Add files using upload-large-folder tool

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-138/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-138/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-138/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-138/special_tokens_map.json

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

checkpoint-138/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-138/trainer_state.json

@@ -0,0 +1,223 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.973544973544973,
+  "eval_steps": 500,
+  "global_step": 138,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21164021164021163,
+      "grad_norm": 0.01096427347511053,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.3143,
+      "step": 5
+    },
+    {
+      "epoch": 0.42328042328042326,
+      "grad_norm": 0.013951408676803112,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.3576,
+      "step": 10
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.01673784852027893,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.3639,
+      "step": 15
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 0.019934486597776413,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.3458,
+      "step": 20
+    },
+    {
+      "epoch": 1.0846560846560847,
+      "grad_norm": 0.02395496889948845,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.4603,
+      "step": 25
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.017271244898438454,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.3034,
+      "step": 30
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.023819392547011375,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.3317,
+      "step": 35
+    },
+    {
+      "epoch": 1.7195767195767195,
+      "grad_norm": 0.021737879142165184,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.3382,
+      "step": 40
+    },
+    {
+      "epoch": 1.9312169312169312,
+      "grad_norm": 0.023687848821282387,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.3288,
+      "step": 45
+    },
+    {
+      "epoch": 2.1693121693121693,
+      "grad_norm": 0.024081828072667122,
+      "learning_rate": 4.9988484157560136e-05,
+      "loss": 0.3521,
+      "step": 50
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.03236062824726105,
+      "learning_rate": 4.994171922976348e-05,
+      "loss": 0.3485,
+      "step": 55
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.03175266832113266,
+      "learning_rate": 4.9859052738933966e-05,
+      "loss": 0.2979,
+      "step": 60
+    },
+    {
+      "epoch": 2.804232804232804,
+      "grad_norm": 0.030012985691428185,
+      "learning_rate": 4.974060367671783e-05,
+      "loss": 0.3055,
+      "step": 65
+    },
+    {
+      "epoch": 3.0423280423280423,
+      "grad_norm": 0.10118062049150467,
+      "learning_rate": 4.958654254084355e-05,
+      "loss": 0.3521,
+      "step": 70
+    },
+    {
+      "epoch": 3.253968253968254,
+      "grad_norm": 0.02641722746193409,
+      "learning_rate": 4.9397091089704364e-05,
+      "loss": 0.3041,
+      "step": 75
+    },
+    {
+      "epoch": 3.4656084656084656,
+      "grad_norm": 0.03561725839972496,
+      "learning_rate": 4.9172522023155154e-05,
+      "loss": 0.2778,
+      "step": 80
+    },
+    {
+      "epoch": 3.677248677248677,
+      "grad_norm": 0.04121287539601326,
+      "learning_rate": 4.8913158589983374e-05,
+      "loss": 0.2698,
+      "step": 85
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.04533043131232262,
+      "learning_rate": 4.8619374122618854e-05,
+      "loss": 0.2704,
+      "step": 90
+    },
+    {
+      "epoch": 4.1269841269841265,
+      "grad_norm": 0.04685904085636139,
+      "learning_rate": 4.8291591499752365e-05,
+      "loss": 0.3338,
+      "step": 95
+    },
+    {
+      "epoch": 4.338624338624339,
+      "grad_norm": 0.06093249469995499,
+      "learning_rate": 4.793028253763633e-05,
+      "loss": 0.2794,
+      "step": 100
+    },
+    {
+      "epoch": 4.550264550264551,
+      "grad_norm": 0.060147590935230255,
+      "learning_rate": 4.7535967310943955e-05,
+      "loss": 0.2724,
+      "step": 105
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.05850926414132118,
+      "learning_rate": 4.710921340416431e-05,
+      "loss": 0.2547,
+      "step": 110
+    },
+    {
+      "epoch": 4.973544973544973,
+      "grad_norm": 0.0650046169757843,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.241,
+      "step": 115
+    },
+    {
+      "epoch": 5.211640211640212,
+      "grad_norm": 0.07884380221366882,
+      "learning_rate": 4.616089246822003e-05,
+      "loss": 0.291,
+      "step": 120
+    },
+    {
+      "epoch": 5.423280423280423,
+      "grad_norm": 0.07263286411762238,
+      "learning_rate": 4.564069046941049e-05,
+      "loss": 0.256,
+      "step": 125
+    },
+    {
+      "epoch": 5.634920634920634,
+      "grad_norm": 0.08540436625480652,
+      "learning_rate": 4.509077788637446e-05,
+      "loss": 0.2362,
+      "step": 130
+    },
+    {
+      "epoch": 5.8465608465608465,
+      "grad_norm": 0.07003481686115265,
+      "learning_rate": 4.4511946273257846e-05,
+      "loss": 0.1973,
+      "step": 135
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 23,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.383923710024745e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-184/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-207/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-207/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-207/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-207/special_tokens_map.json

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

checkpoint-207/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-207/trainer_state.json

@@ -0,0 +1,321 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.973544973544973,
+  "eval_steps": 500,
+  "global_step": 207,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21164021164021163,
+      "grad_norm": 0.01096427347511053,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.3143,
+      "step": 5
+    },
+    {
+      "epoch": 0.42328042328042326,
+      "grad_norm": 0.013951408676803112,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.3576,
+      "step": 10
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.01673784852027893,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.3639,
+      "step": 15
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 0.019934486597776413,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.3458,
+      "step": 20
+    },
+    {
+      "epoch": 1.0846560846560847,
+      "grad_norm": 0.02395496889948845,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.4603,
+      "step": 25
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.017271244898438454,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.3034,
+      "step": 30
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.023819392547011375,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.3317,
+      "step": 35
+    },
+    {
+      "epoch": 1.7195767195767195,
+      "grad_norm": 0.021737879142165184,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.3382,
+      "step": 40
+    },
+    {
+      "epoch": 1.9312169312169312,
+      "grad_norm": 0.023687848821282387,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.3288,
+      "step": 45
+    },
+    {
+      "epoch": 2.1693121693121693,
+      "grad_norm": 0.024081828072667122,
+      "learning_rate": 4.9988484157560136e-05,
+      "loss": 0.3521,
+      "step": 50
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.03236062824726105,
+      "learning_rate": 4.994171922976348e-05,
+      "loss": 0.3485,
+      "step": 55
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.03175266832113266,
+      "learning_rate": 4.9859052738933966e-05,
+      "loss": 0.2979,
+      "step": 60
+    },
+    {
+      "epoch": 2.804232804232804,
+      "grad_norm": 0.030012985691428185,
+      "learning_rate": 4.974060367671783e-05,
+      "loss": 0.3055,
+      "step": 65
+    },
+    {
+      "epoch": 3.0423280423280423,
+      "grad_norm": 0.10118062049150467,
+      "learning_rate": 4.958654254084355e-05,
+      "loss": 0.3521,
+      "step": 70
+    },
+    {
+      "epoch": 3.253968253968254,
+      "grad_norm": 0.02641722746193409,
+      "learning_rate": 4.9397091089704364e-05,
+      "loss": 0.3041,
+      "step": 75
+    },
+    {
+      "epoch": 3.4656084656084656,
+      "grad_norm": 0.03561725839972496,
+      "learning_rate": 4.9172522023155154e-05,
+      "loss": 0.2778,
+      "step": 80
+    },
+    {
+      "epoch": 3.677248677248677,
+      "grad_norm": 0.04121287539601326,
+      "learning_rate": 4.8913158589983374e-05,
+      "loss": 0.2698,
+      "step": 85
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.04533043131232262,
+      "learning_rate": 4.8619374122618854e-05,
+      "loss": 0.2704,
+      "step": 90
+    },
+    {
+      "epoch": 4.1269841269841265,
+      "grad_norm": 0.04685904085636139,
+      "learning_rate": 4.8291591499752365e-05,
+      "loss": 0.3338,
+      "step": 95
+    },
+    {
+      "epoch": 4.338624338624339,
+      "grad_norm": 0.06093249469995499,
+      "learning_rate": 4.793028253763633e-05,
+      "loss": 0.2794,
+      "step": 100
+    },
+    {
+      "epoch": 4.550264550264551,
+      "grad_norm": 0.060147590935230255,
+      "learning_rate": 4.7535967310943955e-05,
+      "loss": 0.2724,
+      "step": 105
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.05850926414132118,
+      "learning_rate": 4.710921340416431e-05,
+      "loss": 0.2547,
+      "step": 110
+    },
+    {
+      "epoch": 4.973544973544973,
+      "grad_norm": 0.0650046169757843,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.241,
+      "step": 115
+    },
+    {
+      "epoch": 5.211640211640212,
+      "grad_norm": 0.07884380221366882,
+      "learning_rate": 4.616089246822003e-05,
+      "loss": 0.291,
+      "step": 120
+    },
+    {
+      "epoch": 5.423280423280423,
+      "grad_norm": 0.07263286411762238,
+      "learning_rate": 4.564069046941049e-05,
+      "loss": 0.256,
+      "step": 125
+    },
+    {
+      "epoch": 5.634920634920634,
+      "grad_norm": 0.08540436625480652,
+      "learning_rate": 4.509077788637446e-05,
+      "loss": 0.2362,
+      "step": 130
+    },
+    {
+      "epoch": 5.8465608465608465,
+      "grad_norm": 0.07003481686115265,
+      "learning_rate": 4.4511946273257846e-05,
+      "loss": 0.1973,
+      "step": 135
+    },
+    {
+      "epoch": 6.084656084656085,
+      "grad_norm": 0.08097032457590103,
+      "learning_rate": 4.390502881078296e-05,
+      "loss": 0.3011,
+      "step": 140
+    },
+    {
+      "epoch": 6.296296296296296,
+      "grad_norm": 0.07847806811332703,
+      "learning_rate": 4.3270899106953105e-05,
+      "loss": 0.2066,
+      "step": 145
+    },
+    {
+      "epoch": 6.507936507936508,
+      "grad_norm": 0.10350590199232101,
+      "learning_rate": 4.261046993956531e-05,
+      "loss": 0.2236,
+      "step": 150
+    },
+    {
+      "epoch": 6.71957671957672,
+      "grad_norm": 0.11323926597833633,
+      "learning_rate": 4.192469194234148e-05,
+      "loss": 0.2215,
+      "step": 155
+    },
+    {
+      "epoch": 6.931216931216931,
+      "grad_norm": 0.09281644225120544,
+      "learning_rate": 4.12145522365689e-05,
+      "loss": 0.2251,
+      "step": 160
+    },
+    {
+      "epoch": 7.169312169312169,
+      "grad_norm": 0.09772001951932907,
+      "learning_rate": 4.048107301022005e-05,
+      "loss": 0.2554,
+      "step": 165
+    },
+    {
+      "epoch": 7.380952380952381,
+      "grad_norm": 0.10654748976230621,
+      "learning_rate": 3.9725310046596595e-05,
+      "loss": 0.2058,
+      "step": 170
+    },
+    {
+      "epoch": 7.592592592592593,
+      "grad_norm": 0.08744902163743973,
+      "learning_rate": 3.894835120461584e-05,
+      "loss": 0.1731,
+      "step": 175
+    },
+    {
+      "epoch": 7.804232804232804,
+      "grad_norm": 0.11190956830978394,
+      "learning_rate": 3.815131485292678e-05,
+      "loss": 0.1955,
+      "step": 180
+    },
+    {
+      "epoch": 8.042328042328043,
+      "grad_norm": 0.3187606632709503,
+      "learning_rate": 3.733534826011008e-05,
+      "loss": 0.1913,
+      "step": 185
+    },
+    {
+      "epoch": 8.253968253968253,
+      "grad_norm": 0.12188898772001266,
+      "learning_rate": 3.6501625943278805e-05,
+      "loss": 0.1777,
+      "step": 190
+    },
+    {
+      "epoch": 8.465608465608465,
+      "grad_norm": 0.09240734577178955,
+      "learning_rate": 3.5651347977457214e-05,
+      "loss": 0.1776,
+      "step": 195
+    },
+    {
+      "epoch": 8.677248677248677,
+      "grad_norm": 0.12097247689962387,
+      "learning_rate": 3.478573826817099e-05,
+      "loss": 0.1812,
+      "step": 200
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.14317023754119873,
+      "learning_rate": 3.390604278973543e-05,
+      "loss": 0.1636,
+      "step": 205
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 23,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2575517725247406e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-23/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-23/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-23/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-23/special_tokens_map.json

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

checkpoint-23/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-23/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9735449735449735,
+  "eval_steps": 500,
+  "global_step": 23,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21164021164021163,
+      "grad_norm": 0.01096427347511053,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.3143,
+      "step": 5
+    },
+    {
+      "epoch": 0.42328042328042326,
+      "grad_norm": 0.013951408676803112,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.3576,
+      "step": 10
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.01673784852027893,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.3639,
+      "step": 15
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 0.019934486597776413,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.3458,
+      "step": 20
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 23,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.388755083633623e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-230/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-230/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-230/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-230/special_tokens_map.json

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

checkpoint-230/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-230/trainer_state.json

@@ -0,0 +1,356 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.973544973544973,
+  "eval_steps": 500,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21164021164021163,
+      "grad_norm": 0.01096427347511053,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.3143,
+      "step": 5
+    },
+    {
+      "epoch": 0.42328042328042326,
+      "grad_norm": 0.013951408676803112,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.3576,
+      "step": 10
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.01673784852027893,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.3639,
+      "step": 15
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 0.019934486597776413,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.3458,
+      "step": 20
+    },
+    {
+      "epoch": 1.0846560846560847,
+      "grad_norm": 0.02395496889948845,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.4603,
+      "step": 25
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.017271244898438454,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.3034,
+      "step": 30
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.023819392547011375,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.3317,
+      "step": 35
+    },
+    {
+      "epoch": 1.7195767195767195,
+      "grad_norm": 0.021737879142165184,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.3382,
+      "step": 40
+    },
+    {
+      "epoch": 1.9312169312169312,
+      "grad_norm": 0.023687848821282387,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.3288,
+      "step": 45
+    },
+    {
+      "epoch": 2.1693121693121693,
+      "grad_norm": 0.024081828072667122,
+      "learning_rate": 4.9988484157560136e-05,
+      "loss": 0.3521,
+      "step": 50
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.03236062824726105,
+      "learning_rate": 4.994171922976348e-05,
+      "loss": 0.3485,
+      "step": 55
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.03175266832113266,
+      "learning_rate": 4.9859052738933966e-05,
+      "loss": 0.2979,
+      "step": 60
+    },
+    {
+      "epoch": 2.804232804232804,
+      "grad_norm": 0.030012985691428185,
+      "learning_rate": 4.974060367671783e-05,
+      "loss": 0.3055,
+      "step": 65
+    },
+    {
+      "epoch": 3.0423280423280423,
+      "grad_norm": 0.10118062049150467,
+      "learning_rate": 4.958654254084355e-05,
+      "loss": 0.3521,
+      "step": 70
+    },
+    {
+      "epoch": 3.253968253968254,
+      "grad_norm": 0.02641722746193409,
+      "learning_rate": 4.9397091089704364e-05,
+      "loss": 0.3041,
+      "step": 75
+    },
+    {
+      "epoch": 3.4656084656084656,
+      "grad_norm": 0.03561725839972496,
+      "learning_rate": 4.9172522023155154e-05,
+      "loss": 0.2778,
+      "step": 80
+    },
+    {
+      "epoch": 3.677248677248677,
+      "grad_norm": 0.04121287539601326,
+      "learning_rate": 4.8913158589983374e-05,
+      "loss": 0.2698,
+      "step": 85
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.04533043131232262,
+      "learning_rate": 4.8619374122618854e-05,
+      "loss": 0.2704,
+      "step": 90
+    },
+    {
+      "epoch": 4.1269841269841265,
+      "grad_norm": 0.04685904085636139,
+      "learning_rate": 4.8291591499752365e-05,
+      "loss": 0.3338,
+      "step": 95
+    },
+    {
+      "epoch": 4.338624338624339,
+      "grad_norm": 0.06093249469995499,
+      "learning_rate": 4.793028253763633e-05,
+      "loss": 0.2794,
+      "step": 100
+    },
+    {
+      "epoch": 4.550264550264551,
+      "grad_norm": 0.060147590935230255,
+      "learning_rate": 4.7535967310943955e-05,
+      "loss": 0.2724,
+      "step": 105
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.05850926414132118,
+      "learning_rate": 4.710921340416431e-05,
+      "loss": 0.2547,
+      "step": 110
+    },
+    {
+      "epoch": 4.973544973544973,
+      "grad_norm": 0.0650046169757843,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.241,
+      "step": 115
+    },
+    {
+      "epoch": 5.211640211640212,
+      "grad_norm": 0.07884380221366882,
+      "learning_rate": 4.616089246822003e-05,
+      "loss": 0.291,
+      "step": 120
+    },
+    {
+      "epoch": 5.423280423280423,
+      "grad_norm": 0.07263286411762238,
+      "learning_rate": 4.564069046941049e-05,
+      "loss": 0.256,
+      "step": 125
+    },
+    {
+      "epoch": 5.634920634920634,
+      "grad_norm": 0.08540436625480652,
+      "learning_rate": 4.509077788637446e-05,
+      "loss": 0.2362,
+      "step": 130
+    },
+    {
+      "epoch": 5.8465608465608465,
+      "grad_norm": 0.07003481686115265,
+      "learning_rate": 4.4511946273257846e-05,
+      "loss": 0.1973,
+      "step": 135
+    },
+    {
+      "epoch": 6.084656084656085,
+      "grad_norm": 0.08097032457590103,
+      "learning_rate": 4.390502881078296e-05,
+      "loss": 0.3011,
+      "step": 140
+    },
+    {
+      "epoch": 6.296296296296296,
+      "grad_norm": 0.07847806811332703,
+      "learning_rate": 4.3270899106953105e-05,
+      "loss": 0.2066,
+      "step": 145
+    },
+    {
+      "epoch": 6.507936507936508,
+      "grad_norm": 0.10350590199232101,
+      "learning_rate": 4.261046993956531e-05,
+      "loss": 0.2236,
+      "step": 150
+    },
+    {
+      "epoch": 6.71957671957672,
+      "grad_norm": 0.11323926597833633,
+      "learning_rate": 4.192469194234148e-05,
+      "loss": 0.2215,
+      "step": 155
+    },
+    {
+      "epoch": 6.931216931216931,
+      "grad_norm": 0.09281644225120544,
+      "learning_rate": 4.12145522365689e-05,
+      "loss": 0.2251,
+      "step": 160
+    },
+    {
+      "epoch": 7.169312169312169,
+      "grad_norm": 0.09772001951932907,
+      "learning_rate": 4.048107301022005e-05,
+      "loss": 0.2554,
+      "step": 165
+    },
+    {
+      "epoch": 7.380952380952381,
+      "grad_norm": 0.10654748976230621,
+      "learning_rate": 3.9725310046596595e-05,
+      "loss": 0.2058,
+      "step": 170
+    },
+    {
+      "epoch": 7.592592592592593,
+      "grad_norm": 0.08744902163743973,
+      "learning_rate": 3.894835120461584e-05,
+      "loss": 0.1731,
+      "step": 175
+    },
+    {
+      "epoch": 7.804232804232804,
+      "grad_norm": 0.11190956830978394,
+      "learning_rate": 3.815131485292678e-05,
+      "loss": 0.1955,
+      "step": 180
+    },
+    {
+      "epoch": 8.042328042328043,
+      "grad_norm": 0.3187606632709503,
+      "learning_rate": 3.733534826011008e-05,
+      "loss": 0.1913,
+      "step": 185
+    },
+    {
+      "epoch": 8.253968253968253,
+      "grad_norm": 0.12188898772001266,
+      "learning_rate": 3.6501625943278805e-05,
+      "loss": 0.1777,
+      "step": 190
+    },
+    {
+      "epoch": 8.465608465608465,
+      "grad_norm": 0.09240734577178955,
+      "learning_rate": 3.5651347977457214e-05,
+      "loss": 0.1776,
+      "step": 195
+    },
+    {
+      "epoch": 8.677248677248677,
+      "grad_norm": 0.12097247689962387,
+      "learning_rate": 3.478573826817099e-05,
+      "loss": 0.1812,
+      "step": 200
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.14317023754119873,
+      "learning_rate": 3.390604278973543e-05,
+      "loss": 0.1636,
+      "step": 205
+    },
+    {
+      "epoch": 9.126984126984127,
+      "grad_norm": 0.1255073994398117,
+      "learning_rate": 3.301352779177743e-05,
+      "loss": 0.2084,
+      "step": 210
+    },
+    {
+      "epoch": 9.338624338624339,
+      "grad_norm": 0.15191367268562317,
+      "learning_rate": 3.21094779765728e-05,
+      "loss": 0.159,
+      "step": 215
+    },
+    {
+      "epoch": 9.55026455026455,
+      "grad_norm": 0.14779330790042877,
+      "learning_rate": 3.11951946498225e-05,
+      "loss": 0.1521,
+      "step": 220
+    },
+    {
+      "epoch": 9.761904761904763,
+      "grad_norm": 0.14298541843891144,
+      "learning_rate": 3.027199384752962e-05,
+      "loss": 0.1485,
+      "step": 225
+    },
+    {
+      "epoch": 9.973544973544973,
+      "grad_norm": 0.14848679304122925,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.1488,
+      "step": 230
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 23,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3971264779415716e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-299/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-299/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-322/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-322/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-322/special_tokens_map.json

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

checkpoint-322/trainer_state.json

@@ -0,0 +1,482 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.973544973544973,
+  "eval_steps": 500,
+  "global_step": 322,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21164021164021163,
+      "grad_norm": 0.01096427347511053,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.3143,
+      "step": 5
+    },
+    {
+      "epoch": 0.42328042328042326,
+      "grad_norm": 0.013951408676803112,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.3576,
+      "step": 10
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.01673784852027893,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.3639,
+      "step": 15
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 0.019934486597776413,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.3458,
+      "step": 20
+    },
+    {
+      "epoch": 1.0846560846560847,
+      "grad_norm": 0.02395496889948845,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.4603,
+      "step": 25
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.017271244898438454,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.3034,
+      "step": 30
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.023819392547011375,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.3317,
+      "step": 35
+    },
+    {
+      "epoch": 1.7195767195767195,
+      "grad_norm": 0.021737879142165184,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.3382,
+      "step": 40
+    },
+    {
+      "epoch": 1.9312169312169312,
+      "grad_norm": 0.023687848821282387,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.3288,
+      "step": 45
+    },
+    {
+      "epoch": 2.1693121693121693,
+      "grad_norm": 0.024081828072667122,
+      "learning_rate": 4.9988484157560136e-05,
+      "loss": 0.3521,
+      "step": 50
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.03236062824726105,
+      "learning_rate": 4.994171922976348e-05,
+      "loss": 0.3485,
+      "step": 55
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.03175266832113266,
+      "learning_rate": 4.9859052738933966e-05,
+      "loss": 0.2979,
+      "step": 60
+    },
+    {
+      "epoch": 2.804232804232804,
+      "grad_norm": 0.030012985691428185,
+      "learning_rate": 4.974060367671783e-05,
+      "loss": 0.3055,
+      "step": 65
+    },
+    {
+      "epoch": 3.0423280423280423,
+      "grad_norm": 0.10118062049150467,
+      "learning_rate": 4.958654254084355e-05,
+      "loss": 0.3521,
+      "step": 70
+    },
+    {
+      "epoch": 3.253968253968254,
+      "grad_norm": 0.02641722746193409,
+      "learning_rate": 4.9397091089704364e-05,
+      "loss": 0.3041,
+      "step": 75
+    },
+    {
+      "epoch": 3.4656084656084656,
+      "grad_norm": 0.03561725839972496,
+      "learning_rate": 4.9172522023155154e-05,
+      "loss": 0.2778,
+      "step": 80
+    },
+    {
+      "epoch": 3.677248677248677,
+      "grad_norm": 0.04121287539601326,
+      "learning_rate": 4.8913158589983374e-05,
+      "loss": 0.2698,
+      "step": 85
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.04533043131232262,
+      "learning_rate": 4.8619374122618854e-05,
+      "loss": 0.2704,
+      "step": 90
+    },
+    {
+      "epoch": 4.1269841269841265,
+      "grad_norm": 0.04685904085636139,
+      "learning_rate": 4.8291591499752365e-05,
+      "loss": 0.3338,
+      "step": 95
+    },
+    {
+      "epoch": 4.338624338624339,
+      "grad_norm": 0.06093249469995499,
+      "learning_rate": 4.793028253763633e-05,
+      "loss": 0.2794,
+      "step": 100
+    },
+    {
+      "epoch": 4.550264550264551,
+      "grad_norm": 0.060147590935230255,
+      "learning_rate": 4.7535967310943955e-05,
+      "loss": 0.2724,
+      "step": 105
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.05850926414132118,
+      "learning_rate": 4.710921340416431e-05,
+      "loss": 0.2547,
+      "step": 110
+    },
+    {
+      "epoch": 4.973544973544973,
+      "grad_norm": 0.0650046169757843,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.241,
+      "step": 115
+    },
+    {
+      "epoch": 5.211640211640212,
+      "grad_norm": 0.07884380221366882,
+      "learning_rate": 4.616089246822003e-05,
+      "loss": 0.291,
+      "step": 120
+    },
+    {
+      "epoch": 5.423280423280423,
+      "grad_norm": 0.07263286411762238,
+      "learning_rate": 4.564069046941049e-05,
+      "loss": 0.256,
+      "step": 125
+    },
+    {
+      "epoch": 5.634920634920634,
+      "grad_norm": 0.08540436625480652,
+      "learning_rate": 4.509077788637446e-05,
+      "loss": 0.2362,
+      "step": 130
+    },
+    {
+      "epoch": 5.8465608465608465,
+      "grad_norm": 0.07003481686115265,
+      "learning_rate": 4.4511946273257846e-05,
+      "loss": 0.1973,
+      "step": 135
+    },
+    {
+      "epoch": 6.084656084656085,
+      "grad_norm": 0.08097032457590103,
+      "learning_rate": 4.390502881078296e-05,
+      "loss": 0.3011,
+      "step": 140
+    },
+    {
+      "epoch": 6.296296296296296,
+      "grad_norm": 0.07847806811332703,
+      "learning_rate": 4.3270899106953105e-05,
+      "loss": 0.2066,
+      "step": 145
+    },
+    {
+      "epoch": 6.507936507936508,
+      "grad_norm": 0.10350590199232101,
+      "learning_rate": 4.261046993956531e-05,
+      "loss": 0.2236,
+      "step": 150
+    },
+    {
+      "epoch": 6.71957671957672,
+      "grad_norm": 0.11323926597833633,
+      "learning_rate": 4.192469194234148e-05,
+      "loss": 0.2215,
+      "step": 155
+    },
+    {
+      "epoch": 6.931216931216931,
+      "grad_norm": 0.09281644225120544,
+      "learning_rate": 4.12145522365689e-05,
+      "loss": 0.2251,
+      "step": 160
+    },
+    {
+      "epoch": 7.169312169312169,
+      "grad_norm": 0.09772001951932907,
+      "learning_rate": 4.048107301022005e-05,
+      "loss": 0.2554,
+      "step": 165
+    },
+    {
+      "epoch": 7.380952380952381,
+      "grad_norm": 0.10654748976230621,
+      "learning_rate": 3.9725310046596595e-05,
+      "loss": 0.2058,
+      "step": 170
+    },
+    {
+      "epoch": 7.592592592592593,
+      "grad_norm": 0.08744902163743973,
+      "learning_rate": 3.894835120461584e-05,
+      "loss": 0.1731,
+      "step": 175
+    },
+    {
+      "epoch": 7.804232804232804,
+      "grad_norm": 0.11190956830978394,
+      "learning_rate": 3.815131485292678e-05,
+      "loss": 0.1955,
+      "step": 180
+    },
+    {
+      "epoch": 8.042328042328043,
+      "grad_norm": 0.3187606632709503,
+      "learning_rate": 3.733534826011008e-05,
+      "loss": 0.1913,
+      "step": 185
+    },
+    {
+      "epoch": 8.253968253968253,
+      "grad_norm": 0.12188898772001266,
+      "learning_rate": 3.6501625943278805e-05,
+      "loss": 0.1777,
+      "step": 190
+    },
+    {
+      "epoch": 8.465608465608465,
+      "grad_norm": 0.09240734577178955,
+      "learning_rate": 3.5651347977457214e-05,
+      "loss": 0.1776,
+      "step": 195
+    },
+    {
+      "epoch": 8.677248677248677,
+      "grad_norm": 0.12097247689962387,
+      "learning_rate": 3.478573826817099e-05,
+      "loss": 0.1812,
+      "step": 200
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.14317023754119873,
+      "learning_rate": 3.390604278973543e-05,
+      "loss": 0.1636,
+      "step": 205
+    },
+    {
+      "epoch": 9.126984126984127,
+      "grad_norm": 0.1255073994398117,
+      "learning_rate": 3.301352779177743e-05,
+      "loss": 0.2084,
+      "step": 210
+    },
+    {
+      "epoch": 9.338624338624339,
+      "grad_norm": 0.15191367268562317,
+      "learning_rate": 3.21094779765728e-05,
+      "loss": 0.159,
+      "step": 215
+    },
+    {
+      "epoch": 9.55026455026455,
+      "grad_norm": 0.14779330790042877,
+      "learning_rate": 3.11951946498225e-05,
+      "loss": 0.1521,
+      "step": 220
+    },
+    {
+      "epoch": 9.761904761904763,
+      "grad_norm": 0.14298541843891144,
+      "learning_rate": 3.027199384752962e-05,
+      "loss": 0.1485,
+      "step": 225
+    },
+    {
+      "epoch": 9.973544973544973,
+      "grad_norm": 0.14848679304122925,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.1488,
+      "step": 230
+    },
+    {
+      "epoch": 10.211640211640212,
+      "grad_norm": 0.15250274538993835,
+      "learning_rate": 2.840416622740617e-05,
+      "loss": 0.1604,
+      "step": 235
+    },
+    {
+      "epoch": 10.423280423280424,
+      "grad_norm": 0.2765931487083435,
+      "learning_rate": 2.7462227994529217e-05,
+      "loss": 0.1455,
+      "step": 240
+    },
+    {
+      "epoch": 10.634920634920634,
+      "grad_norm": 0.16372708976268768,
+      "learning_rate": 2.6516745586018965e-05,
+      "loss": 0.1236,
+      "step": 245
+    },
+    {
+      "epoch": 10.846560846560847,
+      "grad_norm": 0.3377860486507416,
+      "learning_rate": 2.556907994640264e-05,
+      "loss": 0.1393,
+      "step": 250
+    },
+    {
+      "epoch": 11.084656084656086,
+      "grad_norm": 0.1836676001548767,
+      "learning_rate": 2.4620595162789936e-05,
+      "loss": 0.1473,
+      "step": 255
+    },
+    {
+      "epoch": 11.296296296296296,
+      "grad_norm": 0.15243783593177795,
+      "learning_rate": 2.3672656501381272e-05,
+      "loss": 0.1366,
+      "step": 260
+    },
+    {
+      "epoch": 11.507936507936508,
+      "grad_norm": 0.1481999307870865,
+      "learning_rate": 2.2726628442278826e-05,
+      "loss": 0.1039,
+      "step": 265
+    },
+    {
+      "epoch": 11.71957671957672,
+      "grad_norm": 0.17082872986793518,
+      "learning_rate": 2.1783872715429228e-05,
+      "loss": 0.1196,
+      "step": 270
+    },
+    {
+      "epoch": 11.93121693121693,
+      "grad_norm": 0.16833926737308502,
+      "learning_rate": 2.084574634052465e-05,
+      "loss": 0.1245,
+      "step": 275
+    },
+    {
+      "epoch": 12.16931216931217,
+      "grad_norm": 0.18557614088058472,
+      "learning_rate": 1.991359967368416e-05,
+      "loss": 0.1174,
+      "step": 280
+    },
+    {
+      "epoch": 12.380952380952381,
+      "grad_norm": 0.13334429264068604,
+      "learning_rate": 1.8988774463726543e-05,
+      "loss": 0.0977,
+      "step": 285
+    },
+    {
+      "epoch": 12.592592592592592,
+      "grad_norm": 0.18030914664268494,
+      "learning_rate": 1.8072601920832786e-05,
+      "loss": 0.1147,
+      "step": 290
+    },
+    {
+      "epoch": 12.804232804232804,
+      "grad_norm": 0.19089557230472565,
+      "learning_rate": 1.7166400800377948e-05,
+      "loss": 0.1132,
+      "step": 295
+    },
+    {
+      "epoch": 13.042328042328043,
+      "grad_norm": 0.3375261127948761,
+      "learning_rate": 1.6271475504690792e-05,
+      "loss": 0.1448,
+      "step": 300
+    },
+    {
+      "epoch": 13.253968253968253,
+      "grad_norm": 0.1948479562997818,
+      "learning_rate": 1.5389114205473377e-05,
+      "loss": 0.1119,
+      "step": 305
+    },
+    {
+      "epoch": 13.465608465608465,
+      "grad_norm": 0.1664939522743225,
+      "learning_rate": 1.4520586989583406e-05,
+      "loss": 0.0932,
+      "step": 310
+    },
+    {
+      "epoch": 13.677248677248677,
+      "grad_norm": 0.16317923367023468,
+      "learning_rate": 1.3667144030848073e-05,
+      "loss": 0.1007,
+      "step": 315
+    },
+    {
+      "epoch": 13.88888888888889,
+      "grad_norm": 0.18476559221744537,
+      "learning_rate": 1.2830013790541279e-05,
+      "loss": 0.105,
+      "step": 320
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 23,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.956024584985641e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-345/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-14B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.0

checkpoint-345/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-345/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-345/special_tokens_map.json

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

checkpoint-345/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-345/trainer_state.json

@@ -0,0 +1,517 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.973544973544973,
+  "eval_steps": 500,
+  "global_step": 345,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21164021164021163,
+      "grad_norm": 0.01096427347511053,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.3143,
+      "step": 5
+    },
+    {
+      "epoch": 0.42328042328042326,
+      "grad_norm": 0.013951408676803112,
+      "learning_rate": 1.0869565217391305e-05,
+      "loss": 0.3576,
+      "step": 10
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.01673784852027893,
+      "learning_rate": 1.630434782608696e-05,
+      "loss": 0.3639,
+      "step": 15
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 0.019934486597776413,
+      "learning_rate": 2.173913043478261e-05,
+      "loss": 0.3458,
+      "step": 20
+    },
+    {
+      "epoch": 1.0846560846560847,
+      "grad_norm": 0.02395496889948845,
+      "learning_rate": 2.7173913043478262e-05,
+      "loss": 0.4603,
+      "step": 25
+    },
+    {
+      "epoch": 1.2962962962962963,
+      "grad_norm": 0.017271244898438454,
+      "learning_rate": 3.260869565217392e-05,
+      "loss": 0.3034,
+      "step": 30
+    },
+    {
+      "epoch": 1.507936507936508,
+      "grad_norm": 0.023819392547011375,
+      "learning_rate": 3.804347826086957e-05,
+      "loss": 0.3317,
+      "step": 35
+    },
+    {
+      "epoch": 1.7195767195767195,
+      "grad_norm": 0.021737879142165184,
+      "learning_rate": 4.347826086956522e-05,
+      "loss": 0.3382,
+      "step": 40
+    },
+    {
+      "epoch": 1.9312169312169312,
+      "grad_norm": 0.023687848821282387,
+      "learning_rate": 4.891304347826087e-05,
+      "loss": 0.3288,
+      "step": 45
+    },
+    {
+      "epoch": 2.1693121693121693,
+      "grad_norm": 0.024081828072667122,
+      "learning_rate": 4.9988484157560136e-05,
+      "loss": 0.3521,
+      "step": 50
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.03236062824726105,
+      "learning_rate": 4.994171922976348e-05,
+      "loss": 0.3485,
+      "step": 55
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 0.03175266832113266,
+      "learning_rate": 4.9859052738933966e-05,
+      "loss": 0.2979,
+      "step": 60
+    },
+    {
+      "epoch": 2.804232804232804,
+      "grad_norm": 0.030012985691428185,
+      "learning_rate": 4.974060367671783e-05,
+      "loss": 0.3055,
+      "step": 65
+    },
+    {
+      "epoch": 3.0423280423280423,
+      "grad_norm": 0.10118062049150467,
+      "learning_rate": 4.958654254084355e-05,
+      "loss": 0.3521,
+      "step": 70
+    },
+    {
+      "epoch": 3.253968253968254,
+      "grad_norm": 0.02641722746193409,
+      "learning_rate": 4.9397091089704364e-05,
+      "loss": 0.3041,
+      "step": 75
+    },
+    {
+      "epoch": 3.4656084656084656,
+      "grad_norm": 0.03561725839972496,
+      "learning_rate": 4.9172522023155154e-05,
+      "loss": 0.2778,
+      "step": 80
+    },
+    {
+      "epoch": 3.677248677248677,
+      "grad_norm": 0.04121287539601326,
+      "learning_rate": 4.8913158589983374e-05,
+      "loss": 0.2698,
+      "step": 85
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.04533043131232262,
+      "learning_rate": 4.8619374122618854e-05,
+      "loss": 0.2704,
+      "step": 90
+    },
+    {
+      "epoch": 4.1269841269841265,
+      "grad_norm": 0.04685904085636139,
+      "learning_rate": 4.8291591499752365e-05,
+      "loss": 0.3338,
+      "step": 95
+    },
+    {
+      "epoch": 4.338624338624339,
+      "grad_norm": 0.06093249469995499,
+      "learning_rate": 4.793028253763633e-05,
+      "loss": 0.2794,
+      "step": 100
+    },
+    {
+      "epoch": 4.550264550264551,
+      "grad_norm": 0.060147590935230255,
+      "learning_rate": 4.7535967310943955e-05,
+      "loss": 0.2724,
+      "step": 105
+    },
+    {
+      "epoch": 4.761904761904762,
+      "grad_norm": 0.05850926414132118,
+      "learning_rate": 4.710921340416431e-05,
+      "loss": 0.2547,
+      "step": 110
+    },
+    {
+      "epoch": 4.973544973544973,
+      "grad_norm": 0.0650046169757843,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.241,
+      "step": 115
+    },
+    {
+      "epoch": 5.211640211640212,
+      "grad_norm": 0.07884380221366882,
+      "learning_rate": 4.616089246822003e-05,
+      "loss": 0.291,
+      "step": 120
+    },
+    {
+      "epoch": 5.423280423280423,
+      "grad_norm": 0.07263286411762238,
+      "learning_rate": 4.564069046941049e-05,
+      "loss": 0.256,
+      "step": 125
+    },
+    {
+      "epoch": 5.634920634920634,
+      "grad_norm": 0.08540436625480652,
+      "learning_rate": 4.509077788637446e-05,
+      "loss": 0.2362,
+      "step": 130
+    },
+    {
+      "epoch": 5.8465608465608465,
+      "grad_norm": 0.07003481686115265,
+      "learning_rate": 4.4511946273257846e-05,
+      "loss": 0.1973,
+      "step": 135
+    },
+    {
+      "epoch": 6.084656084656085,
+      "grad_norm": 0.08097032457590103,
+      "learning_rate": 4.390502881078296e-05,
+      "loss": 0.3011,
+      "step": 140
+    },
+    {
+      "epoch": 6.296296296296296,
+      "grad_norm": 0.07847806811332703,
+      "learning_rate": 4.3270899106953105e-05,
+      "loss": 0.2066,
+      "step": 145
+    },
+    {
+      "epoch": 6.507936507936508,
+      "grad_norm": 0.10350590199232101,
+      "learning_rate": 4.261046993956531e-05,
+      "loss": 0.2236,
+      "step": 150
+    },
+    {
+      "epoch": 6.71957671957672,
+      "grad_norm": 0.11323926597833633,
+      "learning_rate": 4.192469194234148e-05,
+      "loss": 0.2215,
+      "step": 155
+    },
+    {
+      "epoch": 6.931216931216931,
+      "grad_norm": 0.09281644225120544,
+      "learning_rate": 4.12145522365689e-05,
+      "loss": 0.2251,
+      "step": 160
+    },
+    {
+      "epoch": 7.169312169312169,
+      "grad_norm": 0.09772001951932907,
+      "learning_rate": 4.048107301022005e-05,
+      "loss": 0.2554,
+      "step": 165
+    },
+    {
+      "epoch": 7.380952380952381,
+      "grad_norm": 0.10654748976230621,
+      "learning_rate": 3.9725310046596595e-05,
+      "loss": 0.2058,
+      "step": 170
+    },
+    {
+      "epoch": 7.592592592592593,
+      "grad_norm": 0.08744902163743973,
+      "learning_rate": 3.894835120461584e-05,
+      "loss": 0.1731,
+      "step": 175
+    },
+    {
+      "epoch": 7.804232804232804,
+      "grad_norm": 0.11190956830978394,
+      "learning_rate": 3.815131485292678e-05,
+      "loss": 0.1955,
+      "step": 180
+    },
+    {
+      "epoch": 8.042328042328043,
+      "grad_norm": 0.3187606632709503,
+      "learning_rate": 3.733534826011008e-05,
+      "loss": 0.1913,
+      "step": 185
+    },
+    {
+      "epoch": 8.253968253968253,
+      "grad_norm": 0.12188898772001266,
+      "learning_rate": 3.6501625943278805e-05,
+      "loss": 0.1777,
+      "step": 190
+    },
+    {
+      "epoch": 8.465608465608465,
+      "grad_norm": 0.09240734577178955,
+      "learning_rate": 3.5651347977457214e-05,
+      "loss": 0.1776,
+      "step": 195
+    },
+    {
+      "epoch": 8.677248677248677,
+      "grad_norm": 0.12097247689962387,
+      "learning_rate": 3.478573826817099e-05,
+      "loss": 0.1812,
+      "step": 200
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.14317023754119873,
+      "learning_rate": 3.390604278973543e-05,
+      "loss": 0.1636,
+      "step": 205
+    },
+    {
+      "epoch": 9.126984126984127,
+      "grad_norm": 0.1255073994398117,
+      "learning_rate": 3.301352779177743e-05,
+      "loss": 0.2084,
+      "step": 210
+    },
+    {
+      "epoch": 9.338624338624339,
+      "grad_norm": 0.15191367268562317,
+      "learning_rate": 3.21094779765728e-05,
+      "loss": 0.159,
+      "step": 215
+    },
+    {
+      "epoch": 9.55026455026455,
+      "grad_norm": 0.14779330790042877,
+      "learning_rate": 3.11951946498225e-05,
+      "loss": 0.1521,
+      "step": 220
+    },
+    {
+      "epoch": 9.761904761904763,
+      "grad_norm": 0.14298541843891144,
+      "learning_rate": 3.027199384752962e-05,
+      "loss": 0.1485,
+      "step": 225
+    },
+    {
+      "epoch": 9.973544973544973,
+      "grad_norm": 0.14848679304122925,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.1488,
+      "step": 230
+    },
+    {
+      "epoch": 10.211640211640212,
+      "grad_norm": 0.15250274538993835,
+      "learning_rate": 2.840416622740617e-05,
+      "loss": 0.1604,
+      "step": 235
+    },
+    {
+      "epoch": 10.423280423280424,
+      "grad_norm": 0.2765931487083435,
+      "learning_rate": 2.7462227994529217e-05,
+      "loss": 0.1455,
+      "step": 240
+    },
+    {
+      "epoch": 10.634920634920634,
+      "grad_norm": 0.16372708976268768,
+      "learning_rate": 2.6516745586018965e-05,
+      "loss": 0.1236,
+      "step": 245
+    },
+    {
+      "epoch": 10.846560846560847,
+      "grad_norm": 0.3377860486507416,
+      "learning_rate": 2.556907994640264e-05,
+      "loss": 0.1393,
+      "step": 250
+    },
+    {
+      "epoch": 11.084656084656086,
+      "grad_norm": 0.1836676001548767,
+      "learning_rate": 2.4620595162789936e-05,
+      "loss": 0.1473,
+      "step": 255
+    },
+    {
+      "epoch": 11.296296296296296,
+      "grad_norm": 0.15243783593177795,
+      "learning_rate": 2.3672656501381272e-05,
+      "loss": 0.1366,
+      "step": 260
+    },
+    {
+      "epoch": 11.507936507936508,
+      "grad_norm": 0.1481999307870865,
+      "learning_rate": 2.2726628442278826e-05,
+      "loss": 0.1039,
+      "step": 265
+    },
+    {
+      "epoch": 11.71957671957672,
+      "grad_norm": 0.17082872986793518,
+      "learning_rate": 2.1783872715429228e-05,
+      "loss": 0.1196,
+      "step": 270
+    },
+    {
+      "epoch": 11.93121693121693,
+      "grad_norm": 0.16833926737308502,
+      "learning_rate": 2.084574634052465e-05,
+      "loss": 0.1245,
+      "step": 275
+    },
+    {
+      "epoch": 12.16931216931217,
+      "grad_norm": 0.18557614088058472,
+      "learning_rate": 1.991359967368416e-05,
+      "loss": 0.1174,
+      "step": 280
+    },
+    {
+      "epoch": 12.380952380952381,
+      "grad_norm": 0.13334429264068604,
+      "learning_rate": 1.8988774463726543e-05,
+      "loss": 0.0977,
+      "step": 285
+    },
+    {
+      "epoch": 12.592592592592592,
+      "grad_norm": 0.18030914664268494,
+      "learning_rate": 1.8072601920832786e-05,
+      "loss": 0.1147,
+      "step": 290
+    },
+    {
+      "epoch": 12.804232804232804,
+      "grad_norm": 0.19089557230472565,
+      "learning_rate": 1.7166400800377948e-05,
+      "loss": 0.1132,
+      "step": 295
+    },
+    {
+      "epoch": 13.042328042328043,
+      "grad_norm": 0.3375261127948761,
+      "learning_rate": 1.6271475504690792e-05,
+      "loss": 0.1448,
+      "step": 300
+    },
+    {
+      "epoch": 13.253968253968253,
+      "grad_norm": 0.1948479562997818,
+      "learning_rate": 1.5389114205473377e-05,
+      "loss": 0.1119,
+      "step": 305
+    },
+    {
+      "epoch": 13.465608465608465,
+      "grad_norm": 0.1664939522743225,
+      "learning_rate": 1.4520586989583406e-05,
+      "loss": 0.0932,
+      "step": 310
+    },
+    {
+      "epoch": 13.677248677248677,
+      "grad_norm": 0.16317923367023468,
+      "learning_rate": 1.3667144030848073e-05,
+      "loss": 0.1007,
+      "step": 315
+    },
+    {
+      "epoch": 13.88888888888889,
+      "grad_norm": 0.18476559221744537,
+      "learning_rate": 1.2830013790541279e-05,
+      "loss": 0.105,
+      "step": 320
+    },
+    {
+      "epoch": 14.126984126984127,
+      "grad_norm": 0.13438890874385834,
+      "learning_rate": 1.2010401249114167e-05,
+      "loss": 0.1177,
+      "step": 325
+    },
+    {
+      "epoch": 14.338624338624339,
+      "grad_norm": 0.18302133679389954,
+      "learning_rate": 1.120948617172432e-05,
+      "loss": 0.0864,
+      "step": 330
+    },
+    {
+      "epoch": 14.55026455026455,
+      "grad_norm": 0.18818943202495575,
+      "learning_rate": 1.0428421410060541e-05,
+      "loss": 0.0878,
+      "step": 335
+    },
+    {
+      "epoch": 14.761904761904763,
+      "grad_norm": 0.17307747900485992,
+      "learning_rate": 9.668331242907089e-06,
+      "loss": 0.0895,
+      "step": 340
+    },
+    {
+      "epoch": 14.973544973544973,
+      "grad_norm": 0.2092498242855072,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.0918,
+      "step": 345
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 23,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.094982432167035e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}