Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-3B-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

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-3B-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8709b9ca2bddb2fff8bd6dcc173d6abdd5c030bafbbb31dba7945c15f44b6044
+size 119809824

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-1400/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-3B-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-1400/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-3B-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8709b9ca2bddb2fff8bd6dcc173d6abdd5c030bafbbb31dba7945c15f44b6044
+size 119809824

checkpoint-1400/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-1400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8458c87d6c9e6854104639bb00454232b98d6f1745fefa2c462b1c368d6f2832
+size 239910077

checkpoint-1400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479643527c9a2d98eacfe4c1fa7a1399d67a89724035041366c6883822ce14c8
+size 14244

checkpoint-1400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672552e85582143422da5f3bc23acff3f68526498bef2c72ad1377acf0ae81e5
+size 1064

checkpoint-1400/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

checkpoint-1400/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1400/trainer_state.json

@@ -0,0 +1,1076 @@
+{
+  "best_metric": 0.6909542083740234,
+  "best_model_checkpoint": "/workspace/rm/rm_adapter/checkpoint-1400",
+  "epoch": 2.121212121212121,
+  "eval_steps": 200,
+  "global_step": 1400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015151515151515152,
+      "grad_norm": 3.026841640472412,
+      "learning_rate": 2e-05,
+      "loss": 0.6999,
+      "step": 10
+    },
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 2.487321138381958,
+      "learning_rate": 4e-05,
+      "loss": 0.6998,
+      "step": 20
+    },
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 2.6206929683685303,
+      "learning_rate": 6e-05,
+      "loss": 0.6957,
+      "step": 30
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 1.7623201608657837,
+      "learning_rate": 8e-05,
+      "loss": 0.6922,
+      "step": 40
+    },
+    {
+      "epoch": 0.07575757575757576,
+      "grad_norm": 1.821882724761963,
+      "learning_rate": 0.0001,
+      "loss": 0.695,
+      "step": 50
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 2.205653190612793,
+      "learning_rate": 9.99933760728612e-05,
+      "loss": 0.7181,
+      "step": 60
+    },
+    {
+      "epoch": 0.10606060606060606,
+      "grad_norm": 2.080017328262329,
+      "learning_rate": 9.997350604650123e-05,
+      "loss": 0.6952,
+      "step": 70
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 2.1524713039398193,
+      "learning_rate": 9.994039518562432e-05,
+      "loss": 0.6938,
+      "step": 80
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 2.467346668243408,
+      "learning_rate": 9.989405226318772e-05,
+      "loss": 0.6988,
+      "step": 90
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 2.5009102821350098,
+      "learning_rate": 9.983448955807708e-05,
+      "loss": 0.6819,
+      "step": 100
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 2.6343142986297607,
+      "learning_rate": 9.976172285185314e-05,
+      "loss": 0.6891,
+      "step": 110
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.9957756996154785,
+      "learning_rate": 9.967577142457032e-05,
+      "loss": 0.7024,
+      "step": 120
+    },
+    {
+      "epoch": 0.19696969696969696,
+      "grad_norm": 2.6430771350860596,
+      "learning_rate": 9.957665804966829e-05,
+      "loss": 0.7012,
+      "step": 130
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 2.6395034790039062,
+      "learning_rate": 9.946440898793801e-05,
+      "loss": 0.6826,
+      "step": 140
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 2.5003907680511475,
+      "learning_rate": 9.933905398056372e-05,
+      "loss": 0.7,
+      "step": 150
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 2.4217541217803955,
+      "learning_rate": 9.920062624124282e-05,
+      "loss": 0.6932,
+      "step": 160
+    },
+    {
+      "epoch": 0.25757575757575757,
+      "grad_norm": 3.947263240814209,
+      "learning_rate": 9.904916244738571e-05,
+      "loss": 0.7003,
+      "step": 170
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 3.162750244140625,
+      "learning_rate": 9.888470273039775e-05,
+      "loss": 0.6756,
+      "step": 180
+    },
+    {
+      "epoch": 0.2878787878787879,
+      "grad_norm": 2.7067689895629883,
+      "learning_rate": 9.870729066504629e-05,
+      "loss": 0.7031,
+      "step": 190
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 3.415238618850708,
+      "learning_rate": 9.851697325791505e-05,
+      "loss": 0.6888,
+      "step": 200
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "eval_accuracy": 0.7482014388489209,
+      "eval_loss": 0.6937351822853088,
+      "eval_runtime": 19.5228,
+      "eval_samples_per_second": 14.24,
+      "eval_steps_per_second": 1.793,
+      "step": 200
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 3.3440141677856445,
+      "learning_rate": 9.831380093494957e-05,
+      "loss": 0.6784,
+      "step": 210
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.1289377212524414,
+      "learning_rate": 9.809782752809644e-05,
+      "loss": 0.7005,
+      "step": 220
+    },
+    {
+      "epoch": 0.3484848484848485,
+      "grad_norm": 4.689096927642822,
+      "learning_rate": 9.786911026104007e-05,
+      "loss": 0.7015,
+      "step": 230
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 3.6249144077301025,
+      "learning_rate": 9.762770973404094e-05,
+      "loss": 0.6818,
+      "step": 240
+    },
+    {
+      "epoch": 0.3787878787878788,
+      "grad_norm": 3.3653128147125244,
+      "learning_rate": 9.737368990787916e-05,
+      "loss": 0.706,
+      "step": 250
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 3.5432941913604736,
+      "learning_rate": 9.710711808690754e-05,
+      "loss": 0.7136,
+      "step": 260
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 3.5209529399871826,
+      "learning_rate": 9.682806490121885e-05,
+      "loss": 0.7134,
+      "step": 270
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 2.654764413833618,
+      "learning_rate": 9.653660428793188e-05,
+      "loss": 0.714,
+      "step": 280
+    },
+    {
+      "epoch": 0.4393939393939394,
+      "grad_norm": 6.175410747528076,
+      "learning_rate": 9.623281347160127e-05,
+      "loss": 0.7095,
+      "step": 290
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 2.3064019680023193,
+      "learning_rate": 9.591677294375636e-05,
+      "loss": 0.6922,
+      "step": 300
+    },
+    {
+      "epoch": 0.4696969696969697,
+      "grad_norm": 2.248598337173462,
+      "learning_rate": 9.558856644157432e-05,
+      "loss": 0.6999,
+      "step": 310
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 2.52163028717041,
+      "learning_rate": 9.52482809256934e-05,
+      "loss": 0.7185,
+      "step": 320
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.9855085611343384,
+      "learning_rate": 9.489600655717217e-05,
+      "loss": 0.7,
+      "step": 330
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 2.6163477897644043,
+      "learning_rate": 9.453183667360062e-05,
+      "loss": 0.6893,
+      "step": 340
+    },
+    {
+      "epoch": 0.5303030303030303,
+      "grad_norm": 2.32633900642395,
+      "learning_rate": 9.415586776436973e-05,
+      "loss": 0.7029,
+      "step": 350
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 2.0239343643188477,
+      "learning_rate": 9.376819944510598e-05,
+      "loss": 0.6859,
+      "step": 360
+    },
+    {
+      "epoch": 0.5606060606060606,
+      "grad_norm": 2.0154311656951904,
+      "learning_rate": 9.336893443127738e-05,
+      "loss": 0.6942,
+      "step": 370
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 2.040499210357666,
+      "learning_rate": 9.295817851097837e-05,
+      "loss": 0.6988,
+      "step": 380
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 2.244065999984741,
+      "learning_rate": 9.253604051690046e-05,
+      "loss": 0.6984,
+      "step": 390
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 2.4374303817749023,
+      "learning_rate": 9.210263229749626e-05,
+      "loss": 0.6863,
+      "step": 400
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "eval_accuracy": 0.697841726618705,
+      "eval_loss": 0.6917553544044495,
+      "eval_runtime": 19.5084,
+      "eval_samples_per_second": 14.25,
+      "eval_steps_per_second": 1.794,
+      "step": 400
+    },
+    {
+      "epoch": 0.6212121212121212,
+      "grad_norm": 2.305253505706787,
+      "learning_rate": 9.165806868734444e-05,
+      "loss": 0.7048,
+      "step": 410
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 2.419456720352173,
+      "learning_rate": 9.120246747672347e-05,
+      "loss": 0.7059,
+      "step": 420
+    },
+    {
+      "epoch": 0.6515151515151515,
+      "grad_norm": 2.2635741233825684,
+      "learning_rate": 9.073594938040231e-05,
+      "loss": 0.6961,
+      "step": 430
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.824849843978882,
+      "learning_rate": 9.025863800565613e-05,
+      "loss": 0.7004,
+      "step": 440
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 2.1357405185699463,
+      "learning_rate": 8.977065981951566e-05,
+      "loss": 0.6968,
+      "step": 450
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 3.1660122871398926,
+      "learning_rate": 8.927214411525895e-05,
+      "loss": 0.702,
+      "step": 460
+    },
+    {
+      "epoch": 0.7121212121212122,
+      "grad_norm": 2.296741247177124,
+      "learning_rate": 8.876322297815405e-05,
+      "loss": 0.7001,
+      "step": 470
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 1.987774133682251,
+      "learning_rate": 8.824403125046225e-05,
+      "loss": 0.6947,
+      "step": 480
+    },
+    {
+      "epoch": 0.7424242424242424,
+      "grad_norm": 2.645599603652954,
+      "learning_rate": 8.771470649571056e-05,
+      "loss": 0.7026,
+      "step": 490
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 2.0273940563201904,
+      "learning_rate": 8.717538896224332e-05,
+      "loss": 0.703,
+      "step": 500
+    },
+    {
+      "epoch": 0.7727272727272727,
+      "grad_norm": 6.725697994232178,
+      "learning_rate": 8.662622154606237e-05,
+      "loss": 0.685,
+      "step": 510
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 1.968575358390808,
+      "learning_rate": 8.606734975296578e-05,
+      "loss": 0.7042,
+      "step": 520
+    },
+    {
+      "epoch": 0.803030303030303,
+      "grad_norm": 2.2325947284698486,
+      "learning_rate": 8.549892165999505e-05,
+      "loss": 0.69,
+      "step": 530
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 2.3587887287139893,
+      "learning_rate": 8.492108787620105e-05,
+      "loss": 0.6987,
+      "step": 540
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.0664846897125244,
+      "learning_rate": 8.433400150273906e-05,
+      "loss": 0.708,
+      "step": 550
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 4.4357147216796875,
+      "learning_rate": 8.373781809230355e-05,
+      "loss": 0.6981,
+      "step": 560
+    },
+    {
+      "epoch": 0.8636363636363636,
+      "grad_norm": 2.435680627822876,
+      "learning_rate": 8.313269560791342e-05,
+      "loss": 0.7105,
+      "step": 570
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 2.5096144676208496,
+      "learning_rate": 8.251879438105854e-05,
+      "loss": 0.6897,
+      "step": 580
+    },
+    {
+      "epoch": 0.8939393939393939,
+      "grad_norm": 1.9323264360427856,
+      "learning_rate": 8.189627706921877e-05,
+      "loss": 0.6746,
+      "step": 590
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 2.3687186241149902,
+      "learning_rate": 8.126530861276677e-05,
+      "loss": 0.6847,
+      "step": 600
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "eval_accuracy": 0.5935251798561151,
+      "eval_loss": 0.6970531344413757,
+      "eval_runtime": 19.5244,
+      "eval_samples_per_second": 14.239,
+      "eval_steps_per_second": 1.793,
+      "step": 600
+    },
+    {
+      "epoch": 0.9242424242424242,
+      "grad_norm": 2.470337152481079,
+      "learning_rate": 8.062605619126584e-05,
+      "loss": 0.6787,
+      "step": 610
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 2.8660871982574463,
+      "learning_rate": 7.997868917917453e-05,
+      "loss": 0.6958,
+      "step": 620
+    },
+    {
+      "epoch": 0.9545454545454546,
+      "grad_norm": 3.2916390895843506,
+      "learning_rate": 7.932337910096961e-05,
+      "loss": 0.7024,
+      "step": 630
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 2.203716278076172,
+      "learning_rate": 7.866029958569956e-05,
+      "loss": 0.6858,
+      "step": 640
+    },
+    {
+      "epoch": 0.9848484848484849,
+      "grad_norm": 2.21602463722229,
+      "learning_rate": 7.798962632098024e-05,
+      "loss": 0.7044,
+      "step": 650
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9984266757965088,
+      "learning_rate": 7.73115370064452e-05,
+      "loss": 0.696,
+      "step": 660
+    },
+    {
+      "epoch": 1.0151515151515151,
+      "grad_norm": 2.6973960399627686,
+      "learning_rate": 7.6626211306663e-05,
+      "loss": 0.6972,
+      "step": 670
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 2.1271116733551025,
+      "learning_rate": 7.59338308035337e-05,
+      "loss": 0.6862,
+      "step": 680
+    },
+    {
+      "epoch": 1.0454545454545454,
+      "grad_norm": 2.1646666526794434,
+      "learning_rate": 7.523457894817745e-05,
+      "loss": 0.6957,
+      "step": 690
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 2.122968912124634,
+      "learning_rate": 7.452864101232798e-05,
+      "loss": 0.6931,
+      "step": 700
+    },
+    {
+      "epoch": 1.0757575757575757,
+      "grad_norm": 2.318418502807617,
+      "learning_rate": 7.381620403924333e-05,
+      "loss": 0.6833,
+      "step": 710
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 2.31949782371521,
+      "learning_rate": 7.30974567941475e-05,
+      "loss": 0.6866,
+      "step": 720
+    },
+    {
+      "epoch": 1.106060606060606,
+      "grad_norm": 2.116624355316162,
+      "learning_rate": 7.237258971421587e-05,
+      "loss": 0.6976,
+      "step": 730
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 2.1707992553710938,
+      "learning_rate": 7.164179485811727e-05,
+      "loss": 0.6932,
+      "step": 740
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 2.0329554080963135,
+      "learning_rate": 7.090526585512696e-05,
+      "loss": 0.6872,
+      "step": 750
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 2.590719223022461,
+      "learning_rate": 7.016319785382296e-05,
+      "loss": 0.7154,
+      "step": 760
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 2.158923387527466,
+      "learning_rate": 6.941578747038023e-05,
+      "loss": 0.6906,
+      "step": 770
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 3.0064737796783447,
+      "learning_rate": 6.866323273647563e-05,
+      "loss": 0.6955,
+      "step": 780
+    },
+    {
+      "epoch": 1.196969696969697,
+      "grad_norm": 2.0017855167388916,
+      "learning_rate": 6.79057330468182e-05,
+      "loss": 0.6854,
+      "step": 790
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 3.6152710914611816,
+      "learning_rate": 6.7143489106318e-05,
+      "loss": 0.698,
+      "step": 800
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "eval_accuracy": 0.5935251798561151,
+      "eval_loss": 0.6945483684539795,
+      "eval_runtime": 19.5034,
+      "eval_samples_per_second": 14.254,
+      "eval_steps_per_second": 1.795,
+      "step": 800
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "grad_norm": 1.9689804315567017,
+      "learning_rate": 6.637670287690799e-05,
+      "loss": 0.7115,
+      "step": 810
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 4.077113151550293,
+      "learning_rate": 6.560557752403277e-05,
+      "loss": 0.6883,
+      "step": 820
+    },
+    {
+      "epoch": 1.2575757575757576,
+      "grad_norm": 2.2839391231536865,
+      "learning_rate": 6.483031736281843e-05,
+      "loss": 0.6972,
+      "step": 830
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 1.9423472881317139,
+      "learning_rate": 6.40511278039378e-05,
+      "loss": 0.701,
+      "step": 840
+    },
+    {
+      "epoch": 1.2878787878787878,
+      "grad_norm": 2.111860752105713,
+      "learning_rate": 6.326821529918553e-05,
+      "loss": 0.7023,
+      "step": 850
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 1.9913779497146606,
+      "learning_rate": 6.248178728677711e-05,
+      "loss": 0.7014,
+      "step": 860
+    },
+    {
+      "epoch": 1.3181818181818181,
+      "grad_norm": 1.9043771028518677,
+      "learning_rate": 6.16920521363867e-05,
+      "loss": 0.6891,
+      "step": 870
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 2.018148899078369,
+      "learning_rate": 6.089921909393812e-05,
+      "loss": 0.6969,
+      "step": 880
+    },
+    {
+      "epoch": 1.3484848484848486,
+      "grad_norm": 1.8589205741882324,
+      "learning_rate": 6.0103498226163603e-05,
+      "loss": 0.6982,
+      "step": 890
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 1.8796669244766235,
+      "learning_rate": 5.93051003649452e-05,
+      "loss": 0.6787,
+      "step": 900
+    },
+    {
+      "epoch": 1.378787878787879,
+      "grad_norm": 2.0444390773773193,
+      "learning_rate": 5.850423705145334e-05,
+      "loss": 0.6934,
+      "step": 910
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 2.5297834873199463,
+      "learning_rate": 5.770112048009747e-05,
+      "loss": 0.7092,
+      "step": 920
+    },
+    {
+      "epoch": 1.4090909090909092,
+      "grad_norm": 1.9327147006988525,
+      "learning_rate": 5.68959634423037e-05,
+      "loss": 0.6951,
+      "step": 930
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 1.8969117403030396,
+      "learning_rate": 5.60889792701342e-05,
+      "loss": 0.7045,
+      "step": 940
+    },
+    {
+      "epoch": 1.4393939393939394,
+      "grad_norm": 2.584240198135376,
+      "learning_rate": 5.52803817797633e-05,
+      "loss": 0.6734,
+      "step": 950
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 2.54909086227417,
+      "learning_rate": 5.4470385214825416e-05,
+      "loss": 0.6727,
+      "step": 960
+    },
+    {
+      "epoch": 1.4696969696969697,
+      "grad_norm": 2.040754556655884,
+      "learning_rate": 5.365920418964973e-05,
+      "loss": 0.688,
+      "step": 970
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 2.1792185306549072,
+      "learning_rate": 5.28470536323965e-05,
+      "loss": 0.6911,
+      "step": 980
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.115302562713623,
+      "learning_rate": 5.2034148728110424e-05,
+      "loss": 0.6942,
+      "step": 990
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 6.179975509643555,
+      "learning_rate": 5.1220704861705774e-05,
+      "loss": 0.6945,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "eval_accuracy": 0.4460431654676259,
+      "eval_loss": 0.7005228996276855,
+      "eval_runtime": 19.5262,
+      "eval_samples_per_second": 14.237,
+      "eval_steps_per_second": 1.792,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5303030303030303,
+      "grad_norm": 2.1656877994537354,
+      "learning_rate": 5.0406937560898646e-05,
+      "loss": 0.694,
+      "step": 1010
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 2.0086238384246826,
+      "learning_rate": 4.9593062439101365e-05,
+      "loss": 0.683,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5606060606060606,
+      "grad_norm": 2.685886859893799,
+      "learning_rate": 4.877929513829424e-05,
+      "loss": 0.6927,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 2.2931978702545166,
+      "learning_rate": 4.796585127188958e-05,
+      "loss": 0.6943,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 1.9456837177276611,
+      "learning_rate": 4.715294636760352e-05,
+      "loss": 0.7238,
+      "step": 1050
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 1.9456251859664917,
+      "learning_rate": 4.634079581035029e-05,
+      "loss": 0.6867,
+      "step": 1060
+    },
+    {
+      "epoch": 1.621212121212121,
+      "grad_norm": 1.8919247388839722,
+      "learning_rate": 4.55296147851746e-05,
+      "loss": 0.6679,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 2.3800299167633057,
+      "learning_rate": 4.471961822023671e-05,
+      "loss": 0.6932,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6515151515151514,
+      "grad_norm": 2.1245882511138916,
+      "learning_rate": 4.391102072986581e-05,
+      "loss": 0.6823,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.484229326248169,
+      "learning_rate": 4.3104036557696295e-05,
+      "loss": 0.7094,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6818181818181817,
+      "grad_norm": 2.081204652786255,
+      "learning_rate": 4.229887951990255e-05,
+      "loss": 0.6873,
+      "step": 1110
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 2.008754253387451,
+      "learning_rate": 4.149576294854668e-05,
+      "loss": 0.6957,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7121212121212122,
+      "grad_norm": 2.088444948196411,
+      "learning_rate": 4.069489963505482e-05,
+      "loss": 0.7134,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 2.0371851921081543,
+      "learning_rate": 3.98965017738364e-05,
+      "loss": 0.698,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7424242424242424,
+      "grad_norm": 2.4857864379882812,
+      "learning_rate": 3.9100780906061896e-05,
+      "loss": 0.702,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 1.9480881690979004,
+      "learning_rate": 3.83079478636133e-05,
+      "loss": 0.6875,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7727272727272727,
+      "grad_norm": 2.094036817550659,
+      "learning_rate": 3.7518212713222906e-05,
+      "loss": 0.7047,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 2.085651159286499,
+      "learning_rate": 3.673178470081448e-05,
+      "loss": 0.6933,
+      "step": 1180
+    },
+    {
+      "epoch": 1.803030303030303,
+      "grad_norm": 2.0030457973480225,
+      "learning_rate": 3.594887219606221e-05,
+      "loss": 0.6901,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 2.7572779655456543,
+      "learning_rate": 3.516968263718159e-05,
+      "loss": 0.6808,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_accuracy": 0.5755395683453237,
+      "eval_loss": 0.6959903836250305,
+      "eval_runtime": 19.4971,
+      "eval_samples_per_second": 14.259,
+      "eval_steps_per_second": 1.795,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 2.6810097694396973,
+      "learning_rate": 3.439442247596724e-05,
+      "loss": 0.7154,
+      "step": 1210
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 2.145552635192871,
+      "learning_rate": 3.3623297123092006e-05,
+      "loss": 0.7025,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8636363636363638,
+      "grad_norm": 2.2261226177215576,
+      "learning_rate": 3.285651089368202e-05,
+      "loss": 0.6851,
+      "step": 1230
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 2.2848427295684814,
+      "learning_rate": 3.209426695318182e-05,
+      "loss": 0.686,
+      "step": 1240
+    },
+    {
+      "epoch": 1.893939393939394,
+      "grad_norm": 2.1015465259552,
+      "learning_rate": 3.133676726352438e-05,
+      "loss": 0.6909,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 2.174621105194092,
+      "learning_rate": 3.0584212529619775e-05,
+      "loss": 0.6855,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9242424242424243,
+      "grad_norm": 2.224524974822998,
+      "learning_rate": 2.9836802146177034e-05,
+      "loss": 0.7018,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 5.61815071105957,
+      "learning_rate": 2.9094734144873036e-05,
+      "loss": 0.6926,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9545454545454546,
+      "grad_norm": 1.9148584604263306,
+      "learning_rate": 2.835820514188273e-05,
+      "loss": 0.6977,
+      "step": 1290
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 1.9495019912719727,
+      "learning_rate": 2.7627410285784163e-05,
+      "loss": 0.6976,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9848484848484849,
+      "grad_norm": 2.185170888900757,
+      "learning_rate": 2.6902543205852492e-05,
+      "loss": 0.681,
+      "step": 1310
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.0127036571502686,
+      "learning_rate": 2.618379596075668e-05,
+      "loss": 0.7196,
+      "step": 1320
+    },
+    {
+      "epoch": 2.015151515151515,
+      "grad_norm": 1.9384896755218506,
+      "learning_rate": 2.5471358987672017e-05,
+      "loss": 0.6875,
+      "step": 1330
+    },
+    {
+      "epoch": 2.0303030303030303,
+      "grad_norm": 1.8721387386322021,
+      "learning_rate": 2.476542105182254e-05,
+      "loss": 0.7013,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": 1.915560245513916,
+      "learning_rate": 2.4066169196466326e-05,
+      "loss": 0.6822,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 2.1030776500701904,
+      "learning_rate": 2.3373788693337024e-05,
+      "loss": 0.691,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0757575757575757,
+      "grad_norm": 2.210036277770996,
+      "learning_rate": 2.268846299355481e-05,
+      "loss": 0.6745,
+      "step": 1370
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 2.111227035522461,
+      "learning_rate": 2.2010373679019776e-05,
+      "loss": 0.6932,
+      "step": 1380
+    },
+    {
+      "epoch": 2.106060606060606,
+      "grad_norm": 2.6546616554260254,
+      "learning_rate": 2.133970041430044e-05,
+      "loss": 0.6984,
+      "step": 1390
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 2.6496689319610596,
+      "learning_rate": 2.067662089903039e-05,
+      "loss": 0.6879,
+      "step": 1400
+    },
+    {
+      "epoch": 2.121212121212121,
+      "eval_accuracy": 0.7482014388489209,
+      "eval_loss": 0.6909542083740234,
+      "eval_runtime": 19.5229,
+      "eval_samples_per_second": 14.24,
+      "eval_steps_per_second": 1.793,
+      "step": 1400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1980,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ac343573caf15d93de28eb5786555f4b11b32d7a58af07b6242ad7cb452cef
+size 5176

checkpoint-1980/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-3B-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-1980/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-3B-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1980/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0fdaaef682cb16193b666bf407b96baf50f1834bac4592a8bbc429931a60f0
+size 119809824

checkpoint-1980/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-1980/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b932d54aae51c93788a5db548d4c3bfa08a7b1801c291bad4c49c0e5d9a95b2
+size 239910077

checkpoint-1980/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d92a1443411d8909341319694cd24e9a81729521232128d5fcf76e4f6a7d7c
+size 14244

checkpoint-1980/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96433e3f98fdc7f285e192933ab96e4af2916dcc61413aeb9f0f279a0c3a24ea
+size 1064

checkpoint-1980/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

checkpoint-1980/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1980/trainer_state.json

@@ -0,0 +1,1500 @@
+{
+  "best_metric": 0.6909542083740234,
+  "best_model_checkpoint": "/workspace/rm/rm_adapter/checkpoint-1400",
+  "epoch": 3.0,
+  "eval_steps": 200,
+  "global_step": 1980,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015151515151515152,
+      "grad_norm": 3.026841640472412,
+      "learning_rate": 2e-05,
+      "loss": 0.6999,
+      "step": 10
+    },
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 2.487321138381958,
+      "learning_rate": 4e-05,
+      "loss": 0.6998,
+      "step": 20
+    },
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 2.6206929683685303,
+      "learning_rate": 6e-05,
+      "loss": 0.6957,
+      "step": 30
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 1.7623201608657837,
+      "learning_rate": 8e-05,
+      "loss": 0.6922,
+      "step": 40
+    },
+    {
+      "epoch": 0.07575757575757576,
+      "grad_norm": 1.821882724761963,
+      "learning_rate": 0.0001,
+      "loss": 0.695,
+      "step": 50
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 2.205653190612793,
+      "learning_rate": 9.99933760728612e-05,
+      "loss": 0.7181,
+      "step": 60
+    },
+    {
+      "epoch": 0.10606060606060606,
+      "grad_norm": 2.080017328262329,
+      "learning_rate": 9.997350604650123e-05,
+      "loss": 0.6952,
+      "step": 70
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 2.1524713039398193,
+      "learning_rate": 9.994039518562432e-05,
+      "loss": 0.6938,
+      "step": 80
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 2.467346668243408,
+      "learning_rate": 9.989405226318772e-05,
+      "loss": 0.6988,
+      "step": 90
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 2.5009102821350098,
+      "learning_rate": 9.983448955807708e-05,
+      "loss": 0.6819,
+      "step": 100
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 2.6343142986297607,
+      "learning_rate": 9.976172285185314e-05,
+      "loss": 0.6891,
+      "step": 110
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.9957756996154785,
+      "learning_rate": 9.967577142457032e-05,
+      "loss": 0.7024,
+      "step": 120
+    },
+    {
+      "epoch": 0.19696969696969696,
+      "grad_norm": 2.6430771350860596,
+      "learning_rate": 9.957665804966829e-05,
+      "loss": 0.7012,
+      "step": 130
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 2.6395034790039062,
+      "learning_rate": 9.946440898793801e-05,
+      "loss": 0.6826,
+      "step": 140
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 2.5003907680511475,
+      "learning_rate": 9.933905398056372e-05,
+      "loss": 0.7,
+      "step": 150
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 2.4217541217803955,
+      "learning_rate": 9.920062624124282e-05,
+      "loss": 0.6932,
+      "step": 160
+    },
+    {
+      "epoch": 0.25757575757575757,
+      "grad_norm": 3.947263240814209,
+      "learning_rate": 9.904916244738571e-05,
+      "loss": 0.7003,
+      "step": 170
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 3.162750244140625,
+      "learning_rate": 9.888470273039775e-05,
+      "loss": 0.6756,
+      "step": 180
+    },
+    {
+      "epoch": 0.2878787878787879,
+      "grad_norm": 2.7067689895629883,
+      "learning_rate": 9.870729066504629e-05,
+      "loss": 0.7031,
+      "step": 190
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 3.415238618850708,
+      "learning_rate": 9.851697325791505e-05,
+      "loss": 0.6888,
+      "step": 200
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "eval_accuracy": 0.7482014388489209,
+      "eval_loss": 0.6937351822853088,
+      "eval_runtime": 19.5228,
+      "eval_samples_per_second": 14.24,
+      "eval_steps_per_second": 1.793,
+      "step": 200
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 3.3440141677856445,
+      "learning_rate": 9.831380093494957e-05,
+      "loss": 0.6784,
+      "step": 210
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 3.1289377212524414,
+      "learning_rate": 9.809782752809644e-05,
+      "loss": 0.7005,
+      "step": 220
+    },
+    {
+      "epoch": 0.3484848484848485,
+      "grad_norm": 4.689096927642822,
+      "learning_rate": 9.786911026104007e-05,
+      "loss": 0.7015,
+      "step": 230
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 3.6249144077301025,
+      "learning_rate": 9.762770973404094e-05,
+      "loss": 0.6818,
+      "step": 240
+    },
+    {
+      "epoch": 0.3787878787878788,
+      "grad_norm": 3.3653128147125244,
+      "learning_rate": 9.737368990787916e-05,
+      "loss": 0.706,
+      "step": 250
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 3.5432941913604736,
+      "learning_rate": 9.710711808690754e-05,
+      "loss": 0.7136,
+      "step": 260
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 3.5209529399871826,
+      "learning_rate": 9.682806490121885e-05,
+      "loss": 0.7134,
+      "step": 270
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 2.654764413833618,
+      "learning_rate": 9.653660428793188e-05,
+      "loss": 0.714,
+      "step": 280
+    },
+    {
+      "epoch": 0.4393939393939394,
+      "grad_norm": 6.175410747528076,
+      "learning_rate": 9.623281347160127e-05,
+      "loss": 0.7095,
+      "step": 290
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 2.3064019680023193,
+      "learning_rate": 9.591677294375636e-05,
+      "loss": 0.6922,
+      "step": 300
+    },
+    {
+      "epoch": 0.4696969696969697,
+      "grad_norm": 2.248598337173462,
+      "learning_rate": 9.558856644157432e-05,
+      "loss": 0.6999,
+      "step": 310
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 2.52163028717041,
+      "learning_rate": 9.52482809256934e-05,
+      "loss": 0.7185,
+      "step": 320
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.9855085611343384,
+      "learning_rate": 9.489600655717217e-05,
+      "loss": 0.7,
+      "step": 330
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 2.6163477897644043,
+      "learning_rate": 9.453183667360062e-05,
+      "loss": 0.6893,
+      "step": 340
+    },
+    {
+      "epoch": 0.5303030303030303,
+      "grad_norm": 2.32633900642395,
+      "learning_rate": 9.415586776436973e-05,
+      "loss": 0.7029,
+      "step": 350
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 2.0239343643188477,
+      "learning_rate": 9.376819944510598e-05,
+      "loss": 0.6859,
+      "step": 360
+    },
+    {
+      "epoch": 0.5606060606060606,
+      "grad_norm": 2.0154311656951904,
+      "learning_rate": 9.336893443127738e-05,
+      "loss": 0.6942,
+      "step": 370
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 2.040499210357666,
+      "learning_rate": 9.295817851097837e-05,
+      "loss": 0.6988,
+      "step": 380
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 2.244065999984741,
+      "learning_rate": 9.253604051690046e-05,
+      "loss": 0.6984,
+      "step": 390
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 2.4374303817749023,
+      "learning_rate": 9.210263229749626e-05,
+      "loss": 0.6863,
+      "step": 400
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "eval_accuracy": 0.697841726618705,
+      "eval_loss": 0.6917553544044495,
+      "eval_runtime": 19.5084,
+      "eval_samples_per_second": 14.25,
+      "eval_steps_per_second": 1.794,
+      "step": 400
+    },
+    {
+      "epoch": 0.6212121212121212,
+      "grad_norm": 2.305253505706787,
+      "learning_rate": 9.165806868734444e-05,
+      "loss": 0.7048,
+      "step": 410
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 2.419456720352173,
+      "learning_rate": 9.120246747672347e-05,
+      "loss": 0.7059,
+      "step": 420
+    },
+    {
+      "epoch": 0.6515151515151515,
+      "grad_norm": 2.2635741233825684,
+      "learning_rate": 9.073594938040231e-05,
+      "loss": 0.6961,
+      "step": 430
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.824849843978882,
+      "learning_rate": 9.025863800565613e-05,
+      "loss": 0.7004,
+      "step": 440
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 2.1357405185699463,
+      "learning_rate": 8.977065981951566e-05,
+      "loss": 0.6968,
+      "step": 450
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 3.1660122871398926,
+      "learning_rate": 8.927214411525895e-05,
+      "loss": 0.702,
+      "step": 460
+    },
+    {
+      "epoch": 0.7121212121212122,
+      "grad_norm": 2.296741247177124,
+      "learning_rate": 8.876322297815405e-05,
+      "loss": 0.7001,
+      "step": 470
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 1.987774133682251,
+      "learning_rate": 8.824403125046225e-05,
+      "loss": 0.6947,
+      "step": 480
+    },
+    {
+      "epoch": 0.7424242424242424,
+      "grad_norm": 2.645599603652954,
+      "learning_rate": 8.771470649571056e-05,
+      "loss": 0.7026,
+      "step": 490
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 2.0273940563201904,
+      "learning_rate": 8.717538896224332e-05,
+      "loss": 0.703,
+      "step": 500
+    },
+    {
+      "epoch": 0.7727272727272727,
+      "grad_norm": 6.725697994232178,
+      "learning_rate": 8.662622154606237e-05,
+      "loss": 0.685,
+      "step": 510
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 1.968575358390808,
+      "learning_rate": 8.606734975296578e-05,
+      "loss": 0.7042,
+      "step": 520
+    },
+    {
+      "epoch": 0.803030303030303,
+      "grad_norm": 2.2325947284698486,
+      "learning_rate": 8.549892165999505e-05,
+      "loss": 0.69,
+      "step": 530
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 2.3587887287139893,
+      "learning_rate": 8.492108787620105e-05,
+      "loss": 0.6987,
+      "step": 540
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.0664846897125244,
+      "learning_rate": 8.433400150273906e-05,
+      "loss": 0.708,
+      "step": 550
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 4.4357147216796875,
+      "learning_rate": 8.373781809230355e-05,
+      "loss": 0.6981,
+      "step": 560
+    },
+    {
+      "epoch": 0.8636363636363636,
+      "grad_norm": 2.435680627822876,
+      "learning_rate": 8.313269560791342e-05,
+      "loss": 0.7105,
+      "step": 570
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 2.5096144676208496,
+      "learning_rate": 8.251879438105854e-05,
+      "loss": 0.6897,
+      "step": 580
+    },
+    {
+      "epoch": 0.8939393939393939,
+      "grad_norm": 1.9323264360427856,
+      "learning_rate": 8.189627706921877e-05,
+      "loss": 0.6746,
+      "step": 590
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 2.3687186241149902,
+      "learning_rate": 8.126530861276677e-05,
+      "loss": 0.6847,
+      "step": 600
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "eval_accuracy": 0.5935251798561151,
+      "eval_loss": 0.6970531344413757,
+      "eval_runtime": 19.5244,
+      "eval_samples_per_second": 14.239,
+      "eval_steps_per_second": 1.793,
+      "step": 600
+    },
+    {
+      "epoch": 0.9242424242424242,
+      "grad_norm": 2.470337152481079,
+      "learning_rate": 8.062605619126584e-05,
+      "loss": 0.6787,
+      "step": 610
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 2.8660871982574463,
+      "learning_rate": 7.997868917917453e-05,
+      "loss": 0.6958,
+      "step": 620
+    },
+    {
+      "epoch": 0.9545454545454546,
+      "grad_norm": 3.2916390895843506,
+      "learning_rate": 7.932337910096961e-05,
+      "loss": 0.7024,
+      "step": 630
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 2.203716278076172,
+      "learning_rate": 7.866029958569956e-05,
+      "loss": 0.6858,
+      "step": 640
+    },
+    {
+      "epoch": 0.9848484848484849,
+      "grad_norm": 2.21602463722229,
+      "learning_rate": 7.798962632098024e-05,
+      "loss": 0.7044,
+      "step": 650
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9984266757965088,
+      "learning_rate": 7.73115370064452e-05,
+      "loss": 0.696,
+      "step": 660
+    },
+    {
+      "epoch": 1.0151515151515151,
+      "grad_norm": 2.6973960399627686,
+      "learning_rate": 7.6626211306663e-05,
+      "loss": 0.6972,
+      "step": 670
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 2.1271116733551025,
+      "learning_rate": 7.59338308035337e-05,
+      "loss": 0.6862,
+      "step": 680
+    },
+    {
+      "epoch": 1.0454545454545454,
+      "grad_norm": 2.1646666526794434,
+      "learning_rate": 7.523457894817745e-05,
+      "loss": 0.6957,
+      "step": 690
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 2.122968912124634,
+      "learning_rate": 7.452864101232798e-05,
+      "loss": 0.6931,
+      "step": 700
+    },
+    {
+      "epoch": 1.0757575757575757,
+      "grad_norm": 2.318418502807617,
+      "learning_rate": 7.381620403924333e-05,
+      "loss": 0.6833,
+      "step": 710
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 2.31949782371521,
+      "learning_rate": 7.30974567941475e-05,
+      "loss": 0.6866,
+      "step": 720
+    },
+    {
+      "epoch": 1.106060606060606,
+      "grad_norm": 2.116624355316162,
+      "learning_rate": 7.237258971421587e-05,
+      "loss": 0.6976,
+      "step": 730
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 2.1707992553710938,
+      "learning_rate": 7.164179485811727e-05,
+      "loss": 0.6932,
+      "step": 740
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 2.0329554080963135,
+      "learning_rate": 7.090526585512696e-05,
+      "loss": 0.6872,
+      "step": 750
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 2.590719223022461,
+      "learning_rate": 7.016319785382296e-05,
+      "loss": 0.7154,
+      "step": 760
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 2.158923387527466,
+      "learning_rate": 6.941578747038023e-05,
+      "loss": 0.6906,
+      "step": 770
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 3.0064737796783447,
+      "learning_rate": 6.866323273647563e-05,
+      "loss": 0.6955,
+      "step": 780
+    },
+    {
+      "epoch": 1.196969696969697,
+      "grad_norm": 2.0017855167388916,
+      "learning_rate": 6.79057330468182e-05,
+      "loss": 0.6854,
+      "step": 790
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 3.6152710914611816,
+      "learning_rate": 6.7143489106318e-05,
+      "loss": 0.698,
+      "step": 800
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "eval_accuracy": 0.5935251798561151,
+      "eval_loss": 0.6945483684539795,
+      "eval_runtime": 19.5034,
+      "eval_samples_per_second": 14.254,
+      "eval_steps_per_second": 1.795,
+      "step": 800
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "grad_norm": 1.9689804315567017,
+      "learning_rate": 6.637670287690799e-05,
+      "loss": 0.7115,
+      "step": 810
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 4.077113151550293,
+      "learning_rate": 6.560557752403277e-05,
+      "loss": 0.6883,
+      "step": 820
+    },
+    {
+      "epoch": 1.2575757575757576,
+      "grad_norm": 2.2839391231536865,
+      "learning_rate": 6.483031736281843e-05,
+      "loss": 0.6972,
+      "step": 830
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 1.9423472881317139,
+      "learning_rate": 6.40511278039378e-05,
+      "loss": 0.701,
+      "step": 840
+    },
+    {
+      "epoch": 1.2878787878787878,
+      "grad_norm": 2.111860752105713,
+      "learning_rate": 6.326821529918553e-05,
+      "loss": 0.7023,
+      "step": 850
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 1.9913779497146606,
+      "learning_rate": 6.248178728677711e-05,
+      "loss": 0.7014,
+      "step": 860
+    },
+    {
+      "epoch": 1.3181818181818181,
+      "grad_norm": 1.9043771028518677,
+      "learning_rate": 6.16920521363867e-05,
+      "loss": 0.6891,
+      "step": 870
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 2.018148899078369,
+      "learning_rate": 6.089921909393812e-05,
+      "loss": 0.6969,
+      "step": 880
+    },
+    {
+      "epoch": 1.3484848484848486,
+      "grad_norm": 1.8589205741882324,
+      "learning_rate": 6.0103498226163603e-05,
+      "loss": 0.6982,
+      "step": 890
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 1.8796669244766235,
+      "learning_rate": 5.93051003649452e-05,
+      "loss": 0.6787,
+      "step": 900
+    },
+    {
+      "epoch": 1.378787878787879,
+      "grad_norm": 2.0444390773773193,
+      "learning_rate": 5.850423705145334e-05,
+      "loss": 0.6934,
+      "step": 910
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 2.5297834873199463,
+      "learning_rate": 5.770112048009747e-05,
+      "loss": 0.7092,
+      "step": 920
+    },
+    {
+      "epoch": 1.4090909090909092,
+      "grad_norm": 1.9327147006988525,
+      "learning_rate": 5.68959634423037e-05,
+      "loss": 0.6951,
+      "step": 930
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 1.8969117403030396,
+      "learning_rate": 5.60889792701342e-05,
+      "loss": 0.7045,
+      "step": 940
+    },
+    {
+      "epoch": 1.4393939393939394,
+      "grad_norm": 2.584240198135376,
+      "learning_rate": 5.52803817797633e-05,
+      "loss": 0.6734,
+      "step": 950
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 2.54909086227417,
+      "learning_rate": 5.4470385214825416e-05,
+      "loss": 0.6727,
+      "step": 960
+    },
+    {
+      "epoch": 1.4696969696969697,
+      "grad_norm": 2.040754556655884,
+      "learning_rate": 5.365920418964973e-05,
+      "loss": 0.688,
+      "step": 970
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 2.1792185306549072,
+      "learning_rate": 5.28470536323965e-05,
+      "loss": 0.6911,
+      "step": 980
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.115302562713623,
+      "learning_rate": 5.2034148728110424e-05,
+      "loss": 0.6942,
+      "step": 990
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 6.179975509643555,
+      "learning_rate": 5.1220704861705774e-05,
+      "loss": 0.6945,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "eval_accuracy": 0.4460431654676259,
+      "eval_loss": 0.7005228996276855,
+      "eval_runtime": 19.5262,
+      "eval_samples_per_second": 14.237,
+      "eval_steps_per_second": 1.792,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5303030303030303,
+      "grad_norm": 2.1656877994537354,
+      "learning_rate": 5.0406937560898646e-05,
+      "loss": 0.694,
+      "step": 1010
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 2.0086238384246826,
+      "learning_rate": 4.9593062439101365e-05,
+      "loss": 0.683,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5606060606060606,
+      "grad_norm": 2.685886859893799,
+      "learning_rate": 4.877929513829424e-05,
+      "loss": 0.6927,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 2.2931978702545166,
+      "learning_rate": 4.796585127188958e-05,
+      "loss": 0.6943,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 1.9456837177276611,
+      "learning_rate": 4.715294636760352e-05,
+      "loss": 0.7238,
+      "step": 1050
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 1.9456251859664917,
+      "learning_rate": 4.634079581035029e-05,
+      "loss": 0.6867,
+      "step": 1060
+    },
+    {
+      "epoch": 1.621212121212121,
+      "grad_norm": 1.8919247388839722,
+      "learning_rate": 4.55296147851746e-05,
+      "loss": 0.6679,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 2.3800299167633057,
+      "learning_rate": 4.471961822023671e-05,
+      "loss": 0.6932,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6515151515151514,
+      "grad_norm": 2.1245882511138916,
+      "learning_rate": 4.391102072986581e-05,
+      "loss": 0.6823,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.484229326248169,
+      "learning_rate": 4.3104036557696295e-05,
+      "loss": 0.7094,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6818181818181817,
+      "grad_norm": 2.081204652786255,
+      "learning_rate": 4.229887951990255e-05,
+      "loss": 0.6873,
+      "step": 1110
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 2.008754253387451,
+      "learning_rate": 4.149576294854668e-05,
+      "loss": 0.6957,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7121212121212122,
+      "grad_norm": 2.088444948196411,
+      "learning_rate": 4.069489963505482e-05,
+      "loss": 0.7134,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 2.0371851921081543,
+      "learning_rate": 3.98965017738364e-05,
+      "loss": 0.698,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7424242424242424,
+      "grad_norm": 2.4857864379882812,
+      "learning_rate": 3.9100780906061896e-05,
+      "loss": 0.702,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 1.9480881690979004,
+      "learning_rate": 3.83079478636133e-05,
+      "loss": 0.6875,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7727272727272727,
+      "grad_norm": 2.094036817550659,
+      "learning_rate": 3.7518212713222906e-05,
+      "loss": 0.7047,
+      "step": 1170
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 2.085651159286499,
+      "learning_rate": 3.673178470081448e-05,
+      "loss": 0.6933,
+      "step": 1180
+    },
+    {
+      "epoch": 1.803030303030303,
+      "grad_norm": 2.0030457973480225,
+      "learning_rate": 3.594887219606221e-05,
+      "loss": 0.6901,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 2.7572779655456543,
+      "learning_rate": 3.516968263718159e-05,
+      "loss": 0.6808,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_accuracy": 0.5755395683453237,
+      "eval_loss": 0.6959903836250305,
+      "eval_runtime": 19.4971,
+      "eval_samples_per_second": 14.259,
+      "eval_steps_per_second": 1.795,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 2.6810097694396973,
+      "learning_rate": 3.439442247596724e-05,
+      "loss": 0.7154,
+      "step": 1210
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 2.145552635192871,
+      "learning_rate": 3.3623297123092006e-05,
+      "loss": 0.7025,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8636363636363638,
+      "grad_norm": 2.2261226177215576,
+      "learning_rate": 3.285651089368202e-05,
+      "loss": 0.6851,
+      "step": 1230
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 2.2848427295684814,
+      "learning_rate": 3.209426695318182e-05,
+      "loss": 0.686,
+      "step": 1240
+    },
+    {
+      "epoch": 1.893939393939394,
+      "grad_norm": 2.1015465259552,
+      "learning_rate": 3.133676726352438e-05,
+      "loss": 0.6909,
+      "step": 1250
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 2.174621105194092,
+      "learning_rate": 3.0584212529619775e-05,
+      "loss": 0.6855,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9242424242424243,
+      "grad_norm": 2.224524974822998,
+      "learning_rate": 2.9836802146177034e-05,
+      "loss": 0.7018,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 5.61815071105957,
+      "learning_rate": 2.9094734144873036e-05,
+      "loss": 0.6926,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9545454545454546,
+      "grad_norm": 1.9148584604263306,
+      "learning_rate": 2.835820514188273e-05,
+      "loss": 0.6977,
+      "step": 1290
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 1.9495019912719727,
+      "learning_rate": 2.7627410285784163e-05,
+      "loss": 0.6976,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9848484848484849,
+      "grad_norm": 2.185170888900757,
+      "learning_rate": 2.6902543205852492e-05,
+      "loss": 0.681,
+      "step": 1310
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.0127036571502686,
+      "learning_rate": 2.618379596075668e-05,
+      "loss": 0.7196,
+      "step": 1320
+    },
+    {
+      "epoch": 2.015151515151515,
+      "grad_norm": 1.9384896755218506,
+      "learning_rate": 2.5471358987672017e-05,
+      "loss": 0.6875,
+      "step": 1330
+    },
+    {
+      "epoch": 2.0303030303030303,
+      "grad_norm": 1.8721387386322021,
+      "learning_rate": 2.476542105182254e-05,
+      "loss": 0.7013,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": 1.915560245513916,
+      "learning_rate": 2.4066169196466326e-05,
+      "loss": 0.6822,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 2.1030776500701904,
+      "learning_rate": 2.3373788693337024e-05,
+      "loss": 0.691,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0757575757575757,
+      "grad_norm": 2.210036277770996,
+      "learning_rate": 2.268846299355481e-05,
+      "loss": 0.6745,
+      "step": 1370
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 2.111227035522461,
+      "learning_rate": 2.2010373679019776e-05,
+      "loss": 0.6932,
+      "step": 1380
+    },
+    {
+      "epoch": 2.106060606060606,
+      "grad_norm": 2.6546616554260254,
+      "learning_rate": 2.133970041430044e-05,
+      "loss": 0.6984,
+      "step": 1390
+    },
+    {
+      "epoch": 2.121212121212121,
+      "grad_norm": 2.6496689319610596,
+      "learning_rate": 2.067662089903039e-05,
+      "loss": 0.6879,
+      "step": 1400
+    },
+    {
+      "epoch": 2.121212121212121,
+      "eval_accuracy": 0.7482014388489209,
+      "eval_loss": 0.6909542083740234,
+      "eval_runtime": 19.5229,
+      "eval_samples_per_second": 14.24,
+      "eval_steps_per_second": 1.793,
+      "step": 1400
+    },
+    {
+      "epoch": 2.1363636363636362,
+      "grad_norm": 1.9020475149154663,
+      "learning_rate": 2.002131082082549e-05,
+      "loss": 0.6966,
+      "step": 1410
+    },
+    {
+      "epoch": 2.1515151515151514,
+      "grad_norm": 2.5339136123657227,
+      "learning_rate": 1.937394380873418e-05,
+      "loss": 0.7058,
+      "step": 1420
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 2.2435576915740967,
+      "learning_rate": 1.873469138723325e-05,
+      "loss": 0.7006,
+      "step": 1430
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 1.8887898921966553,
+      "learning_rate": 1.8103722930781247e-05,
+      "loss": 0.6943,
+      "step": 1440
+    },
+    {
+      "epoch": 2.196969696969697,
+      "grad_norm": 1.812873125076294,
+      "learning_rate": 1.748120561894147e-05,
+      "loss": 0.702,
+      "step": 1450
+    },
+    {
+      "epoch": 2.212121212121212,
+      "grad_norm": 2.076291561126709,
+      "learning_rate": 1.6867304392086575e-05,
+      "loss": 0.7033,
+      "step": 1460
+    },
+    {
+      "epoch": 2.227272727272727,
+      "grad_norm": 1.9465279579162598,
+      "learning_rate": 1.6262181907696454e-05,
+      "loss": 0.6952,
+      "step": 1470
+    },
+    {
+      "epoch": 2.242424242424242,
+      "grad_norm": 1.871740698814392,
+      "learning_rate": 1.5665998497260958e-05,
+      "loss": 0.6923,
+      "step": 1480
+    },
+    {
+      "epoch": 2.257575757575758,
+      "grad_norm": 2.0625593662261963,
+      "learning_rate": 1.5078912123798961e-05,
+      "loss": 0.7015,
+      "step": 1490
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 1.8296911716461182,
+      "learning_rate": 1.4501078340004953e-05,
+      "loss": 0.6824,
+      "step": 1500
+    },
+    {
+      "epoch": 2.287878787878788,
+      "grad_norm": 1.894636631011963,
+      "learning_rate": 1.3932650247034218e-05,
+      "loss": 0.6955,
+      "step": 1510
+    },
+    {
+      "epoch": 2.303030303030303,
+      "grad_norm": 2.202396869659424,
+      "learning_rate": 1.337377845393763e-05,
+      "loss": 0.6946,
+      "step": 1520
+    },
+    {
+      "epoch": 2.3181818181818183,
+      "grad_norm": 1.974416732788086,
+      "learning_rate": 1.2824611037756684e-05,
+      "loss": 0.6921,
+      "step": 1530
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 1.8844738006591797,
+      "learning_rate": 1.2285293504289447e-05,
+      "loss": 0.6891,
+      "step": 1540
+    },
+    {
+      "epoch": 2.3484848484848486,
+      "grad_norm": 2.2203423976898193,
+      "learning_rate": 1.1755968749537754e-05,
+      "loss": 0.6983,
+      "step": 1550
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 2.217637300491333,
+      "learning_rate": 1.1236777021845956e-05,
+      "loss": 0.7082,
+      "step": 1560
+    },
+    {
+      "epoch": 2.378787878787879,
+      "grad_norm": 2.1142191886901855,
+      "learning_rate": 1.0727855884741056e-05,
+      "loss": 0.6949,
+      "step": 1570
+    },
+    {
+      "epoch": 2.393939393939394,
+      "grad_norm": 2.0874030590057373,
+      "learning_rate": 1.022934018048432e-05,
+      "loss": 0.6853,
+      "step": 1580
+    },
+    {
+      "epoch": 2.409090909090909,
+      "grad_norm": 2.1230809688568115,
+      "learning_rate": 9.741361994343867e-06,
+      "loss": 0.6928,
+      "step": 1590
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 2.0048282146453857,
+      "learning_rate": 9.264050619597697e-06,
+      "loss": 0.6991,
+      "step": 1600
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "eval_accuracy": 0.6402877697841727,
+      "eval_loss": 0.6958355903625488,
+      "eval_runtime": 19.5282,
+      "eval_samples_per_second": 14.236,
+      "eval_steps_per_second": 1.792,
+      "step": 1600
+    },
+    {
+      "epoch": 2.4393939393939394,
+      "grad_norm": 1.7928433418273926,
+      "learning_rate": 8.797532523276542e-06,
+      "loss": 0.6909,
+      "step": 1610
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 1.8756718635559082,
+      "learning_rate": 8.341931312655582e-06,
+      "loss": 0.6911,
+      "step": 1620
+    },
+    {
+      "epoch": 2.4696969696969697,
+      "grad_norm": 1.9278541803359985,
+      "learning_rate": 7.897367702503756e-06,
+      "loss": 0.6896,
+      "step": 1630
+    },
+    {
+      "epoch": 2.484848484848485,
+      "grad_norm": 2.110722064971924,
+      "learning_rate": 7.463959483099547e-06,
+      "loss": 0.698,
+      "step": 1640
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.9607691764831543,
+      "learning_rate": 7.041821489021639e-06,
+      "loss": 0.699,
+      "step": 1650
+    },
+    {
+      "epoch": 2.515151515151515,
+      "grad_norm": 1.8575242757797241,
+      "learning_rate": 6.631065568722633e-06,
+      "loss": 0.7021,
+      "step": 1660
+    },
+    {
+      "epoch": 2.5303030303030303,
+      "grad_norm": 1.9291802644729614,
+      "learning_rate": 6.231800554894029e-06,
+      "loss": 0.6944,
+      "step": 1670
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 2.037835121154785,
+      "learning_rate": 5.844132235630273e-06,
+      "loss": 0.6944,
+      "step": 1680
+    },
+    {
+      "epoch": 2.5606060606060606,
+      "grad_norm": 2.086446523666382,
+      "learning_rate": 5.468163326399389e-06,
+      "loss": 0.7098,
+      "step": 1690
+    },
+    {
+      "epoch": 2.5757575757575757,
+      "grad_norm": 2.0862929821014404,
+      "learning_rate": 5.103993442827831e-06,
+      "loss": 0.7055,
+      "step": 1700
+    },
+    {
+      "epoch": 2.590909090909091,
+      "grad_norm": 2.007094621658325,
+      "learning_rate": 4.751719074306604e-06,
+      "loss": 0.6928,
+      "step": 1710
+    },
+    {
+      "epoch": 2.606060606060606,
+      "grad_norm": 2.4104299545288086,
+      "learning_rate": 4.411433558425698e-06,
+      "loss": 0.6934,
+      "step": 1720
+    },
+    {
+      "epoch": 2.621212121212121,
+      "grad_norm": 1.9547191858291626,
+      "learning_rate": 4.083227056243644e-06,
+      "loss": 0.713,
+      "step": 1730
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 1.9469369649887085,
+      "learning_rate": 3.767186528398725e-06,
+      "loss": 0.6887,
+      "step": 1740
+    },
+    {
+      "epoch": 2.6515151515151514,
+      "grad_norm": 1.8792847394943237,
+      "learning_rate": 3.4633957120681293e-06,
+      "loss": 0.699,
+      "step": 1750
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.878363847732544,
+      "learning_rate": 3.1719350987811534e-06,
+      "loss": 0.6969,
+      "step": 1760
+    },
+    {
+      "epoch": 2.6818181818181817,
+      "grad_norm": 1.8515868186950684,
+      "learning_rate": 2.8928819130924657e-06,
+      "loss": 0.6963,
+      "step": 1770
+    },
+    {
+      "epoch": 2.6969696969696972,
+      "grad_norm": 1.9838860034942627,
+      "learning_rate": 2.6263100921208482e-06,
+      "loss": 0.6992,
+      "step": 1780
+    },
+    {
+      "epoch": 2.712121212121212,
+      "grad_norm": 1.841746211051941,
+      "learning_rate": 2.372290265959065e-06,
+      "loss": 0.7081,
+      "step": 1790
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 2.14920973777771,
+      "learning_rate": 2.130889738959946e-06,
+      "loss": 0.7126,
+      "step": 1800
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "eval_accuracy": 0.6510791366906474,
+      "eval_loss": 0.6965467929840088,
+      "eval_runtime": 19.6613,
+      "eval_samples_per_second": 14.139,
+      "eval_steps_per_second": 1.78,
+      "step": 1800
+    },
+    {
+      "epoch": 2.742424242424242,
+      "grad_norm": 2.150446653366089,
+      "learning_rate": 1.9021724719035628e-06,
+      "loss": 0.6918,
+      "step": 1810
+    },
+    {
+      "epoch": 2.757575757575758,
+      "grad_norm": 1.683022141456604,
+      "learning_rate": 1.6861990650504255e-06,
+      "loss": 0.7026,
+      "step": 1820
+    },
+    {
+      "epoch": 2.7727272727272725,
+      "grad_norm": 1.9644994735717773,
+      "learning_rate": 1.4830267420849585e-06,
+      "loss": 0.711,
+      "step": 1830
+    },
+    {
+      "epoch": 2.787878787878788,
+      "grad_norm": 1.8732028007507324,
+      "learning_rate": 1.292709334953729e-06,
+      "loss": 0.6866,
+      "step": 1840
+    },
+    {
+      "epoch": 2.8030303030303028,
+      "grad_norm": 1.9413446187973022,
+      "learning_rate": 1.1152972696022445e-06,
+      "loss": 0.6862,
+      "step": 1850
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 1.8554645776748657,
+      "learning_rate": 9.508375526142976e-07,
+      "loss": 0.6915,
+      "step": 1860
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 1.7176835536956787,
+      "learning_rate": 7.993737587571826e-07,
+      "loss": 0.6806,
+      "step": 1870
+    },
+    {
+      "epoch": 2.8484848484848486,
+      "grad_norm": 1.8371529579162598,
+      "learning_rate": 6.609460194362927e-07,
+      "loss": 0.6811,
+      "step": 1880
+    },
+    {
+      "epoch": 2.8636363636363638,
+      "grad_norm": 2.010014057159424,
+      "learning_rate": 5.355910120620034e-07,
+      "loss": 0.6994,
+      "step": 1890
+    },
+    {
+      "epoch": 2.878787878787879,
+      "grad_norm": 1.748685598373413,
+      "learning_rate": 4.233419503317182e-07,
+      "loss": 0.6823,
+      "step": 1900
+    },
+    {
+      "epoch": 2.893939393939394,
+      "grad_norm": 1.8147194385528564,
+      "learning_rate": 3.242285754296859e-07,
+      "loss": 0.6943,
+      "step": 1910
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 1.9330848455429077,
+      "learning_rate": 2.3827714814686486e-07,
+      "loss": 0.6923,
+      "step": 1920
+    },
+    {
+      "epoch": 2.9242424242424243,
+      "grad_norm": 1.868577480316162,
+      "learning_rate": 1.655104419229281e-07,
+      "loss": 0.689,
+      "step": 1930
+    },
+    {
+      "epoch": 2.9393939393939394,
+      "grad_norm": 1.9551337957382202,
+      "learning_rate": 1.059477368122841e-07,
+      "loss": 0.6878,
+      "step": 1940
+    },
+    {
+      "epoch": 2.9545454545454546,
+      "grad_norm": 1.7769166231155396,
+      "learning_rate": 5.960481437568555e-08,
+      "loss": 0.6912,
+      "step": 1950
+    },
+    {
+      "epoch": 2.9696969696969697,
+      "grad_norm": 1.908371090888977,
+      "learning_rate": 2.649395349879069e-08,
+      "loss": 0.699,
+      "step": 1960
+    },
+    {
+      "epoch": 2.984848484848485,
+      "grad_norm": 2.117502450942993,
+      "learning_rate": 6.623927138804664e-09,
+      "loss": 0.6896,
+      "step": 1970
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.9173846244812012,
+      "learning_rate": 0.0,
+      "loss": 0.6877,
+      "step": 1980
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1980,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1980/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243356b79fa6043bbb1f7a9746b4d6f8b6a34ab7a90f768f01b225454d3705ad
+size 5176

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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",
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}