "step": 35
+    },
+    {
+      "epoch": 0.9664429530201343,
+      "grad_norm": 0.06981746852397919,
+      "learning_rate": 4.9870343870771256e-05,
+      "loss": 0.3651,
+      "num_input_tokens_seen": 1895440,
+      "step": 36
+    },
+    {
+      "epoch": 0.9932885906040269,
+      "grad_norm": 1.1971335411071777,
+      "learning_rate": 4.9863047384206835e-05,
+      "loss": 0.3117,
+      "num_input_tokens_seen": 1948776,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13761547207832336,
+      "learning_rate": 4.985555173501106e-05,
+      "loss": 0.3247,
+      "num_input_tokens_seen": 1961808,
+      "step": 38
+    },
+    {
+      "epoch": 1.0268456375838926,
+      "grad_norm": 0.08985067158937454,
+      "learning_rate": 4.9847856983226996e-05,
+      "loss": 0.3328,
+      "num_input_tokens_seen": 2020584,
+      "step": 39
+    },
+    {
+      "epoch": 1.0536912751677852,
+      "grad_norm": 0.08735290169715881,
+      "learning_rate": 4.9839963190492576e-05,
+      "loss": 0.3809,
+      "num_input_tokens_seen": 2077264,
+      "step": 40
+    },
+    {
+      "epoch": 1.0805369127516777,
+      "grad_norm": 0.08123548328876495,
+      "learning_rate": 4.9831870420040126e-05,
+      "loss": 0.296,
+      "num_input_tokens_seen": 2117808,
+      "step": 41
+    },
+    {
+      "epoch": 1.1073825503355705,
+      "grad_norm": 0.09133706986904144,
+      "learning_rate": 4.982357873669589e-05,
+      "loss": 0.3045,
+      "num_input_tokens_seen": 2157928,
+      "step": 42
+    },
+    {
+      "epoch": 1.1342281879194631,
+      "grad_norm": 0.07161358743906021,
+      "learning_rate": 4.981508820687943e-05,
+      "loss": 0.3037,
+      "num_input_tokens_seen": 2215144,
+      "step": 43
+    },
+    {
+      "epoch": 1.1610738255033557,
+      "grad_norm": 0.07848912477493286,
+      "learning_rate": 4.9806398898603206e-05,
+      "loss": 0.308,
+      "num_input_tokens_seen": 2268776,
+      "step": 44
+    },
+    {
+      "epoch": 1.1879194630872483,
+      "grad_norm": 0.07580725848674774,
+      "learning_rate": 4.979751088147192e-05,
+      "loss": 0.3095,
+      "num_input_tokens_seen": 2316136,
+      "step": 45
+    },
+    {
+      "epoch": 1.2147651006711409,
+      "grad_norm": 0.13087698817253113,
+      "learning_rate": 4.978842422668204e-05,
+      "loss": 0.3144,
+      "num_input_tokens_seen": 2370888,
+      "step": 46
+    },
+    {
+      "epoch": 1.2416107382550337,
+      "grad_norm": 0.07428968697786331,
+      "learning_rate": 4.9779139007021184e-05,
+      "loss": 0.3084,
+      "num_input_tokens_seen": 2426656,
+      "step": 47
+    },
+    {
+      "epoch": 1.2684563758389262,
+      "grad_norm": 0.08130094408988953,
+      "learning_rate": 4.9769655296867554e-05,
+      "loss": 0.2861,
+      "num_input_tokens_seen": 2471944,
+      "step": 48
+    },
+    {
+      "epoch": 1.2953020134228188,
+      "grad_norm": 0.16188324987888336,
+      "learning_rate": 4.9759973172189334e-05,
+      "loss": 0.3136,
+      "num_input_tokens_seen": 2539888,
+      "step": 49
+    },
+    {
+      "epoch": 1.3221476510067114,
+      "grad_norm": 0.08185111731290817,
+      "learning_rate": 4.975009271054409e-05,
+      "loss": 0.26,
+      "num_input_tokens_seen": 2581936,
+      "step": 50
+    },
+    {
+      "epoch": 1.348993288590604,
+      "grad_norm": 0.07140379399061203,
+      "learning_rate": 4.974001399107816e-05,
+      "loss": 0.3178,
+      "num_input_tokens_seen": 2647016,
+      "step": 51
+    },
+    {
+      "epoch": 1.3758389261744965,
+      "grad_norm": 0.08086609840393066,
+      "learning_rate": 4.972973709452597e-05,
+      "loss": 0.2853,
+      "num_input_tokens_seen": 2694512,
+      "step": 52
+    },
+    {
+      "epoch": 1.4026845637583891,
+      "grad_norm": 0.08030746877193451,
+      "learning_rate": 4.971926210320944e-05,
+      "loss": 0.3009,
+      "num_input_tokens_seen": 2735672,
+      "step": 53
+    },
+    {
+      "epoch": 1.429530201342282,
+      "grad_norm": 0.07996731996536255,
+      "learning_rate": 4.9708589101037306e-05,
+      "loss": 0.2967,
+      "num_input_tokens_seen": 2789104,
+      "step": 54
+    },
+    {
+      "epoch": 1.4563758389261745,
+      "grad_norm": 0.0722445398569107,
+      "learning_rate": 4.969771817350445e-05,
+      "loss": 0.2741,
+      "num_input_tokens_seen": 2836960,
+      "step": 55
+    },
+    {
+      "epoch": 1.483221476510067,
+      "grad_norm": 0.08382672816514969,
+      "learning_rate": 4.968664940769121e-05,
+      "loss": 0.3276,
+      "num_input_tokens_seen": 2900208,
+      "step": 56
+    },
+    {
+      "epoch": 1.5100671140939599,
+      "grad_norm": 0.07235248386859894,
+      "learning_rate": 4.967538289226267e-05,
+      "loss": 0.2721,
+      "num_input_tokens_seen": 2964720,
+      "step": 57
+    },
+    {
+      "epoch": 1.5369127516778525,
+      "grad_norm": 0.07382500171661377,
+      "learning_rate": 4.9663918717467996e-05,
+      "loss": 0.3084,
+      "num_input_tokens_seen": 3029912,
+      "step": 58
+    },
+    {
+      "epoch": 1.563758389261745,
+      "grad_norm": 0.07173939794301987,
+      "learning_rate": 4.965225697513965e-05,
+      "loss": 0.2752,
+      "num_input_tokens_seen": 3081216,
+      "step": 59
+    },
+    {
+      "epoch": 1.5906040268456376,
+      "grad_norm": 0.07698569446802139,
+      "learning_rate": 4.9640397758692715e-05,
+      "loss": 0.2684,
+      "num_input_tokens_seen": 3131424,
+      "step": 60
+    },
+    {
+      "epoch": 1.6174496644295302,
+      "grad_norm": 0.07956692576408386,
+      "learning_rate": 4.962834116312409e-05,
+      "loss": 0.2663,
+      "num_input_tokens_seen": 3183240,
+      "step": 61
+    },
+    {
+      "epoch": 1.6442953020134228,
+      "grad_norm": 0.09150110185146332,
+      "learning_rate": 4.961608728501178e-05,
+      "loss": 0.2845,
+      "num_input_tokens_seen": 3231192,
+      "step": 62
+    },
+    {
+      "epoch": 1.6711409395973154,
+      "grad_norm": 0.07471323758363724,
+      "learning_rate": 4.960363622251409e-05,
+      "loss": 0.2873,
+      "num_input_tokens_seen": 3290616,
+      "step": 63
+    },
+    {
+      "epoch": 1.697986577181208,
+      "grad_norm": 0.08185286819934845,
+      "learning_rate": 4.959098807536885e-05,
+      "loss": 0.2858,
+      "num_input_tokens_seen": 3342512,
+      "step": 64
+    },
+    {
+      "epoch": 1.7248322147651005,
+      "grad_norm": 0.07076375931501389,
+      "learning_rate": 4.957814294489261e-05,
+      "loss": 0.2813,
+      "num_input_tokens_seen": 3404912,
+      "step": 65
+    },
+    {
+      "epoch": 1.7516778523489933,
+      "grad_norm": 0.08946257829666138,
+      "learning_rate": 4.956510093397983e-05,
+      "loss": 0.2417,
+      "num_input_tokens_seen": 3444648,
+      "step": 66
+    },
+    {
+      "epoch": 1.778523489932886,
+      "grad_norm": 0.08985330909490585,
+      "learning_rate": 4.955186214710208e-05,
+      "loss": 0.303,
+      "num_input_tokens_seen": 3493584,
+      "step": 67
+    },
+    {
+      "epoch": 1.8053691275167785,
+      "grad_norm": 0.0905148983001709,
+      "learning_rate": 4.953842669030716e-05,
+      "loss": 0.259,
+      "num_input_tokens_seen": 3544904,
+      "step": 68
+    },
+    {
+      "epoch": 1.8322147651006713,
+      "grad_norm": 0.08572433143854141,
+      "learning_rate": 4.952479467121827e-05,
+      "loss": 0.2709,
+      "num_input_tokens_seen": 3591296,
+      "step": 69
+    },
+    {
+      "epoch": 1.8590604026845639,
+      "grad_norm": 0.09188525378704071,
+      "learning_rate": 4.9510966199033174e-05,
+      "loss": 0.2615,
+      "num_input_tokens_seen": 3655368,
+      "step": 70
+    },
+    {
+      "epoch": 1.8859060402684564,
+      "grad_norm": 0.0810374766588211,
+      "learning_rate": 4.949694138452327e-05,
+      "loss": 0.2607,
+      "num_input_tokens_seen": 3707872,
+      "step": 71
+    },
+    {
+      "epoch": 1.912751677852349,
+      "grad_norm": 0.09255556017160416,
+      "learning_rate": 4.948272034003275e-05,
+      "loss": 0.2876,
+      "num_input_tokens_seen": 3755824,
+      "step": 72
+    },
+    {
+      "epoch": 1.9395973154362416,
+      "grad_norm": 0.07975213974714279,
+      "learning_rate": 4.9468303179477706e-05,
+      "loss": 0.2429,
+      "num_input_tokens_seen": 3810712,
+      "step": 73
+    },
+    {
+      "epoch": 1.9664429530201342,
+      "grad_norm": 0.09419341385364532,
+      "learning_rate": 4.9453690018345144e-05,
+      "loss": 0.2672,
+      "num_input_tokens_seen": 3861920,
+      "step": 74
+    },
+    {
+      "epoch": 1.9932885906040267,
+      "grad_norm": 0.10117878019809723,
+      "learning_rate": 4.943888097369216e-05,
+      "loss": 0.2764,
+      "num_input_tokens_seen": 3909768,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.16053622961044312,
+      "learning_rate": 4.942387616414492e-05,
+      "loss": 0.2707,
+      "num_input_tokens_seen": 3923616,
+      "step": 76
+    },
+    {
+      "epoch": 2.0268456375838926,
+      "grad_norm": 0.14125753939151764,
+      "learning_rate": 4.940867570989777e-05,
+      "loss": 0.2517,
+      "num_input_tokens_seen": 3978224,
+      "step": 77
+    },
+    {
+      "epoch": 2.053691275167785,
+      "grad_norm": 0.08800158649682999,
+      "learning_rate": 4.939327973271221e-05,
+      "loss": 0.2821,
+      "num_input_tokens_seen": 4024096,
+      "step": 78
+    },
+    {
+      "epoch": 2.0805369127516777,
+      "grad_norm": 0.08880551159381866,
+      "learning_rate": 4.9377688355915994e-05,
+      "loss": 0.2396,
+      "num_input_tokens_seen": 4080656,
+      "step": 79
+    },
+    {
+      "epoch": 2.1073825503355703,
+      "grad_norm": 0.09785644710063934,
+      "learning_rate": 4.936190170440208e-05,
+      "loss": 0.2564,
+      "num_input_tokens_seen": 4122248,
+      "step": 80
+    },
+    {
+      "epoch": 2.134228187919463,
+      "grad_norm": 0.10203557461500168,
+      "learning_rate": 4.934591990462766e-05,
+      "loss": 0.2663,
+      "num_input_tokens_seen": 4183624,
+      "step": 81
+    },
+    {
+      "epoch": 2.1610738255033555,
+      "grad_norm": 0.09022527933120728,
+      "learning_rate": 4.932974308461311e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 4223696,
+      "step": 82
+    },
+    {
+      "epoch": 2.1879194630872485,
+      "grad_norm": 0.08529677987098694,
+      "learning_rate": 4.931337137394105e-05,
+      "loss": 0.2743,
+      "num_input_tokens_seen": 4282504,
+      "step": 83
+    },
+    {
+      "epoch": 2.214765100671141,
+      "grad_norm": 0.10522245615720749,
+      "learning_rate": 4.92968049037552e-05,
+      "loss": 0.2516,
+      "num_input_tokens_seen": 4338600,
+      "step": 84
+    },
+    {
+      "epoch": 2.2416107382550337,
+      "grad_norm": 0.09364143013954163,
+      "learning_rate": 4.928004380675941e-05,
+      "loss": 0.2463,
+      "num_input_tokens_seen": 4385840,
+      "step": 85
+    },
+    {
+      "epoch": 2.2684563758389262,
+      "grad_norm": 0.10501237958669662,
+      "learning_rate": 4.9263088217216544e-05,
+      "loss": 0.2578,
+      "num_input_tokens_seen": 4440368,
+      "step": 86
+    },
+    {
+      "epoch": 2.295302013422819,
+      "grad_norm": 0.09559391438961029,
+      "learning_rate": 4.9245938270947435e-05,
+      "loss": 0.2369,
+      "num_input_tokens_seen": 4502040,
+      "step": 87
+    },
+    {
+      "epoch": 2.3221476510067114,
+      "grad_norm": 0.08705922961235046,
+      "learning_rate": 4.922859410532978e-05,
+      "loss": 0.3009,
+      "num_input_tokens_seen": 4563296,
+      "step": 88
+    },
+    {
+      "epoch": 2.348993288590604,
+      "grad_norm": 0.08942529559135437,
+      "learning_rate": 4.921105585929709e-05,
+      "loss": 0.211,
+      "num_input_tokens_seen": 4620344,
+      "step": 89
+    },
+    {
+      "epoch": 2.3758389261744965,
+      "grad_norm": 0.088467076420784,
+      "learning_rate": 4.9193323673337476e-05,
+      "loss": 0.2463,
+      "num_input_tokens_seen": 4675400,
+      "step": 90
+    },
+    {
+      "epoch": 2.402684563758389,
+      "grad_norm": 0.08302924036979675,
+      "learning_rate": 4.9175397689492614e-05,
+      "loss": 0.2536,
+      "num_input_tokens_seen": 4734696,
+      "step": 91
+    },
+    {
+      "epoch": 2.4295302013422817,
+      "grad_norm": 0.10511067509651184,
+      "learning_rate": 4.915727805135657e-05,
+      "loss": 0.2538,
+      "num_input_tokens_seen": 4782448,
+      "step": 92
+    },
+    {
+      "epoch": 2.4563758389261743,
+      "grad_norm": 0.09681275486946106,
+      "learning_rate": 4.9138964904074667e-05,
+      "loss": 0.2243,
+      "num_input_tokens_seen": 4830504,
+      "step": 93
+    },
+    {
+      "epoch": 2.4832214765100673,
+      "grad_norm": 0.10118114203214645,
+      "learning_rate": 4.91204583943423e-05,
+      "loss": 0.2701,
+      "num_input_tokens_seen": 4886040,
+      "step": 94
+    },
+    {
+      "epoch": 2.51006711409396,
+      "grad_norm": 0.11683424562215805,
+      "learning_rate": 4.910175867040377e-05,
+      "loss": 0.2292,
+      "num_input_tokens_seen": 4934448,
+      "step": 95
+    },
+    {
+      "epoch": 2.5369127516778525,
+      "grad_norm": 0.09783443063497543,
+      "learning_rate": 4.90828658820511e-05,
+      "loss": 0.2398,
+      "num_input_tokens_seen": 4987040,
+      "step": 96
+    },
+    {
+      "epoch": 2.563758389261745,
+      "grad_norm": 0.10438188165426254,
+      "learning_rate": 4.9063780180622845e-05,
+      "loss": 0.2355,
+      "num_input_tokens_seen": 5037360,
+      "step": 97
+    },
+    {
+      "epoch": 2.5906040268456376,
+      "grad_norm": 0.1034293919801712,
+      "learning_rate": 4.9044501719002844e-05,
+      "loss": 0.2554,
+      "num_input_tokens_seen": 5091640,
+      "step": 98
+    },
+    {
+      "epoch": 2.61744966442953,
+      "grad_norm": 0.09722857177257538,
+      "learning_rate": 4.9025030651619046e-05,
+      "loss": 0.2176,
+      "num_input_tokens_seen": 5149232,
+      "step": 99
+    },
+    {
+      "epoch": 2.6442953020134228,
+      "grad_norm": 0.1010555699467659,
+      "learning_rate": 4.9005367134442235e-05,
+      "loss": 0.2191,
+      "num_input_tokens_seen": 5196648,
+      "step": 100
+    },
+    {
+      "epoch": 2.6711409395973154,
+      "grad_norm": 0.085463747382164,
+      "learning_rate": 4.89855113249848e-05,
+      "loss": 0.2283,
+      "num_input_tokens_seen": 5261568,
+      "step": 101
+    },
+    {
+      "epoch": 2.697986577181208,
+      "grad_norm": 0.10148970782756805,
+      "learning_rate": 4.896546338229945e-05,
+      "loss": 0.234,
+      "num_input_tokens_seen": 5312104,
+      "step": 102
+    },
+    {
+      "epoch": 2.7248322147651005,
+      "grad_norm": 0.12468232959508896,
+      "learning_rate": 4.894522346697796e-05,
+      "loss": 0.2373,
+      "num_input_tokens_seen": 5360104,
+      "step": 103
+    },
+    {
+      "epoch": 2.751677852348993,
+      "grad_norm": 0.11668706685304642,
+      "learning_rate": 4.892479174114989e-05,
+      "loss": 0.2291,
+      "num_input_tokens_seen": 5402856,
+      "step": 104
+    },
+    {
+      "epoch": 2.778523489932886,
+      "grad_norm": 0.11586510390043259,
+      "learning_rate": 4.890416836848127e-05,
+      "loss": 0.2297,
+      "num_input_tokens_seen": 5445040,
+      "step": 105
+    },
+    {
+      "epoch": 2.8053691275167782,
+      "grad_norm": 0.09793268144130707,
+      "learning_rate": 4.888335351417331e-05,
+      "loss": 0.2271,
+      "num_input_tokens_seen": 5497368,
+      "step": 106
+    },
+    {
+      "epoch": 2.8322147651006713,
+      "grad_norm": 0.1202295795083046,
+      "learning_rate": 4.886234734496102e-05,
+      "loss": 0.261,
+      "num_input_tokens_seen": 5560720,
+      "step": 107
+    },
+    {
+      "epoch": 2.859060402684564,
+      "grad_norm": 0.10316886752843857,
+      "learning_rate": 4.884115002911197e-05,
+      "loss": 0.2532,
+      "num_input_tokens_seen": 5616592,
+      "step": 108
+    },
+    {
+      "epoch": 2.8859060402684564,
+      "grad_norm": 0.10972882062196732,
+      "learning_rate": 4.8819761736424854e-05,
+      "loss": 0.2265,
+      "num_input_tokens_seen": 5674352,
+      "step": 109
+    },
+    {
+      "epoch": 2.912751677852349,
+      "grad_norm": 0.11267542093992233,
+      "learning_rate": 4.8798182638228166e-05,
+      "loss": 0.2356,
+      "num_input_tokens_seen": 5710912,
+      "step": 110
+    },
+    {
+      "epoch": 2.9395973154362416,
+      "grad_norm": 0.11448722332715988,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.2381,
+      "num_input_tokens_seen": 5757920,
+      "step": 111
+    },
+    {
+      "epoch": 2.966442953020134,
+      "grad_norm": 0.11678655445575714,
+      "learning_rate": 4.875445271826084e-05,
+      "loss": 0.2288,
+      "num_input_tokens_seen": 5802192,
+      "step": 112
+    },
+    {
+      "epoch": 2.9932885906040267,
+      "grad_norm": 0.11252844333648682,
+      "learning_rate": 4.87323022467838e-05,
+      "loss": 0.2264,
+      "num_input_tokens_seen": 5867304,
+      "step": 113
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19352872669696808,
+      "learning_rate": 4.870996167038154e-05,
+      "loss": 0.2352,
+      "num_input_tokens_seen": 5885424,
+      "step": 114
+    },
+    {
+      "epoch": 3.0268456375838926,
+      "grad_norm": 0.1173228845000267,
+      "learning_rate": 4.868743116801074e-05,
+      "loss": 0.2164,
+      "num_input_tokens_seen": 5944528,
+      "step": 115
+    },
+    {
+      "epoch": 3.053691275167785,
+      "grad_norm": 0.11860992014408112,
+      "learning_rate": 4.866471092014945e-05,
+      "loss": 0.2329,
+      "num_input_tokens_seen": 6003480,
+      "step": 116
+    },
+    {
+      "epoch": 3.0805369127516777,
+      "grad_norm": 0.10296034812927246,
+      "learning_rate": 4.864180110879562e-05,
+      "loss": 0.2318,
+      "num_input_tokens_seen": 6059304,
+      "step": 117
+    },
+    {
+      "epoch": 3.1073825503355703,
+      "grad_norm": 0.11512338370084763,
+      "learning_rate": 4.861870191746573e-05,
+      "loss": 0.2054,
+      "num_input_tokens_seen": 6117288,
+      "step": 118
+    },
+    {
+      "epoch": 3.134228187919463,
+      "grad_norm": 0.13150866329669952,
+      "learning_rate": 4.859541353119322e-05,
+      "loss": 0.2086,
+      "num_input_tokens_seen": 6164008,
+      "step": 119
+    },
+    {
+      "epoch": 3.1610738255033555,
+      "grad_norm": 0.11846304684877396,
+      "learning_rate": 4.857193613652711e-05,
+      "loss": 0.2353,
+      "num_input_tokens_seen": 6224560,
+      "step": 120
+    },
+    {
+      "epoch": 3.1879194630872485,
+      "grad_norm": 0.12476348876953125,
+      "learning_rate": 4.854826992153038e-05,
+      "loss": 0.2295,
+      "num_input_tokens_seen": 6273248,
+      "step": 121
+    },
+    {
+      "epoch": 3.214765100671141,
+      "grad_norm": 0.11604316532611847,
+      "learning_rate": 4.8524415075778597e-05,
+      "loss": 0.1945,
+      "num_input_tokens_seen": 6327592,
+      "step": 122
+    },
+    {
+      "epoch": 3.2416107382550337,
+      "grad_norm": 0.12193804979324341,
+      "learning_rate": 4.850037179035829e-05,
+      "loss": 0.2389,
+      "num_input_tokens_seen": 6389680,
+      "step": 123
+    },
+    {
+      "epoch": 3.2684563758389262,
+      "grad_norm": 0.12192777544260025,
+      "learning_rate": 4.847614025786549e-05,
+      "loss": 0.2083,
+      "num_input_tokens_seen": 6441392,
+      "step": 124
+    },
+    {
+      "epoch": 3.295302013422819,
+      "grad_norm": 0.13284096121788025,
+      "learning_rate": 4.845172067240415e-05,
+      "loss": 0.2497,
+      "num_input_tokens_seen": 6483464,
+      "step": 125
+    },
+    {
+      "epoch": 3.3221476510067114,
+      "grad_norm": 0.10930957645177841,
+      "learning_rate": 4.842711322958459e-05,
+      "loss": 0.188,
+      "num_input_tokens_seen": 6536056,
+      "step": 126
+    },
+    {
+      "epoch": 3.348993288590604,
+      "grad_norm": 0.12303247302770615,
+      "learning_rate": 4.840231812652196e-05,
+      "loss": 0.1913,
+      "num_input_tokens_seen": 6583768,
+      "step": 127
+    },
+    {
+      "epoch": 3.3758389261744965,
+      "grad_norm": 0.12305760383605957,
+      "learning_rate": 4.837733556183463e-05,
+      "loss": 0.1926,
+      "num_input_tokens_seen": 6639048,
+      "step": 128
+    },
+    {
+      "epoch": 3.402684563758389,
+      "grad_norm": 0.13311812281608582,
+      "learning_rate": 4.8352165735642604e-05,
+      "loss": 0.2234,
+      "num_input_tokens_seen": 6691360,
+      "step": 129
+    },
+    {
+      "epoch": 3.4295302013422817,
+      "grad_norm": 0.12300640344619751,
+      "learning_rate": 4.8326808849565936e-05,
+      "loss": 0.2332,
+      "num_input_tokens_seen": 6743408,
+      "step": 130
+    },
+    {
+      "epoch": 3.4563758389261743,
+      "grad_norm": 0.1301521509885788,
+      "learning_rate": 4.830126510672309e-05,
+      "loss": 0.18,
+      "num_input_tokens_seen": 6790704,
+      "step": 131
+    },
+    {
+      "epoch": 3.4832214765100673,
+      "grad_norm": 0.1255597174167633,
+      "learning_rate": 4.827553471172935e-05,
+      "loss": 0.1964,
+      "num_input_tokens_seen": 6839200,
+      "step": 132
+    },
+    {
+      "epoch": 3.51006711409396,
+      "grad_norm": 0.13288290798664093,
+      "learning_rate": 4.824961787069511e-05,
+      "loss": 0.2116,
+      "num_input_tokens_seen": 6892832,
+      "step": 133
+    },
+    {
+      "epoch": 3.5369127516778525,
+      "grad_norm": 0.11485302448272705,
+      "learning_rate": 4.822351479122432e-05,
+      "loss": 0.2071,
+      "num_input_tokens_seen": 6949464,
+      "step": 134
+    },
+    {
+      "epoch": 3.563758389261745,
+      "grad_norm": 0.11960192024707794,
+      "learning_rate": 4.819722568241274e-05,
+      "loss": 0.175,
+      "num_input_tokens_seen": 6996480,
+      "step": 135
+    },
+    {
+      "epoch": 3.5906040268456376,
+      "grad_norm": 0.14381754398345947,
+      "learning_rate": 4.817075075484629e-05,
+      "loss": 0.237,
+      "num_input_tokens_seen": 7053720,
+      "step": 136
+    },
+    {
+      "epoch": 3.61744966442953,
+      "grad_norm": 0.1209937036037445,
+      "learning_rate": 4.8144090220599416e-05,
+      "loss": 0.2176,
+      "num_input_tokens_seen": 7111480,
+      "step": 137
+    },
+    {
+      "epoch": 3.6442953020134228,
+      "grad_norm": 0.13339534401893616,
+      "learning_rate": 4.811724429323329e-05,
+      "loss": 0.2164,
+      "num_input_tokens_seen": 7165728,
+      "step": 138
+    },
+    {
+      "epoch": 3.6711409395973154,
+      "grad_norm": 0.14351628720760345,
+      "learning_rate": 4.809021318779419e-05,
+      "loss": 0.1876,
+      "num_input_tokens_seen": 7207648,
+      "step": 139
+    },
+    {
+      "epoch": 3.697986577181208,
+      "grad_norm": 0.1557406485080719,
+      "learning_rate": 4.806299712081172e-05,
+      "loss": 0.2697,
+      "num_input_tokens_seen": 7254280,
+      "step": 140
+    },
+    {
+      "epoch": 3.7248322147651005,
+      "grad_norm": 0.14036628603935242,
+      "learning_rate": 4.8035596310297124e-05,
+      "loss": 0.1955,
+      "num_input_tokens_seen": 7297912,
+      "step": 141
+    },
+    {
+      "epoch": 3.751677852348993,
+      "grad_norm": 0.1406165212392807,
+      "learning_rate": 4.800801097574149e-05,
+      "loss": 0.2048,
+      "num_input_tokens_seen": 7343304,
+      "step": 142
+    },
+    {
+      "epoch": 3.778523489932886,
+      "grad_norm": 0.1484479159116745,
+      "learning_rate": 4.798024133811403e-05,
+      "loss": 0.2062,
+      "num_input_tokens_seen": 7391688,
+      "step": 143
+    },
+    {
+      "epoch": 3.8053691275167782,
+      "grad_norm": 0.15288512408733368,
+      "learning_rate": 4.795228761986028e-05,
+      "loss": 0.2123,
+      "num_input_tokens_seen": 7448016,
+      "step": 144
+    },
+    {
+      "epoch": 3.8322147651006713,
+      "grad_norm": 0.1407124102115631,
+      "learning_rate": 4.792415004490034e-05,
+      "loss": 0.2128,
+      "num_input_tokens_seen": 7495312,
+      "step": 145
+    },
+    {
+      "epoch": 3.859060402684564,
+      "grad_norm": 0.1452370434999466,
+      "learning_rate": 4.789582883862708e-05,
+      "loss": 0.207,
+      "num_input_tokens_seen": 7552600,
+      "step": 146
+    },
+    {
+      "epoch": 3.8859060402684564,
+      "grad_norm": 0.16543127596378326,
+      "learning_rate": 4.786732422790432e-05,
+      "loss": 0.2227,
+      "num_input_tokens_seen": 7615064,
+      "step": 147
+    },
+    {
+      "epoch": 3.912751677852349,
+      "grad_norm": 0.15252095460891724,
+      "learning_rate": 4.783863644106502e-05,
+      "loss": 0.2296,
+      "num_input_tokens_seen": 7671712,
+      "step": 148
+    },
+    {
+      "epoch": 3.9395973154362416,
+      "grad_norm": 0.1682525873184204,
+      "learning_rate": 4.780976570790947e-05,
+      "loss": 0.1989,
+      "num_input_tokens_seen": 7713880,
+      "step": 149
+    },
+    {
+      "epoch": 3.966442953020134,
+      "grad_norm": 0.15517935156822205,
+      "learning_rate": 4.77807122597034e-05,
+      "loss": 0.2485,
+      "num_input_tokens_seen": 7766672,
+      "step": 150
+    },
+    {
+      "epoch": 3.9932885906040267,
+      "grad_norm": 0.13144247233867645,
+      "learning_rate": 4.775147632917617e-05,
+      "loss": 0.1962,
+      "num_input_tokens_seen": 7835800,
+      "step": 151
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.3006974160671234,
+      "learning_rate": 4.7722058150518914e-05,
+      "loss": 0.2309,
+      "num_input_tokens_seen": 7847232,
+      "step": 152
+    },
+    {
+      "epoch": 4.026845637583893,
+      "grad_norm": 0.1415897011756897,
+      "learning_rate": 4.769245795938261e-05,
+      "loss": 0.2234,
+      "num_input_tokens_seen": 7894656,
+      "step": 153
+    },
+    {
+      "epoch": 4.053691275167785,
+      "grad_norm": 0.15622243285179138,
+      "learning_rate": 4.766267599287625e-05,
+      "loss": 0.1936,
+      "num_input_tokens_seen": 7957712,
+      "step": 154
+    },
+    {
+      "epoch": 4.080536912751678,
+      "grad_norm": 0.152387797832489,
+      "learning_rate": 4.7632712489564926e-05,
+      "loss": 0.1859,
+      "num_input_tokens_seen": 8005344,
+      "step": 155
+    },
+    {
+      "epoch": 4.10738255033557,
+      "grad_norm": 0.13995884358882904,
+      "learning_rate": 4.760256768946787e-05,
+      "loss": 0.1705,
+      "num_input_tokens_seen": 8065064,
+      "step": 156
+    },
+    {
+      "epoch": 4.134228187919463,
+      "grad_norm": 0.15024860203266144,
+      "learning_rate": 4.7572241834056616e-05,
+      "loss": 0.1845,
+      "num_input_tokens_seen": 8122464,
+      "step": 157
+    },
+    {
+      "epoch": 4.1610738255033555,
+      "grad_norm": 0.16085512936115265,
+      "learning_rate": 4.7541735166252986e-05,
+      "loss": 0.2019,
+      "num_input_tokens_seen": 8169408,
+      "step": 158
+    },
+    {
+      "epoch": 4.1879194630872485,
+      "grad_norm": 0.15862515568733215,
+      "learning_rate": 4.751104793042722e-05,
+      "loss": 0.2003,
+      "num_input_tokens_seen": 8226728,
+      "step": 159
+    },
+    {
+      "epoch": 4.214765100671141,
+      "grad_norm": 0.1638798713684082,
+      "learning_rate": 4.748018037239592e-05,
+      "loss": 0.1931,
+      "num_input_tokens_seen": 8285288,
+      "step": 160
+    },
+    {
+      "epoch": 4.241610738255034,
+      "grad_norm": 0.16194795072078705,
+      "learning_rate": 4.74491327394202e-05,
+      "loss": 0.2145,
+      "num_input_tokens_seen": 8329624,
+      "step": 161
+    },
+    {
+      "epoch": 4.268456375838926,
+      "grad_norm": 0.14317141473293304,
+      "learning_rate": 4.7417905280203594e-05,
+      "loss": 0.1892,
+      "num_input_tokens_seen": 8375536,
+      "step": 162
+    },
+    {
+      "epoch": 4.295302013422819,
+      "grad_norm": 0.174782857298851,
+      "learning_rate": 4.7386498244890146e-05,
+      "loss": 0.206,
+      "num_input_tokens_seen": 8433088,
+      "step": 163
+    },
+    {
+      "epoch": 4.322147651006711,
+      "grad_norm": 0.1592899113893509,
+      "learning_rate": 4.735491188506237e-05,
+      "loss": 0.1692,
+      "num_input_tokens_seen": 8480984,
+      "step": 164
+    },
+    {
+      "epoch": 4.348993288590604,
+      "grad_norm": 0.17513258755207062,
+      "learning_rate": 4.732314645373921e-05,
+      "loss": 0.2201,
+      "num_input_tokens_seen": 8532168,
+      "step": 165
+    },
+    {
+      "epoch": 4.375838926174497,
+      "grad_norm": 0.1629508137702942,
+      "learning_rate": 4.7291202205374086e-05,
+      "loss": 0.1763,
+      "num_input_tokens_seen": 8579384,
+      "step": 166
+    },
+    {
+      "epoch": 4.402684563758389,
+      "grad_norm": 0.15738122165203094,
+      "learning_rate": 4.7259079395852776e-05,
+      "loss": 0.1781,
+      "num_input_tokens_seen": 8626592,
+      "step": 167
+    },
+    {
+      "epoch": 4.429530201342282,
+      "grad_norm": 0.18833334743976593,
+      "learning_rate": 4.7226778282491424e-05,
+      "loss": 0.2067,
+      "num_input_tokens_seen": 8680320,
+      "step": 168
+    },
+    {
+      "epoch": 4.456375838926174,
+      "grad_norm": 0.14375615119934082,
+      "learning_rate": 4.719429912403445e-05,
+      "loss": 0.1795,
+      "num_input_tokens_seen": 8740824,
+      "step": 169
+    },
+    {
+      "epoch": 4.483221476510067,
+      "grad_norm": 0.17458012700080872,
+      "learning_rate": 4.7161642180652464e-05,
+      "loss": 0.2021,
+      "num_input_tokens_seen": 8789312,
+      "step": 170
+    },
+    {
+      "epoch": 4.510067114093959,
+      "grad_norm": 0.17704319953918457,
+      "learning_rate": 4.712880771394024e-05,
+      "loss": 0.1916,
+      "num_input_tokens_seen": 8838400,
+      "step": 171
+    },
+    {
+      "epoch": 4.5369127516778525,
+      "grad_norm": 0.1582602709531784,
+      "learning_rate": 4.709579598691456e-05,
+      "loss": 0.1852,
+      "num_input_tokens_seen": 8883320,
+      "step": 172
+    },
+    {
+      "epoch": 4.563758389261745,
+      "grad_norm": 0.16678012907505035,
+      "learning_rate": 4.7062607264012124e-05,
+      "loss": 0.162,
+      "num_input_tokens_seen": 8931240,
+      "step": 173
+    },
+    {
+      "epoch": 4.590604026845638,
+      "grad_norm": 0.15457355976104736,
+      "learning_rate": 4.7029241811087457e-05,
+      "loss": 0.1763,
+      "num_input_tokens_seen": 8982280,
+      "step": 174
+    },
+    {
+      "epoch": 4.617449664429531,
+      "grad_norm": 0.16706790030002594,
+      "learning_rate": 4.699569989541074e-05,
+      "loss": 0.2005,
+      "num_input_tokens_seen": 9027824,
+      "step": 175
+    },
+    {
+      "epoch": 4.644295302013423,
+      "grad_norm": 0.16770173609256744,
+      "learning_rate": 4.69619817856657e-05,
+      "loss": 0.1985,
+      "num_input_tokens_seen": 9081584,
+      "step": 176
+    },
+    {
+      "epoch": 4.671140939597316,
+      "grad_norm": 0.19141702353954315,
+      "learning_rate": 4.692808775194745e-05,
+      "loss": 0.1963,
+      "num_input_tokens_seen": 9142112,
+      "step": 177
+    },
+    {
+      "epoch": 4.697986577181208,
+      "grad_norm": 0.15951097011566162,
+      "learning_rate": 4.68940180657603e-05,
+      "loss": 0.1691,
+      "num_input_tokens_seen": 9190280,
+      "step": 178
+    },
+    {
+      "epoch": 4.724832214765101,
+      "grad_norm": 0.16681668162345886,
+      "learning_rate": 4.685977300001565e-05,
+      "loss": 0.1896,
+      "num_input_tokens_seen": 9240592,
+      "step": 179
+    },
+    {
+      "epoch": 4.751677852348993,
+      "grad_norm": 0.16679206490516663,
+      "learning_rate": 4.6825352829029705e-05,
+      "loss": 0.1724,
+      "num_input_tokens_seen": 9294464,
+      "step": 180
+    },
+    {
+      "epoch": 4.778523489932886,
+      "grad_norm": 0.16181506216526031,
+      "learning_rate": 4.679075782852137e-05,
+      "loss": 0.1698,
+      "num_input_tokens_seen": 9349552,
+      "step": 181
+    },
+    {
+      "epoch": 4.805369127516778,
+      "grad_norm": 0.16370564699172974,
+      "learning_rate": 4.675598827560998e-05,
+      "loss": 0.2092,
+      "num_input_tokens_seen": 9409136,
+      "step": 182
+    },
+    {
+      "epoch": 4.832214765100671,
+      "grad_norm": 0.18401412665843964,
+      "learning_rate": 4.67210444488131e-05,
+      "loss": 0.1763,
+      "num_input_tokens_seen": 9444096,
+      "step": 183
+    },
+    {
+      "epoch": 4.859060402684563,
+      "grad_norm": 0.21891450881958008,
+      "learning_rate": 4.668592662804432e-05,
+      "loss": 0.219,
+      "num_input_tokens_seen": 9508552,
+      "step": 184
+    },
+    {
+      "epoch": 4.885906040268456,
+      "grad_norm": 0.19035810232162476,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.1856,
+      "num_input_tokens_seen": 9564224,
+      "step": 185
+    },
+    {
+      "epoch": 4.912751677852349,
+      "grad_norm": 0.16957947611808777,
+      "learning_rate": 4.661517013121189e-05,
+      "loss": 0.1747,
+      "num_input_tokens_seen": 9620384,
+      "step": 186
+    },
+    {
+      "epoch": 4.939597315436242,
+      "grad_norm": 0.16003385186195374,
+      "learning_rate": 4.657953202193516e-05,
+      "loss": 0.1685,
+      "num_input_tokens_seen": 9679824,
+      "step": 187
+    },
+    {
+      "epoch": 4.966442953020135,
+      "grad_norm": 0.1679641157388687,
+      "learning_rate": 4.654372105225583e-05,
+      "loss": 0.1636,
+      "num_input_tokens_seen": 9732328,
+      "step": 188
+    },
+    {
+      "epoch": 4.993288590604027,
+      "grad_norm": 0.15429595112800598,
+      "learning_rate": 4.650773750903363e-05,
+      "loss": 0.1429,
+      "num_input_tokens_seen": 9793456,
+      "step": 189
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.30234482884407043,
+      "learning_rate": 4.647158168051066e-05,
+      "loss": 0.1757,
+      "num_input_tokens_seen": 9809040,
+      "step": 190
+    },
+    {
+      "epoch": 5.026845637583893,
+      "grad_norm": 0.19254004955291748,
+      "learning_rate": 4.6435253856309094e-05,
+      "loss": 0.1711,
+      "num_input_tokens_seen": 9863696,
+      "step": 191
+    },
+    {
+      "epoch": 5.053691275167785,
+      "grad_norm": 0.16591961681842804,
+      "learning_rate": 4.639875432742886e-05,
+      "loss": 0.156,
+      "num_input_tokens_seen": 9906912,
+      "step": 192
+    },
+    {
+      "epoch": 5.080536912751678,
+      "grad_norm": 0.18133562803268433,
+      "learning_rate": 4.636208338624533e-05,
+      "loss": 0.17,
+      "num_input_tokens_seen": 9950056,
+      "step": 193
+    },
+    {
+      "epoch": 5.10738255033557,
+      "grad_norm": 0.19608290493488312,
+      "learning_rate": 4.6325241326506915e-05,
+      "loss": 0.1882,
+      "num_input_tokens_seen": 10001296,
+      "step": 194
+    },
+    {
+      "epoch": 5.134228187919463,
+      "grad_norm": 0.2348538637161255,
+      "learning_rate": 4.628822844333278e-05,
+      "loss": 0.1564,
+      "num_input_tokens_seen": 10052888,
+      "step": 195
+    },
+    {
+      "epoch": 5.1610738255033555,
+      "grad_norm": 0.17895568907260895,
+      "learning_rate": 4.625104503321045e-05,
+      "loss": 0.1606,
+      "num_input_tokens_seen": 10109912,
+      "step": 196
+    },
+    {
+      "epoch": 5.1879194630872485,
+      "grad_norm": 0.1882435381412506,
+      "learning_rate": 4.621369139399341e-05,
+      "loss": 0.1722,
+      "num_input_tokens_seen": 10151104,
+      "step": 197
+    },
+    {
+      "epoch": 5.214765100671141,
+      "grad_norm": 0.18267786502838135,
+      "learning_rate": 4.6176167824898773e-05,
+      "loss": 0.1679,
+      "num_input_tokens_seen": 10196304,
+      "step": 198
+    },
+    {
+      "epoch": 5.241610738255034,
+      "grad_norm": 0.16710643470287323,
+      "learning_rate": 4.613847462650486e-05,
+      "loss": 0.1548,
+      "num_input_tokens_seen": 10255152,
+      "step": 199
+    },
+    {
+      "epoch": 5.268456375838926,
+      "grad_norm": 0.19108474254608154,
+      "learning_rate": 4.6100612100748765e-05,
+      "loss": 0.166,
+      "num_input_tokens_seen": 10294912,
+      "step": 200
+    },
+    {
+      "epoch": 5.295302013422819,
+      "grad_norm": 0.16066554188728333,
+      "learning_rate": 4.606258055092397e-05,
+      "loss": 0.1648,
+      "num_input_tokens_seen": 10357248,
+      "step": 201
+    },
+    {
+      "epoch": 5.322147651006711,
+      "grad_norm": 0.18054331839084625,
+      "learning_rate": 4.602438028167792e-05,
+      "loss": 0.1419,
+      "num_input_tokens_seen": 10411456,
+      "step": 202
+    },
+    {
+      "epoch": 5.348993288590604,
+      "grad_norm": 0.22617101669311523,
+      "learning_rate": 4.5986011599009544e-05,
+      "loss": 0.1935,
+      "num_input_tokens_seen": 10462080,
+      "step": 203
+    },
+    {
+      "epoch": 5.375838926174497,
+      "grad_norm": 0.1666952520608902,
+      "learning_rate": 4.594747481026684e-05,
+      "loss": 0.1449,
+      "num_input_tokens_seen": 10530312,
+      "step": 204
+    },
+    {
+      "epoch": 5.402684563758389,
+      "grad_norm": 0.16662774980068207,
+      "learning_rate": 4.59087702241444e-05,
+      "loss": 0.1548,
+      "num_input_tokens_seen": 10593232,
+      "step": 205
+    },
+    {
+      "epoch": 5.429530201342282,
+      "grad_norm": 0.1743718981742859,
+      "learning_rate": 4.586989815068095e-05,
+      "loss": 0.2084,
+      "num_input_tokens_seen": 10661464,
+      "step": 206
+    },
+    {
+      "epoch": 5.456375838926174,
+      "grad_norm": 0.191987544298172,
+      "learning_rate": 4.5830858901256826e-05,
+      "loss": 0.1527,
+      "num_input_tokens_seen": 10704912,
+      "step": 207
+    },
+    {
+      "epoch": 5.483221476510067,
+      "grad_norm": 0.19640536606311798,
+      "learning_rate": 4.579165278859152e-05,
+      "loss": 0.1515,
+      "num_input_tokens_seen": 10750792,
+      "step": 208
+    },
+    {
+      "epoch": 5.510067114093959,
+      "grad_norm": 0.22779090702533722,
+      "learning_rate": 4.575228012674118e-05,
+      "loss": 0.155,
+      "num_input_tokens_seen": 10818288,
+      "step": 209
+    },
+    {
+      "epoch": 5.5369127516778525,
+      "grad_norm": 0.18574051558971405,
+      "learning_rate": 4.571274123109606e-05,
+      "loss": 0.1514,
+      "num_input_tokens_seen": 10871488,
+      "step": 210
+    },
+    {
+      "epoch": 5.563758389261745,
+      "grad_norm": 0.20689000189304352,
+      "learning_rate": 4.5673036418378006e-05,
+      "loss": 0.1645,
+      "num_input_tokens_seen": 10925024,
+      "step": 211
+    },
+    {
+      "epoch": 5.590604026845638,
+      "grad_norm": 0.20517326891422272,
+      "learning_rate": 4.563316600663795e-05,
+      "loss": 0.1532,
+      "num_input_tokens_seen": 10982200,
+      "step": 212
+    },
+    {
+      "epoch": 5.617449664429531,
+      "grad_norm": 0.19169899821281433,
+      "learning_rate": 4.559313031525331e-05,
+      "loss": 0.1754,
+      "num_input_tokens_seen": 11029976,
+      "step": 213
+    },
+    {
+      "epoch": 5.644295302013423,
+      "grad_norm": 0.19880560040473938,
+      "learning_rate": 4.555292966492547e-05,
+      "loss": 0.1611,
+      "num_input_tokens_seen": 11085192,
+      "step": 214
+    },
+    {
+      "epoch": 5.671140939597316,
+      "grad_norm": 0.2045927792787552,
+      "learning_rate": 4.551256437767719e-05,
+      "loss": 0.1856,
+      "num_input_tokens_seen": 11132072,
+      "step": 215
+    },
+    {
+      "epoch": 5.697986577181208,
+      "grad_norm": 0.18255843222141266,
+      "learning_rate": 4.547203477685005e-05,
+      "loss": 0.1658,
+      "num_input_tokens_seen": 11195808,
+      "step": 216
+    },
+    {
+      "epoch": 5.724832214765101,
+      "grad_norm": 0.19551897048950195,
+      "learning_rate": 4.543134118710184e-05,
+      "loss": 0.1649,
+      "num_input_tokens_seen": 11244688,
+      "step": 217
+    },
+    {
+      "epoch": 5.751677852348993,
+      "grad_norm": 0.19608667492866516,
+      "learning_rate": 4.539048393440395e-05,
+      "loss": 0.1582,
+      "num_input_tokens_seen": 11298888,
+      "step": 218
+    },
+    {
+      "epoch": 5.778523489932886,
+      "grad_norm": 0.2286413460969925,
+      "learning_rate": 4.534946334603879e-05,
+      "loss": 0.1624,
+      "num_input_tokens_seen": 11345304,
+      "step": 219
+    },
+    {
+      "epoch": 5.805369127516778,
+      "grad_norm": 0.21048720180988312,
+      "learning_rate": 4.530827975059715e-05,
+      "loss": 0.1548,
+      "num_input_tokens_seen": 11387752,
+      "step": 220
+    },
+    {
+      "epoch": 5.832214765100671,
+      "grad_norm": 0.1970525085926056,
+      "learning_rate": 4.526693347797557e-05,
+      "loss": 0.1478,
+      "num_input_tokens_seen": 11432728,
+      "step": 221
+    },
+    {
+      "epoch": 5.859060402684563,
+      "grad_norm": 0.18459273874759674,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.1313,
+      "num_input_tokens_seen": 11493064,
+      "step": 222
+    },
+    {
+      "epoch": 5.885906040268456,
+      "grad_norm": 0.22195135056972504,
+      "learning_rate": 4.518375422729161e-05,
+      "loss": 0.1719,
+      "num_input_tokens_seen": 11542392,
+      "step": 223
+    },
+    {
+      "epoch": 5.912751677852349,
+      "grad_norm": 0.21980145573616028,
+      "learning_rate": 4.5141921915527216e-05,
+      "loss": 0.1587,
+      "num_input_tokens_seen": 11596408,
+      "step": 224
+    },
+    {
+      "epoch": 5.939597315436242,
+      "grad_norm": 0.21877101063728333,
+      "learning_rate": 4.5099928259173516e-05,
+      "loss": 0.1751,
+      "num_input_tokens_seen": 11657288,
+      "step": 225
+    },
+    {
+      "epoch": 5.966442953020135,
+      "grad_norm": 0.21569234132766724,
+      "learning_rate": 4.505777359461595e-05,
+      "loss": 0.1532,
+      "num_input_tokens_seen": 11714680,
+      "step": 226
+    },
+    {
+      "epoch": 5.993288590604027,
+      "grad_norm": 0.2067164033651352,
+      "learning_rate": 4.50154582595297e-05,
+      "loss": 0.1638,
+      "num_input_tokens_seen": 11751840,
+      "step": 227
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.31630751490592957,
+      "learning_rate": 4.497298259287696e-05,
+      "loss": 0.118,
+      "num_input_tokens_seen": 11770848,
+      "step": 228
+    },
+    {
+      "epoch": 6.026845637583893,
+      "grad_norm": 0.2094467580318451,
+      "learning_rate": 4.493034693490427e-05,
+      "loss": 0.1428,
+      "num_input_tokens_seen": 11821848,
+      "step": 229
+    },
+    {
+      "epoch": 6.053691275167785,
+      "grad_norm": 0.20361250638961792,
+      "learning_rate": 4.488755162713975e-05,
+      "loss": 0.1504,
+      "num_input_tokens_seen": 11869152,
+      "step": 230
+    },
+    {
+      "epoch": 6.080536912751678,
+      "grad_norm": 0.22751058638095856,
+      "learning_rate": 4.484459701239038e-05,
+      "loss": 0.161,
+      "num_input_tokens_seen": 11917464,
+      "step": 231
+    },
+    {
+      "epoch": 6.10738255033557,
+      "grad_norm": 0.21245698630809784,
+      "learning_rate": 4.480148343473923e-05,
+      "loss": 0.1354,
+      "num_input_tokens_seen": 11962184,
+      "step": 232
+    },
+    {
+      "epoch": 6.134228187919463,
+      "grad_norm": 0.2415906935930252,
+      "learning_rate": 4.475821123954275e-05,
+      "loss": 0.1328,
+      "num_input_tokens_seen": 12005088,
+      "step": 233
+    },
+    {
+      "epoch": 6.1610738255033555,
+      "grad_norm": 0.22683894634246826,
+      "learning_rate": 4.471478077342798e-05,
+      "loss": 0.1532,
+      "num_input_tokens_seen": 12058808,
+      "step": 234
+    },
+    {
+      "epoch": 6.1879194630872485,
+      "grad_norm": 0.22128812968730927,
+      "learning_rate": 4.467119238428975e-05,
+      "loss": 0.1316,
+      "num_input_tokens_seen": 12126248,
+      "step": 235
+    },
+    {
+      "epoch": 6.214765100671141,
+      "grad_norm": 0.19066843390464783,
+      "learning_rate": 4.4627446421287935e-05,
+      "loss": 0.1279,
+      "num_input_tokens_seen": 12186960,
+      "step": 236
+    },
+    {
+      "epoch": 6.241610738255034,
+      "grad_norm": 0.21822784841060638,
+      "learning_rate": 4.4583543234844616e-05,
+      "loss": 0.1389,
+      "num_input_tokens_seen": 12246416,
+      "step": 237
+    },
+    {
+      "epoch": 6.268456375838926,
+      "grad_norm": 0.3152228593826294,
+      "learning_rate": 4.4539483176641304e-05,
+      "loss": 0.1439,
+      "num_input_tokens_seen": 12301360,
+      "step": 238
+    },
+    {
+      "epoch": 6.295302013422819,
+      "grad_norm": 0.2345726042985916,
+      "learning_rate": 4.4495266599616136e-05,
+      "loss": 0.1386,
+      "num_input_tokens_seen": 12347960,
+      "step": 239
+    },
+    {
+      "epoch": 6.322147651006711,
+      "grad_norm": 0.27413222193717957,
+      "learning_rate": 4.445089385796099e-05,
+      "loss": 0.1562,
+      "num_input_tokens_seen": 12399640,
+      "step": 240
+    },
+    {
+      "epoch": 6.348993288590604,
+      "grad_norm": 0.21653778851032257,
+      "learning_rate": 4.4406365307118703e-05,
+      "loss": 0.1364,
+      "num_input_tokens_seen": 12451256,
+      "step": 241
+    },
+    {
+      "epoch": 6.375838926174497,
+      "grad_norm": 0.21994851529598236,
+      "learning_rate": 4.4361681303780195e-05,
+      "loss": 0.1404,
+      "num_input_tokens_seen": 12497184,
+      "step": 242
+    },
+    {
+      "epoch": 6.402684563758389,
+      "grad_norm": 0.20164069533348083,
+      "learning_rate": 4.431684220588163e-05,
+      "loss": 0.1622,
+      "num_input_tokens_seen": 12551512,
+      "step": 243
+    },
+    {
+      "epoch": 6.429530201342282,
+      "grad_norm": 0.23192667961120605,
+      "learning_rate": 4.427184837260153e-05,
+      "loss": 0.1497,
+      "num_input_tokens_seen": 12595808,
+      "step": 244
+    },
+    {
+      "epoch": 6.456375838926174,
+      "grad_norm": 0.22512899339199066,
+      "learning_rate": 4.422670016435792e-05,
+      "loss": 0.1504,
+      "num_input_tokens_seen": 12649504,
+      "step": 245
+    },
+    {
+      "epoch": 6.483221476510067,
+      "grad_norm": 0.2125946432352066,
+      "learning_rate": 4.418139794280541e-05,
+      "loss": 0.129,
+      "num_input_tokens_seen": 12694312,
+      "step": 246
+    },
+    {
+      "epoch": 6.510067114093959,
+      "grad_norm": 0.2329980880022049,
+      "learning_rate": 4.413594207083234e-05,
+      "loss": 0.1363,
+      "num_input_tokens_seen": 12741872,
+      "step": 247
+    },
+    {
+      "epoch": 6.5369127516778525,
+      "grad_norm": 0.23576146364212036,
+      "learning_rate": 4.409033291255782e-05,
+      "loss": 0.1325,
+      "num_input_tokens_seen": 12799032,
+      "step": 248
+    },
+    {
+      "epoch": 6.563758389261745,
+      "grad_norm": 0.3069142997264862,
+      "learning_rate": 4.404457083332886e-05,
+      "loss": 0.1501,
+      "num_input_tokens_seen": 12860432,
+      "step": 249
+    },
+    {
+      "epoch": 6.590604026845638,
+      "grad_norm": 0.24110864102840424,
+      "learning_rate": 4.3998656199717435e-05,
+      "loss": 0.1375,
+      "num_input_tokens_seen": 12906592,
+      "step": 250
+    },
+    {
+      "epoch": 6.617449664429531,
+      "grad_norm": 0.2534135580062866,
+      "learning_rate": 4.395258937951753e-05,
+      "loss": 0.1387,
+      "num_input_tokens_seen": 12966808,
+      "step": 251
+    },
+    {
+      "epoch": 6.644295302013423,
+      "grad_norm": 0.20937450230121613,
+      "learning_rate": 4.3906370741742186e-05,
+      "loss": 0.1627,
+      "num_input_tokens_seen": 13026504,
+      "step": 252
+    },
+    {
+      "epoch": 6.671140939597316,
+      "grad_norm": 0.2298954874277115,
+      "learning_rate": 4.386000065662059e-05,
+      "loss": 0.1509,
+      "num_input_tokens_seen": 13070176,
+      "step": 253
+    },
+    {
+      "epoch": 6.697986577181208,
+      "grad_norm": 0.22058549523353577,
+      "learning_rate": 4.381347949559506e-05,
+      "loss": 0.1298,
+      "num_input_tokens_seen": 13126104,
+      "step": 254
+    },
+    {
+      "epoch": 6.724832214765101,
+      "grad_norm": 0.22921989858150482,
+      "learning_rate": 4.3766807631318106e-05,
+      "loss": 0.1396,
+      "num_input_tokens_seen": 13178312,
+      "step": 255
+    },
+    {
+      "epoch": 6.751677852348993,
+      "grad_norm": 0.20291879773139954,
+      "learning_rate": 4.371998543764943e-05,
+      "loss": 0.1206,
+      "num_input_tokens_seen": 13236216,
+      "step": 256
+    },
+    {
+      "epoch": 6.778523489932886,
+      "grad_norm": 0.1957395225763321,
+      "learning_rate": 4.367301328965291e-05,
+      "loss": 0.1168,
+      "num_input_tokens_seen": 13291752,
+      "step": 257
+    },
+    {
+      "epoch": 6.805369127516778,
+      "grad_norm": 0.241806298494339,
+      "learning_rate": 4.3625891563593626e-05,
+      "loss": 0.1435,
+      "num_input_tokens_seen": 13349872,
+      "step": 258
+    },
+    {
+      "epoch": 6.832214765100671,
+      "grad_norm": 0.2894677519798279,
+      "learning_rate": 4.357862063693486e-05,
+      "loss": 0.1216,
+      "num_input_tokens_seen": 13406328,
+      "step": 259
+    },
+    {
+      "epoch": 6.859060402684563,
+      "grad_norm": 0.21700353920459747,
+      "learning_rate": 4.353120088833501e-05,
+      "loss": 0.1269,
+      "num_input_tokens_seen": 13459016,
+      "step": 260
+    },
+    {
+      "epoch": 6.885906040268456,
+      "grad_norm": 0.2301565408706665,
+      "learning_rate": 4.348363269764462e-05,
+      "loss": 0.1441,
+      "num_input_tokens_seen": 13505008,
+      "step": 261
+    },
+    {
+      "epoch": 6.912751677852349,
+      "grad_norm": 0.21690794825553894,
+      "learning_rate": 4.3435916445903296e-05,
+      "loss": 0.1136,
+      "num_input_tokens_seen": 13559976,
+      "step": 262
+    },
+    {
+      "epoch": 6.939597315436242,
+      "grad_norm": 0.2487451285123825,
+      "learning_rate": 4.3388052515336696e-05,
+      "loss": 0.1511,
+      "num_input_tokens_seen": 13608168,
+      "step": 263
+    },
+    {
+      "epoch": 6.966442953020135,
+      "grad_norm": 0.22782735526561737,
+      "learning_rate": 4.3340041289353415e-05,
+      "loss": 0.1307,
+      "num_input_tokens_seen": 13660808,
+      "step": 264
+    },
+    {
+      "epoch": 6.993288590604027,
+      "grad_norm": 0.23830646276474,
+      "learning_rate": 4.329188315254196e-05,
+      "loss": 0.1342,
+      "num_input_tokens_seen": 13716800,
+      "step": 265
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.3767189383506775,
+      "learning_rate": 4.324357849066764e-05,
+      "loss": 0.1316,
+      "num_input_tokens_seen": 13732656,
+      "step": 266
+    },
+    {
+      "epoch": 7.026845637583893,
+      "grad_norm": 0.22937406599521637,
+      "learning_rate": 4.319512769066949e-05,
+      "loss": 0.12,
+      "num_input_tokens_seen": 13772968,
+      "step": 267
+    },
+    {
+      "epoch": 7.053691275167785,
+      "grad_norm": 0.2137727588415146,
+      "learning_rate": 4.3146531140657176e-05,
+      "loss": 0.1223,
+      "num_input_tokens_seen": 13823688,
+      "step": 268
+    },
+    {
+      "epoch": 7.080536912751678,
+      "grad_norm": 0.2268005758523941,
+      "learning_rate": 4.309778922990786e-05,
+      "loss": 0.1282,
+      "num_input_tokens_seen": 13886264,
+      "step": 269
+    },
+    {
+      "epoch": 7.10738255033557,
+      "grad_norm": 0.2435617595911026,
+      "learning_rate": 4.3048902348863116e-05,
+      "loss": 0.1336,
+      "num_input_tokens_seen": 13944672,
+      "step": 270
+    },
+    {
+      "epoch": 7.134228187919463,
+      "grad_norm": 0.24664700031280518,
+      "learning_rate": 4.299987088912577e-05,
+      "loss": 0.121,
+      "num_input_tokens_seen": 13999968,
+      "step": 271
+    },
+    {
+      "epoch": 7.1610738255033555,
+      "grad_norm": 0.2270224392414093,
+      "learning_rate": 4.295069524345681e-05,
+      "loss": 0.1186,
+      "num_input_tokens_seen": 14054224,
+      "step": 272
+    },
+    {
+      "epoch": 7.1879194630872485,
+      "grad_norm": 0.2454068511724472,
+      "learning_rate": 4.290137580577216e-05,
+      "loss": 0.1355,
+      "num_input_tokens_seen": 14106328,
+      "step": 273
+    },
+    {
+      "epoch": 7.214765100671141,
+      "grad_norm": 0.250244140625,
+      "learning_rate": 4.285191297113962e-05,
+      "loss": 0.1239,
+      "num_input_tokens_seen": 14154608,
+      "step": 274
+    },
+    {
+      "epoch": 7.241610738255034,
+      "grad_norm": 0.24651585519313812,
+      "learning_rate": 4.280230713577564e-05,
+      "loss": 0.129,
+      "num_input_tokens_seen": 14207424,
+      "step": 275
+    },
+    {
+      "epoch": 7.268456375838926,
+      "grad_norm": 0.2339150756597519,
+      "learning_rate": 4.275255869704214e-05,
+      "loss": 0.117,
+      "num_input_tokens_seen": 14268200,
+      "step": 276
+    },
+    {
+      "epoch": 7.295302013422819,
+      "grad_norm": 0.2495085448026657,
+      "learning_rate": 4.2702668053443394e-05,
+      "loss": 0.1202,
+      "num_input_tokens_seen": 14319864,
+      "step": 277
+    },
+    {
+      "epoch": 7.322147651006711,
+      "grad_norm": 0.24790653586387634,
+      "learning_rate": 4.265263560462275e-05,
+      "loss": 0.1429,
+      "num_input_tokens_seen": 14370536,
+      "step": 278
+    },
+    {
+      "epoch": 7.348993288590604,
+      "grad_norm": 0.22188791632652283,
+      "learning_rate": 4.260246175135948e-05,
+      "loss": 0.1076,
+      "num_input_tokens_seen": 14431608,
+      "step": 279
+    },
+    {
+      "epoch": 7.375838926174497,
+      "grad_norm": 0.24197377264499664,
+      "learning_rate": 4.255214689556557e-05,
+      "loss": 0.109,
+      "num_input_tokens_seen": 14486360,
+      "step": 280
+    },
+    {
+      "epoch": 7.402684563758389,
+      "grad_norm": 0.26805874705314636,
+      "learning_rate": 4.2501691440282476e-05,
+      "loss": 0.121,
+      "num_input_tokens_seen": 14529160,
+      "step": 281
+    },
+    {
+      "epoch": 7.429530201342282,
+      "grad_norm": 0.27267780900001526,
+      "learning_rate": 4.2451095789677945e-05,
+      "loss": 0.1183,
+      "num_input_tokens_seen": 14573320,
+      "step": 282
+    },
+    {
+      "epoch": 7.456375838926174,
+      "grad_norm": 0.27364009618759155,
+      "learning_rate": 4.24003603490427e-05,
+      "loss": 0.1345,
+      "num_input_tokens_seen": 14628488,
+      "step": 283
+    },
+    {
+      "epoch": 7.483221476510067,
+      "grad_norm": 0.25592902302742004,
+      "learning_rate": 4.234948552478726e-05,
+      "loss": 0.1195,
+      "num_input_tokens_seen": 14670808,
+      "step": 284
+    },
+    {
+      "epoch": 7.510067114093959,
+      "grad_norm": 0.2379164844751358,
+      "learning_rate": 4.229847172443866e-05,
+      "loss": 0.1245,
+      "num_input_tokens_seen": 14716336,
+      "step": 285
+    },
+    {
+      "epoch": 7.5369127516778525,
+      "grad_norm": 0.237826868891716,
+      "learning_rate": 4.2247319356637174e-05,
+      "loss": 0.1456,
+      "num_input_tokens_seen": 14786728,
+      "step": 286
+    },
+    {
+      "epoch": 7.563758389261745,
+      "grad_norm": 0.3425538241863251,
+      "learning_rate": 4.219602883113306e-05,
+      "loss": 0.1158,
+      "num_input_tokens_seen": 14839744,
+      "step": 287
+    },
+    {
+      "epoch": 7.590604026845638,
+      "grad_norm": 0.25014984607696533,
+      "learning_rate": 4.214460055878329e-05,
+      "loss": 0.1049,
+      "num_input_tokens_seen": 14891016,
+      "step": 288
+    },
+    {
+      "epoch": 7.617449664429531,
+      "grad_norm": 0.2666330337524414,
+      "learning_rate": 4.209303495154822e-05,
+      "loss": 0.1165,
+      "num_input_tokens_seen": 14948496,
+      "step": 289
+    },
+    {
+      "epoch": 7.644295302013423,
+      "grad_norm": 0.26408740878105164,
+      "learning_rate": 4.204133242248832e-05,
+      "loss": 0.12,
+      "num_input_tokens_seen": 15001096,
+      "step": 290
+    },
+    {
+      "epoch": 7.671140939597316,
+      "grad_norm": 0.4048908054828644,
+      "learning_rate": 4.1989493385760864e-05,
+      "loss": 0.1135,
+      "num_input_tokens_seen": 15064648,
+      "step": 291
+    },
+    {
+      "epoch": 7.697986577181208,
+      "grad_norm": 0.2592375576496124,
+      "learning_rate": 4.193751825661658e-05,
+      "loss": 0.1081,
+      "num_input_tokens_seen": 15106280,
+      "step": 292
+    },
+    {
+      "epoch": 7.724832214765101,
+      "grad_norm": 0.270054429769516,
+      "learning_rate": 4.188540745139638e-05,
+      "loss": 0.1251,
+      "num_input_tokens_seen": 15142096,
+      "step": 293
+    },
+    {
+      "epoch": 7.751677852348993,
+      "grad_norm": 0.21358565986156464,
+      "learning_rate": 4.1833161387527986e-05,
+      "loss": 0.1018,
+      "num_input_tokens_seen": 15213520,
+      "step": 294
+    },
+    {
+      "epoch": 7.778523489932886,
+      "grad_norm": 0.25034505128860474,
+      "learning_rate": 4.1780780483522575e-05,
+      "loss": 0.1049,
+      "num_input_tokens_seen": 15269304,
+      "step": 295
+    },
+    {
+      "epoch": 7.805369127516778,
+      "grad_norm": 0.2544301450252533,
+      "learning_rate": 4.172826515897146e-05,
+      "loss": 0.1171,
+      "num_input_tokens_seen": 15322184,
+      "step": 296
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1110,
+  "num_input_tokens_seen": 15322184,
+  "num_train_epochs": 30,
+  "save_steps": 37,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2926050701976535e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-333/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-333/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-333/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ef05967e5f48aca96f144841f47ddb247cedd722f7357a2981fa402cbf9327
+size 275341720

checkpoint-333/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
+}

checkpoint-333/special_tokens_map.json

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

checkpoint-333/tokenizer.json

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