Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-640/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-640/README.md

@@ -0,0 +1,202 @@
+---
+base_model: oliver213/MNLP_M3_mcqa_model
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-640/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "oliver213/MNLP_M3_mcqa_model",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 28,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "self_attn.q_proj",
+    "mlp.up_proj",
+    "mlp.down_proj",
+    "self_attn.o_proj",
+    "self_attn.v_proj",
+    "self_attn.k_proj",
+    "mlp.gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-640/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19eb36483de347af1124a2438166a0c92502beccd43b53f985491b5d8671a518
+size 70788906

checkpoint-640/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-640/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23d987eec83ecec8d7bfd887179de241a092c5783377406155f006aa68308e71
+size 141625194

checkpoint-640/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85c472fde275d045c96367b115b526acb9574f35243eb83d4408e389c0e59639
+size 14244

checkpoint-640/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2b9e0cc886b0bc28c1877a3ec3ac149cd5e813036526536d6f6991829e09c3
+size 988

checkpoint-640/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54e27beb66f11e1149703734dada84cc1a72a71ccc7038b8baa93abf238aa3a
+size 1064

checkpoint-640/special_tokens_map.json

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

checkpoint-640/tokenizer.json

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

checkpoint-640/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-640/trainer_state.json

@@ -0,0 +1,650 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.2,
+  "eval_steps": 160,
+  "global_step": 640,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.43827545642852783,
+      "learning_rate": 0.0001,
+      "loss": 0.9667,
+      "mean_token_accuracy": 0.7421795547008514,
+      "num_tokens": 18527.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.39240607619285583,
+      "learning_rate": 0.0001,
+      "loss": 1.0018,
+      "mean_token_accuracy": 0.728947314620018,
+      "num_tokens": 37412.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.38427555561065674,
+      "learning_rate": 0.0001,
+      "loss": 1.0093,
+      "mean_token_accuracy": 0.7267461150884629,
+      "num_tokens": 56239.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.42408332228660583,
+      "learning_rate": 0.0001,
+      "loss": 0.9559,
+      "mean_token_accuracy": 0.7414480298757553,
+      "num_tokens": 75307.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.46401479840278625,
+      "learning_rate": 0.0001,
+      "loss": 1.0349,
+      "mean_token_accuracy": 0.7188403815031051,
+      "num_tokens": 93699.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.4213346838951111,
+      "learning_rate": 0.0001,
+      "loss": 0.9546,
+      "mean_token_accuracy": 0.7375499308109283,
+      "num_tokens": 112724.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.40055790543556213,
+      "learning_rate": 0.0001,
+      "loss": 0.9743,
+      "mean_token_accuracy": 0.7378433406352997,
+      "num_tokens": 131831.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.45163631439208984,
+      "learning_rate": 0.0001,
+      "loss": 1.0189,
+      "mean_token_accuracy": 0.7263641938567161,
+      "num_tokens": 151163.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4101933538913727,
+      "learning_rate": 0.0001,
+      "loss": 0.9672,
+      "mean_token_accuracy": 0.7346487194299698,
+      "num_tokens": 169973.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.44324934482574463,
+      "learning_rate": 0.0001,
+      "loss": 1.0263,
+      "mean_token_accuracy": 0.7225876390933991,
+      "num_tokens": 188998.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.47263675928115845,
+      "learning_rate": 0.0001,
+      "loss": 0.9865,
+      "mean_token_accuracy": 0.7291134670376778,
+      "num_tokens": 207403.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.418999046087265,
+      "learning_rate": 0.0001,
+      "loss": 0.9624,
+      "mean_token_accuracy": 0.7337665259838104,
+      "num_tokens": 225944.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.48299098014831543,
+      "learning_rate": 0.0001,
+      "loss": 1.0097,
+      "mean_token_accuracy": 0.7260663375258446,
+      "num_tokens": 244001.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.45383280515670776,
+      "learning_rate": 0.0001,
+      "loss": 0.9367,
+      "mean_token_accuracy": 0.7450008347630501,
+      "num_tokens": 262380.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.3950103521347046,
+      "learning_rate": 0.0001,
+      "loss": 0.9511,
+      "mean_token_accuracy": 0.7413627594709397,
+      "num_tokens": 281319.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5174494981765747,
+      "learning_rate": 0.0001,
+      "loss": 0.8982,
+      "mean_token_accuracy": 0.7503622397780418,
+      "num_tokens": 301270.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.0890034437179565,
+      "eval_mean_token_accuracy": 0.7177740011364222,
+      "eval_num_tokens": 301270.0,
+      "eval_runtime": 18.3264,
+      "eval_samples_per_second": 17.461,
+      "eval_steps_per_second": 8.731,
+      "step": 160
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.5073578953742981,
+      "learning_rate": 0.0001,
+      "loss": 0.9498,
+      "mean_token_accuracy": 0.7435929998755455,
+      "num_tokens": 320325.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.4688466489315033,
+      "learning_rate": 0.0001,
+      "loss": 0.957,
+      "mean_token_accuracy": 0.7374263137578965,
+      "num_tokens": 339313.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.5929768085479736,
+      "learning_rate": 0.0001,
+      "loss": 1.02,
+      "mean_token_accuracy": 0.7251972034573555,
+      "num_tokens": 357224.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5086683630943298,
+      "learning_rate": 0.0001,
+      "loss": 0.992,
+      "mean_token_accuracy": 0.7353695958852768,
+      "num_tokens": 376643.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.4679737985134125,
+      "learning_rate": 0.0001,
+      "loss": 0.8852,
+      "mean_token_accuracy": 0.7536615505814552,
+      "num_tokens": 395121.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.4789438843727112,
+      "learning_rate": 0.0001,
+      "loss": 0.9377,
+      "mean_token_accuracy": 0.7422916859388351,
+      "num_tokens": 413895.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.5487397313117981,
+      "learning_rate": 0.0001,
+      "loss": 0.8488,
+      "mean_token_accuracy": 0.7590507015585899,
+      "num_tokens": 432763.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.5337480306625366,
+      "learning_rate": 0.0001,
+      "loss": 0.8666,
+      "mean_token_accuracy": 0.7579806029796601,
+      "num_tokens": 451608.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.49510490894317627,
+      "learning_rate": 0.0001,
+      "loss": 0.9104,
+      "mean_token_accuracy": 0.7497919097542762,
+      "num_tokens": 470554.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.657990038394928,
+      "learning_rate": 0.0001,
+      "loss": 0.8951,
+      "mean_token_accuracy": 0.7483552470803261,
+      "num_tokens": 488654.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.6424926519393921,
+      "learning_rate": 0.0001,
+      "loss": 0.8812,
+      "mean_token_accuracy": 0.7524763226509095,
+      "num_tokens": 507895.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.556791365146637,
+      "learning_rate": 0.0001,
+      "loss": 0.8923,
+      "mean_token_accuracy": 0.753830075263977,
+      "num_tokens": 526416.0,
+      "step": 280
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.5518726110458374,
+      "learning_rate": 0.0001,
+      "loss": 0.919,
+      "mean_token_accuracy": 0.7403171643614769,
+      "num_tokens": 545947.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5887808799743652,
+      "learning_rate": 0.0001,
+      "loss": 0.9512,
+      "mean_token_accuracy": 0.741435107588768,
+      "num_tokens": 564070.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.4931485056877136,
+      "learning_rate": 0.0001,
+      "loss": 0.8012,
+      "mean_token_accuracy": 0.775481553375721,
+      "num_tokens": 583519.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5791897177696228,
+      "learning_rate": 0.0001,
+      "loss": 0.8834,
+      "mean_token_accuracy": 0.7559772610664368,
+      "num_tokens": 602601.0,
+      "step": 320
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.0932101011276245,
+      "eval_mean_token_accuracy": 0.7169803511351347,
+      "eval_num_tokens": 602601.0,
+      "eval_runtime": 18.3278,
+      "eval_samples_per_second": 17.46,
+      "eval_steps_per_second": 8.73,
+      "step": 320
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.5467931032180786,
+      "learning_rate": 0.0001,
+      "loss": 0.9429,
+      "mean_token_accuracy": 0.7412704437971115,
+      "num_tokens": 621579.0,
+      "step": 330
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.5784661173820496,
+      "learning_rate": 0.0001,
+      "loss": 0.8529,
+      "mean_token_accuracy": 0.7641629755496979,
+      "num_tokens": 640332.0,
+      "step": 340
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.4568150043487549,
+      "learning_rate": 0.0001,
+      "loss": 0.8716,
+      "mean_token_accuracy": 0.7545537993311882,
+      "num_tokens": 659812.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.5498734712600708,
+      "learning_rate": 0.0001,
+      "loss": 0.8971,
+      "mean_token_accuracy": 0.752374118566513,
+      "num_tokens": 678799.0,
+      "step": 360
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.5936706066131592,
+      "learning_rate": 0.0001,
+      "loss": 0.9918,
+      "mean_token_accuracy": 0.7298657700419426,
+      "num_tokens": 696438.0,
+      "step": 370
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.5029641389846802,
+      "learning_rate": 0.0001,
+      "loss": 0.9371,
+      "mean_token_accuracy": 0.7457024067640304,
+      "num_tokens": 715459.0,
+      "step": 380
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.4978192448616028,
+      "learning_rate": 0.0001,
+      "loss": 0.9429,
+      "mean_token_accuracy": 0.7435312032699585,
+      "num_tokens": 733927.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5036607384681702,
+      "learning_rate": 0.0001,
+      "loss": 0.9169,
+      "mean_token_accuracy": 0.7488818317651749,
+      "num_tokens": 753286.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.6137449741363525,
+      "learning_rate": 0.0001,
+      "loss": 0.7911,
+      "mean_token_accuracy": 0.7788830995559692,
+      "num_tokens": 772442.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.5912206172943115,
+      "learning_rate": 0.0001,
+      "loss": 0.7946,
+      "mean_token_accuracy": 0.7781713724136352,
+      "num_tokens": 790693.0,
+      "step": 420
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.6016007661819458,
+      "learning_rate": 0.0001,
+      "loss": 0.7889,
+      "mean_token_accuracy": 0.7735364139080048,
+      "num_tokens": 809966.0,
+      "step": 430
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.5786302089691162,
+      "learning_rate": 0.0001,
+      "loss": 0.8027,
+      "mean_token_accuracy": 0.7732229202985763,
+      "num_tokens": 829851.0,
+      "step": 440
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.5368697047233582,
+      "learning_rate": 0.0001,
+      "loss": 0.8208,
+      "mean_token_accuracy": 0.7645123034715653,
+      "num_tokens": 848464.0,
+      "step": 450
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.712200403213501,
+      "learning_rate": 0.0001,
+      "loss": 0.8047,
+      "mean_token_accuracy": 0.7703322827816009,
+      "num_tokens": 867916.0,
+      "step": 460
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.7731253504753113,
+      "learning_rate": 0.0001,
+      "loss": 0.8328,
+      "mean_token_accuracy": 0.7687120333313942,
+      "num_tokens": 886785.0,
+      "step": 470
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.629067599773407,
+      "learning_rate": 0.0001,
+      "loss": 0.8092,
+      "mean_token_accuracy": 0.7728568613529205,
+      "num_tokens": 905795.0,
+      "step": 480
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.125347375869751,
+      "eval_mean_token_accuracy": 0.711500994861126,
+      "eval_num_tokens": 905795.0,
+      "eval_runtime": 18.3351,
+      "eval_samples_per_second": 17.453,
+      "eval_steps_per_second": 8.726,
+      "step": 480
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.6760151982307434,
+      "learning_rate": 0.0001,
+      "loss": 0.8256,
+      "mean_token_accuracy": 0.7666228592395783,
+      "num_tokens": 925208.0,
+      "step": 490
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.6286083459854126,
+      "learning_rate": 0.0001,
+      "loss": 0.7471,
+      "mean_token_accuracy": 0.7834655106067657,
+      "num_tokens": 944333.0,
+      "step": 500
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.6746655702590942,
+      "learning_rate": 0.0001,
+      "loss": 0.7931,
+      "mean_token_accuracy": 0.7782243847846985,
+      "num_tokens": 962570.0,
+      "step": 510
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.5208497643470764,
+      "learning_rate": 0.0001,
+      "loss": 0.8246,
+      "mean_token_accuracy": 0.7665972113609314,
+      "num_tokens": 981133.0,
+      "step": 520
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.7782342433929443,
+      "learning_rate": 0.0001,
+      "loss": 0.9398,
+      "mean_token_accuracy": 0.743607884645462,
+      "num_tokens": 997998.0,
+      "step": 530
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.6813472509384155,
+      "learning_rate": 0.0001,
+      "loss": 0.777,
+      "mean_token_accuracy": 0.7756537094712257,
+      "num_tokens": 1016188.0,
+      "step": 540
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.6890157461166382,
+      "learning_rate": 0.0001,
+      "loss": 0.8493,
+      "mean_token_accuracy": 0.7614479854702949,
+      "num_tokens": 1035174.0,
+      "step": 550
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.6942604780197144,
+      "learning_rate": 0.0001,
+      "loss": 0.8153,
+      "mean_token_accuracy": 0.7713455215096474,
+      "num_tokens": 1054954.0,
+      "step": 560
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.6722708344459534,
+      "learning_rate": 0.0001,
+      "loss": 0.8811,
+      "mean_token_accuracy": 0.7551201656460762,
+      "num_tokens": 1073025.0,
+      "step": 570
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.6637946963310242,
+      "learning_rate": 0.0001,
+      "loss": 0.7876,
+      "mean_token_accuracy": 0.7747491240501404,
+      "num_tokens": 1092124.0,
+      "step": 580
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.6677461862564087,
+      "learning_rate": 0.0001,
+      "loss": 0.8539,
+      "mean_token_accuracy": 0.762774932384491,
+      "num_tokens": 1110204.0,
+      "step": 590
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.4877650737762451,
+      "learning_rate": 0.0001,
+      "loss": 0.8402,
+      "mean_token_accuracy": 0.7657597422599792,
+      "num_tokens": 1129929.0,
+      "step": 600
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.6816550493240356,
+      "learning_rate": 0.0001,
+      "loss": 0.7319,
+      "mean_token_accuracy": 0.7943529888987542,
+      "num_tokens": 1149086.0,
+      "step": 610
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.7251542210578918,
+      "learning_rate": 0.0001,
+      "loss": 0.7057,
+      "mean_token_accuracy": 0.7959758445620537,
+      "num_tokens": 1168048.0,
+      "step": 620
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 0.7146134376525879,
+      "learning_rate": 0.0001,
+      "loss": 0.7221,
+      "mean_token_accuracy": 0.7933965891599655,
+      "num_tokens": 1186753.0,
+      "step": 630
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.6925667524337769,
+      "learning_rate": 0.0001,
+      "loss": 0.7238,
+      "mean_token_accuracy": 0.7958982989192009,
+      "num_tokens": 1205471.0,
+      "step": 640
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 1.1755249500274658,
+      "eval_mean_token_accuracy": 0.7095268920063973,
+      "eval_num_tokens": 1205471.0,
+      "eval_runtime": 18.3277,
+      "eval_samples_per_second": 17.46,
+      "eval_steps_per_second": 8.73,
+      "step": 640
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 160,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3837357892042752.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-640/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20619a8f09e05873c207ca3dd2fc4ded0b3cd0adfaf3ee7de8e7806e358f8ac
+size 5688

checkpoint-800/README.md

@@ -0,0 +1,202 @@
+---
+base_model: oliver213/MNLP_M3_mcqa_model
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

checkpoint-800/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "oliver213/MNLP_M3_mcqa_model",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 28,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "self_attn.q_proj",
+    "mlp.up_proj",
+    "mlp.down_proj",
+    "self_attn.o_proj",
+    "self_attn.v_proj",
+    "self_attn.k_proj",
+    "mlp.gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-800/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c310c47f276584bdada679c2094f523475ca0f1ba5ed9854e8fea360272f74f6
+size 70788906

checkpoint-800/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d8fb9a81f1bf545709ceea60a2a3da7408ff36489c2e669aa5ef5f8d650b21
+size 141625194

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e99638e2a850c7861a93788fbb231ee96bdf34118c627bfd10a0ea958af5523d
+size 14244

checkpoint-800/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d26e9687ed387160aa99c5f36032f8ef15c2391c97a795e46a4329714467bc
+size 988

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7847f5134d705577faee25af150145f5a0a552ec46c6008bc52ad812b9e8f038
+size 1064

checkpoint-800/special_tokens_map.json

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

checkpoint-800/tokenizer.json

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

checkpoint-800/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-800/trainer_state.json

@@ -0,0 +1,804 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 160,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.43827545642852783,
+      "learning_rate": 0.0001,
+      "loss": 0.9667,
+      "mean_token_accuracy": 0.7421795547008514,
+      "num_tokens": 18527.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.39240607619285583,
+      "learning_rate": 0.0001,
+      "loss": 1.0018,
+      "mean_token_accuracy": 0.728947314620018,
+      "num_tokens": 37412.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.38427555561065674,
+      "learning_rate": 0.0001,
+      "loss": 1.0093,
+      "mean_token_accuracy": 0.7267461150884629,
+      "num_tokens": 56239.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.42408332228660583,
+      "learning_rate": 0.0001,
+      "loss": 0.9559,
+      "mean_token_accuracy": 0.7414480298757553,
+      "num_tokens": 75307.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.46401479840278625,
+      "learning_rate": 0.0001,
+      "loss": 1.0349,
+      "mean_token_accuracy": 0.7188403815031051,
+      "num_tokens": 93699.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.4213346838951111,
+      "learning_rate": 0.0001,
+      "loss": 0.9546,
+      "mean_token_accuracy": 0.7375499308109283,
+      "num_tokens": 112724.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.40055790543556213,
+      "learning_rate": 0.0001,
+      "loss": 0.9743,
+      "mean_token_accuracy": 0.7378433406352997,
+      "num_tokens": 131831.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.45163631439208984,
+      "learning_rate": 0.0001,
+      "loss": 1.0189,
+      "mean_token_accuracy": 0.7263641938567161,
+      "num_tokens": 151163.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.4101933538913727,
+      "learning_rate": 0.0001,
+      "loss": 0.9672,
+      "mean_token_accuracy": 0.7346487194299698,
+      "num_tokens": 169973.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.44324934482574463,
+      "learning_rate": 0.0001,
+      "loss": 1.0263,
+      "mean_token_accuracy": 0.7225876390933991,
+      "num_tokens": 188998.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.47263675928115845,
+      "learning_rate": 0.0001,
+      "loss": 0.9865,
+      "mean_token_accuracy": 0.7291134670376778,
+      "num_tokens": 207403.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.418999046087265,
+      "learning_rate": 0.0001,
+      "loss": 0.9624,
+      "mean_token_accuracy": 0.7337665259838104,
+      "num_tokens": 225944.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.48299098014831543,
+      "learning_rate": 0.0001,
+      "loss": 1.0097,
+      "mean_token_accuracy": 0.7260663375258446,
+      "num_tokens": 244001.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.45383280515670776,
+      "learning_rate": 0.0001,
+      "loss": 0.9367,
+      "mean_token_accuracy": 0.7450008347630501,
+      "num_tokens": 262380.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.3950103521347046,
+      "learning_rate": 0.0001,
+      "loss": 0.9511,
+      "mean_token_accuracy": 0.7413627594709397,
+      "num_tokens": 281319.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5174494981765747,
+      "learning_rate": 0.0001,
+      "loss": 0.8982,
+      "mean_token_accuracy": 0.7503622397780418,
+      "num_tokens": 301270.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.0890034437179565,
+      "eval_mean_token_accuracy": 0.7177740011364222,
+      "eval_num_tokens": 301270.0,
+      "eval_runtime": 18.3264,
+      "eval_samples_per_second": 17.461,
+      "eval_steps_per_second": 8.731,
+      "step": 160
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.5073578953742981,
+      "learning_rate": 0.0001,
+      "loss": 0.9498,
+      "mean_token_accuracy": 0.7435929998755455,
+      "num_tokens": 320325.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.4688466489315033,
+      "learning_rate": 0.0001,
+      "loss": 0.957,
+      "mean_token_accuracy": 0.7374263137578965,
+      "num_tokens": 339313.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.5929768085479736,
+      "learning_rate": 0.0001,
+      "loss": 1.02,
+      "mean_token_accuracy": 0.7251972034573555,
+      "num_tokens": 357224.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5086683630943298,
+      "learning_rate": 0.0001,
+      "loss": 0.992,
+      "mean_token_accuracy": 0.7353695958852768,
+      "num_tokens": 376643.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.4679737985134125,
+      "learning_rate": 0.0001,
+      "loss": 0.8852,
+      "mean_token_accuracy": 0.7536615505814552,
+      "num_tokens": 395121.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.4789438843727112,
+      "learning_rate": 0.0001,
+      "loss": 0.9377,
+      "mean_token_accuracy": 0.7422916859388351,
+      "num_tokens": 413895.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.5487397313117981,
+      "learning_rate": 0.0001,
+      "loss": 0.8488,
+      "mean_token_accuracy": 0.7590507015585899,
+      "num_tokens": 432763.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.5337480306625366,
+      "learning_rate": 0.0001,
+      "loss": 0.8666,
+      "mean_token_accuracy": 0.7579806029796601,
+      "num_tokens": 451608.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.49510490894317627,
+      "learning_rate": 0.0001,
+      "loss": 0.9104,
+      "mean_token_accuracy": 0.7497919097542762,
+      "num_tokens": 470554.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.657990038394928,
+      "learning_rate": 0.0001,
+      "loss": 0.8951,
+      "mean_token_accuracy": 0.7483552470803261,
+      "num_tokens": 488654.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.6424926519393921,
+      "learning_rate": 0.0001,
+      "loss": 0.8812,
+      "mean_token_accuracy": 0.7524763226509095,
+      "num_tokens": 507895.0,
+      "step": 270
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.556791365146637,
+      "learning_rate": 0.0001,
+      "loss": 0.8923,
+      "mean_token_accuracy": 0.753830075263977,
+      "num_tokens": 526416.0,
+      "step": 280
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.5518726110458374,
+      "learning_rate": 0.0001,
+      "loss": 0.919,
+      "mean_token_accuracy": 0.7403171643614769,
+      "num_tokens": 545947.0,
+      "step": 290
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5887808799743652,
+      "learning_rate": 0.0001,
+      "loss": 0.9512,
+      "mean_token_accuracy": 0.741435107588768,
+      "num_tokens": 564070.0,
+      "step": 300
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.4931485056877136,
+      "learning_rate": 0.0001,
+      "loss": 0.8012,
+      "mean_token_accuracy": 0.775481553375721,
+      "num_tokens": 583519.0,
+      "step": 310
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.5791897177696228,
+      "learning_rate": 0.0001,
+      "loss": 0.8834,
+      "mean_token_accuracy": 0.7559772610664368,
+      "num_tokens": 602601.0,
+      "step": 320
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.0932101011276245,
+      "eval_mean_token_accuracy": 0.7169803511351347,
+      "eval_num_tokens": 602601.0,
+      "eval_runtime": 18.3278,
+      "eval_samples_per_second": 17.46,
+      "eval_steps_per_second": 8.73,
+      "step": 320
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.5467931032180786,
+      "learning_rate": 0.0001,
+      "loss": 0.9429,
+      "mean_token_accuracy": 0.7412704437971115,
+      "num_tokens": 621579.0,
+      "step": 330
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.5784661173820496,
+      "learning_rate": 0.0001,
+      "loss": 0.8529,
+      "mean_token_accuracy": 0.7641629755496979,
+      "num_tokens": 640332.0,
+      "step": 340
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.4568150043487549,
+      "learning_rate": 0.0001,
+      "loss": 0.8716,
+      "mean_token_accuracy": 0.7545537993311882,
+      "num_tokens": 659812.0,
+      "step": 350
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.5498734712600708,
+      "learning_rate": 0.0001,
+      "loss": 0.8971,
+      "mean_token_accuracy": 0.752374118566513,
+      "num_tokens": 678799.0,
+      "step": 360
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.5936706066131592,
+      "learning_rate": 0.0001,
+      "loss": 0.9918,
+      "mean_token_accuracy": 0.7298657700419426,
+      "num_tokens": 696438.0,
+      "step": 370
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.5029641389846802,
+      "learning_rate": 0.0001,
+      "loss": 0.9371,
+      "mean_token_accuracy": 0.7457024067640304,
+      "num_tokens": 715459.0,
+      "step": 380
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 0.4978192448616028,
+      "learning_rate": 0.0001,
+      "loss": 0.9429,
+      "mean_token_accuracy": 0.7435312032699585,
+      "num_tokens": 733927.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5036607384681702,
+      "learning_rate": 0.0001,
+      "loss": 0.9169,
+      "mean_token_accuracy": 0.7488818317651749,
+      "num_tokens": 753286.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.6137449741363525,
+      "learning_rate": 0.0001,
+      "loss": 0.7911,
+      "mean_token_accuracy": 0.7788830995559692,
+      "num_tokens": 772442.0,
+      "step": 410
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.5912206172943115,
+      "learning_rate": 0.0001,
+      "loss": 0.7946,
+      "mean_token_accuracy": 0.7781713724136352,
+      "num_tokens": 790693.0,
+      "step": 420
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.6016007661819458,
+      "learning_rate": 0.0001,
+      "loss": 0.7889,
+      "mean_token_accuracy": 0.7735364139080048,
+      "num_tokens": 809966.0,
+      "step": 430
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.5786302089691162,
+      "learning_rate": 0.0001,
+      "loss": 0.8027,
+      "mean_token_accuracy": 0.7732229202985763,
+      "num_tokens": 829851.0,
+      "step": 440
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.5368697047233582,
+      "learning_rate": 0.0001,
+      "loss": 0.8208,
+      "mean_token_accuracy": 0.7645123034715653,
+      "num_tokens": 848464.0,
+      "step": 450
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.712200403213501,
+      "learning_rate": 0.0001,
+      "loss": 0.8047,
+      "mean_token_accuracy": 0.7703322827816009,
+      "num_tokens": 867916.0,
+      "step": 460
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.7731253504753113,
+      "learning_rate": 0.0001,
+      "loss": 0.8328,
+      "mean_token_accuracy": 0.7687120333313942,
+      "num_tokens": 886785.0,
+      "step": 470
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.629067599773407,
+      "learning_rate": 0.0001,
+      "loss": 0.8092,
+      "mean_token_accuracy": 0.7728568613529205,
+      "num_tokens": 905795.0,
+      "step": 480
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.125347375869751,
+      "eval_mean_token_accuracy": 0.711500994861126,
+      "eval_num_tokens": 905795.0,
+      "eval_runtime": 18.3351,
+      "eval_samples_per_second": 17.453,
+      "eval_steps_per_second": 8.726,
+      "step": 480
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 0.6760151982307434,
+      "learning_rate": 0.0001,
+      "loss": 0.8256,
+      "mean_token_accuracy": 0.7666228592395783,
+      "num_tokens": 925208.0,
+      "step": 490
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.6286083459854126,
+      "learning_rate": 0.0001,
+      "loss": 0.7471,
+      "mean_token_accuracy": 0.7834655106067657,
+      "num_tokens": 944333.0,
+      "step": 500
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.6746655702590942,
+      "learning_rate": 0.0001,
+      "loss": 0.7931,
+      "mean_token_accuracy": 0.7782243847846985,
+      "num_tokens": 962570.0,
+      "step": 510
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.5208497643470764,
+      "learning_rate": 0.0001,
+      "loss": 0.8246,
+      "mean_token_accuracy": 0.7665972113609314,
+      "num_tokens": 981133.0,
+      "step": 520
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.7782342433929443,
+      "learning_rate": 0.0001,
+      "loss": 0.9398,
+      "mean_token_accuracy": 0.743607884645462,
+      "num_tokens": 997998.0,
+      "step": 530
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.6813472509384155,
+      "learning_rate": 0.0001,
+      "loss": 0.777,
+      "mean_token_accuracy": 0.7756537094712257,
+      "num_tokens": 1016188.0,
+      "step": 540
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.6890157461166382,
+      "learning_rate": 0.0001,
+      "loss": 0.8493,
+      "mean_token_accuracy": 0.7614479854702949,
+      "num_tokens": 1035174.0,
+      "step": 550
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.6942604780197144,
+      "learning_rate": 0.0001,
+      "loss": 0.8153,
+      "mean_token_accuracy": 0.7713455215096474,
+      "num_tokens": 1054954.0,
+      "step": 560
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.6722708344459534,
+      "learning_rate": 0.0001,
+      "loss": 0.8811,
+      "mean_token_accuracy": 0.7551201656460762,
+      "num_tokens": 1073025.0,
+      "step": 570
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.6637946963310242,
+      "learning_rate": 0.0001,
+      "loss": 0.7876,
+      "mean_token_accuracy": 0.7747491240501404,
+      "num_tokens": 1092124.0,
+      "step": 580
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.6677461862564087,
+      "learning_rate": 0.0001,
+      "loss": 0.8539,
+      "mean_token_accuracy": 0.762774932384491,
+      "num_tokens": 1110204.0,
+      "step": 590
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.4877650737762451,
+      "learning_rate": 0.0001,
+      "loss": 0.8402,
+      "mean_token_accuracy": 0.7657597422599792,
+      "num_tokens": 1129929.0,
+      "step": 600
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.6816550493240356,
+      "learning_rate": 0.0001,
+      "loss": 0.7319,
+      "mean_token_accuracy": 0.7943529888987542,
+      "num_tokens": 1149086.0,
+      "step": 610
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.7251542210578918,
+      "learning_rate": 0.0001,
+      "loss": 0.7057,
+      "mean_token_accuracy": 0.7959758445620537,
+      "num_tokens": 1168048.0,
+      "step": 620
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 0.7146134376525879,
+      "learning_rate": 0.0001,
+      "loss": 0.7221,
+      "mean_token_accuracy": 0.7933965891599655,
+      "num_tokens": 1186753.0,
+      "step": 630
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.6925667524337769,
+      "learning_rate": 0.0001,
+      "loss": 0.7238,
+      "mean_token_accuracy": 0.7958982989192009,
+      "num_tokens": 1205471.0,
+      "step": 640
+    },
+    {
+      "epoch": 3.2,
+      "eval_loss": 1.1755249500274658,
+      "eval_mean_token_accuracy": 0.7095268920063973,
+      "eval_num_tokens": 1205471.0,
+      "eval_runtime": 18.3277,
+      "eval_samples_per_second": 17.46,
+      "eval_steps_per_second": 8.73,
+      "step": 640
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.6561554074287415,
+      "learning_rate": 0.0001,
+      "loss": 0.7076,
+      "mean_token_accuracy": 0.7985713094472885,
+      "num_tokens": 1225099.0,
+      "step": 650
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.6188570857048035,
+      "learning_rate": 0.0001,
+      "loss": 0.7698,
+      "mean_token_accuracy": 0.7828378319740296,
+      "num_tokens": 1244074.0,
+      "step": 660
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 0.7147638201713562,
+      "learning_rate": 0.0001,
+      "loss": 0.6592,
+      "mean_token_accuracy": 0.8094674125313759,
+      "num_tokens": 1263781.0,
+      "step": 670
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.761284589767456,
+      "learning_rate": 0.0001,
+      "loss": 0.7407,
+      "mean_token_accuracy": 0.7847389072179795,
+      "num_tokens": 1282554.0,
+      "step": 680
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 0.7286498546600342,
+      "learning_rate": 0.0001,
+      "loss": 0.7481,
+      "mean_token_accuracy": 0.7902553915977478,
+      "num_tokens": 1300680.0,
+      "step": 690
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.8410418033599854,
+      "learning_rate": 0.0001,
+      "loss": 0.7742,
+      "mean_token_accuracy": 0.7788675397634506,
+      "num_tokens": 1318486.0,
+      "step": 700
+    },
+    {
+      "epoch": 3.55,
+      "grad_norm": 0.7173243165016174,
+      "learning_rate": 0.0001,
+      "loss": 0.7424,
+      "mean_token_accuracy": 0.784093214571476,
+      "num_tokens": 1337891.0,
+      "step": 710
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.7642121911048889,
+      "learning_rate": 0.0001,
+      "loss": 0.7925,
+      "mean_token_accuracy": 0.7764820963144302,
+      "num_tokens": 1355920.0,
+      "step": 720
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 0.5757165551185608,
+      "learning_rate": 0.0001,
+      "loss": 0.7781,
+      "mean_token_accuracy": 0.7775384098291397,
+      "num_tokens": 1374735.0,
+      "step": 730
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.8661559820175171,
+      "learning_rate": 0.0001,
+      "loss": 0.7351,
+      "mean_token_accuracy": 0.7928005129098892,
+      "num_tokens": 1393708.0,
+      "step": 740
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.6611236333847046,
+      "learning_rate": 0.0001,
+      "loss": 0.7353,
+      "mean_token_accuracy": 0.7899313852190971,
+      "num_tokens": 1412985.0,
+      "step": 750
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.787530779838562,
+      "learning_rate": 0.0001,
+      "loss": 0.758,
+      "mean_token_accuracy": 0.7841869756579399,
+      "num_tokens": 1431040.0,
+      "step": 760
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 0.8499215841293335,
+      "learning_rate": 0.0001,
+      "loss": 0.6919,
+      "mean_token_accuracy": 0.8019102051854133,
+      "num_tokens": 1450564.0,
+      "step": 770
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.6646876335144043,
+      "learning_rate": 0.0001,
+      "loss": 0.7811,
+      "mean_token_accuracy": 0.7774537593126297,
+      "num_tokens": 1468469.0,
+      "step": 780
+    },
+    {
+      "epoch": 3.95,
+      "grad_norm": 0.692534863948822,
+      "learning_rate": 0.0001,
+      "loss": 0.6728,
+      "mean_token_accuracy": 0.8075501427054406,
+      "num_tokens": 1487203.0,
+      "step": 790
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.673222541809082,
+      "learning_rate": 0.0001,
+      "loss": 0.6851,
+      "mean_token_accuracy": 0.7982731312513351,
+      "num_tokens": 1506572.0,
+      "step": 800
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.1678171157836914,
+      "eval_mean_token_accuracy": 0.708535186573863,
+      "eval_num_tokens": 1506572.0,
+      "eval_runtime": 18.3587,
+      "eval_samples_per_second": 17.43,
+      "eval_steps_per_second": 8.715,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 160,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4794283939332096.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20619a8f09e05873c207ca3dd2fc4ded0b3cd0adfaf3ee7de8e7806e358f8ac
+size 5688

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ad3c66fb92113a0c56622629c132f404344b62b7e706cc4e6c9cb0ba917a60
+size 2384234968

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}