Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-186/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+library_name: peft
+license: other
+base_model: unsloth/Qwen2.5-7B-Instruct-bnb-4bit
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen_lora
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen_lora
+
+This model is a fine-tuned version of [unsloth/Qwen2.5-7B-Instruct-bnb-4bit](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct-bnb-4bit) on the alpaca_en_demo dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.3.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24265fa4db48b82701ec9d851a8cf18ad230a758eb619e23ca65e6660c421c20
+size 80792096

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.976,
+    "total_flos": 1.5945119821725696e+16,
+    "train_loss": 0.7450424432754517,
+    "train_runtime": 1935.7993,
+    "train_samples_per_second": 0.775,
+    "train_steps_per_second": 0.096
+}

checkpoint-186/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen2.5-7B-Instruct-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-186/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-186/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24265fa4db48b82701ec9d851a8cf18ad230a758eb619e23ca65e6660c421c20
+size 80792096

checkpoint-186/added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-186/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44ec9ca2da4a77dbab0a75ca7135897c2d3af906e0fd87091efceb44f8b0770
+size 161810538

checkpoint-186/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-186/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7169aff194791ecda725e64de0c229a441c71e4d4927fa7f1fe7cde23ccff4b4
+size 1064

checkpoint-186/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": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-186/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

checkpoint-186/tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-186/trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.976,
+  "eval_steps": 500,
+  "global_step": 186,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.374408483505249,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 1.1454,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.311002641916275,
+      "learning_rate": 4.999557652060729e-05,
+      "loss": 1.0246,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.30777308344841003,
+      "learning_rate": 4.946665048328287e-05,
+      "loss": 0.9632,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4400554895401001,
+      "learning_rate": 4.807442755497524e-05,
+      "loss": 0.978,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4841279983520508,
+      "learning_rate": 4.586803181690609e-05,
+      "loss": 0.968,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.34245041012763977,
+      "learning_rate": 4.292531514268008e-05,
+      "loss": 0.9348,
+      "step": 60
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.4096768796443939,
+      "learning_rate": 3.9350110223152844e-05,
+      "loss": 0.7968,
+      "step": 70
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.6328812837600708,
+      "learning_rate": 3.526856686758269e-05,
+      "loss": 0.7295,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.47058913111686707,
+      "learning_rate": 3.082470085335133e-05,
+      "loss": 0.6724,
+      "step": 90
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.46030929684638977,
+      "learning_rate": 2.6175312381477442e-05,
+      "loss": 0.6994,
+      "step": 100
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.5056099891662598,
+      "learning_rate": 2.148445343837755e-05,
+      "loss": 0.7171,
+      "step": 110
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.39329010248184204,
+      "learning_rate": 1.69176392810087e-05,
+      "loss": 0.7364,
+      "step": 120
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.5568200349807739,
+      "learning_rate": 1.2636008291040618e-05,
+      "loss": 0.7352,
+      "step": 130
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.714911937713623,
+      "learning_rate": 8.790636265485334e-06,
+      "loss": 0.4738,
+      "step": 140
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.5729328989982605,
+      "learning_rate": 5.51720576197794e-06,
+      "loss": 0.5162,
+      "step": 150
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.6667868494987488,
+      "learning_rate": 2.931218588927315e-06,
+      "loss": 0.4586,
+      "step": 160
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.49541157484054565,
+      "learning_rate": 1.1239203660860648e-06,
+      "loss": 0.5178,
+      "step": 170
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.5764051079750061,
+      "learning_rate": 1.5908095594207583e-07,
+      "loss": 0.4586,
+      "step": 180
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 186,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5945119821725696e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-186/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b5e005dc9a5beca09dd51601eaba35b5f185b9d137518d28408059ed202c19
+size 5368

runs/Dec25_08-54-56_fceb1800ede4/events.out.tfevents.1735117070.fceb1800ede4.2439.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71f025f0909486ad19981fc063d770301da080bdc1f767f0ea119f3648f76a2
+size 9881

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": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

tokenizer_config.json

@@ -0,0 +1,216 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.976,
+    "total_flos": 1.5945119821725696e+16,
+    "train_loss": 0.7450424432754517,
+    "train_runtime": 1935.7993,
+    "train_samples_per_second": 0.775,
+    "train_steps_per_second": 0.096
+}

trainer_log.jsonl

@@ -0,0 +1,19 @@
+{"current_steps": 10, "total_steps": 186, "loss": 1.1454, "lr": 2.6315789473684212e-05, "epoch": 0.16, "percentage": 5.38, "elapsed_time": "0:01:44", "remaining_time": "0:30:38"}
+{"current_steps": 20, "total_steps": 186, "loss": 1.0246, "lr": 4.999557652060729e-05, "epoch": 0.32, "percentage": 10.75, "elapsed_time": "0:03:28", "remaining_time": "0:28:47"}
+{"current_steps": 30, "total_steps": 186, "loss": 0.9632, "lr": 4.946665048328287e-05, "epoch": 0.48, "percentage": 16.13, "elapsed_time": "0:05:07", "remaining_time": "0:26:40"}
+{"current_steps": 40, "total_steps": 186, "loss": 0.978, "lr": 4.807442755497524e-05, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:06:54", "remaining_time": "0:25:13"}
+{"current_steps": 50, "total_steps": 186, "loss": 0.968, "lr": 4.586803181690609e-05, "epoch": 0.8, "percentage": 26.88, "elapsed_time": "0:08:35", "remaining_time": "0:23:22"}
+{"current_steps": 60, "total_steps": 186, "loss": 0.9348, "lr": 4.292531514268008e-05, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:10:16", "remaining_time": "0:21:34"}
+{"current_steps": 70, "total_steps": 186, "loss": 0.7968, "lr": 3.9350110223152844e-05, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:11:56", "remaining_time": "0:19:47"}
+{"current_steps": 80, "total_steps": 186, "loss": 0.7295, "lr": 3.526856686758269e-05, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "0:13:42", "remaining_time": "0:18:09"}
+{"current_steps": 90, "total_steps": 186, "loss": 0.6724, "lr": 3.082470085335133e-05, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "0:15:20", "remaining_time": "0:16:21"}
+{"current_steps": 100, "total_steps": 186, "loss": 0.6994, "lr": 2.6175312381477442e-05, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:17:00", "remaining_time": "0:14:37"}
+{"current_steps": 110, "total_steps": 186, "loss": 0.7171, "lr": 2.148445343837755e-05, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "0:18:39", "remaining_time": "0:12:53"}
+{"current_steps": 120, "total_steps": 186, "loss": 0.7364, "lr": 1.69176392810087e-05, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:20:24", "remaining_time": "0:11:13"}
+{"current_steps": 130, "total_steps": 186, "loss": 0.7352, "lr": 1.2636008291040618e-05, "epoch": 2.08, "percentage": 69.89, "elapsed_time": "0:22:10", "remaining_time": "0:09:33"}
+{"current_steps": 140, "total_steps": 186, "loss": 0.4738, "lr": 8.790636265485334e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:24:05", "remaining_time": "0:07:54"}
+{"current_steps": 150, "total_steps": 186, "loss": 0.5162, "lr": 5.51720576197794e-06, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "0:25:43", "remaining_time": "0:06:10"}
+{"current_steps": 160, "total_steps": 186, "loss": 0.4586, "lr": 2.931218588927315e-06, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:27:18", "remaining_time": "0:04:26"}
+{"current_steps": 170, "total_steps": 186, "loss": 0.5178, "lr": 1.1239203660860648e-06, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "0:28:57", "remaining_time": "0:02:43"}
+{"current_steps": 180, "total_steps": 186, "loss": 0.4586, "lr": 1.5908095594207583e-07, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:30:50", "remaining_time": "0:01:01"}
+{"current_steps": 186, "total_steps": 186, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:31:47", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,168 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.976,
+  "eval_steps": 500,
+  "global_step": 186,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.374408483505249,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 1.1454,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.311002641916275,
+      "learning_rate": 4.999557652060729e-05,
+      "loss": 1.0246,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.30777308344841003,
+      "learning_rate": 4.946665048328287e-05,
+      "loss": 0.9632,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.4400554895401001,
+      "learning_rate": 4.807442755497524e-05,
+      "loss": 0.978,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.4841279983520508,
+      "learning_rate": 4.586803181690609e-05,
+      "loss": 0.968,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.34245041012763977,
+      "learning_rate": 4.292531514268008e-05,
+      "loss": 0.9348,
+      "step": 60
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.4096768796443939,
+      "learning_rate": 3.9350110223152844e-05,
+      "loss": 0.7968,
+      "step": 70
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.6328812837600708,
+      "learning_rate": 3.526856686758269e-05,
+      "loss": 0.7295,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.47058913111686707,
+      "learning_rate": 3.082470085335133e-05,
+      "loss": 0.6724,
+      "step": 90
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.46030929684638977,
+      "learning_rate": 2.6175312381477442e-05,
+      "loss": 0.6994,
+      "step": 100
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.5056099891662598,
+      "learning_rate": 2.148445343837755e-05,
+      "loss": 0.7171,
+      "step": 110
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.39329010248184204,
+      "learning_rate": 1.69176392810087e-05,
+      "loss": 0.7364,
+      "step": 120
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.5568200349807739,
+      "learning_rate": 1.2636008291040618e-05,
+      "loss": 0.7352,
+      "step": 130
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.714911937713623,
+      "learning_rate": 8.790636265485334e-06,
+      "loss": 0.4738,
+      "step": 140
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.5729328989982605,
+      "learning_rate": 5.51720576197794e-06,
+      "loss": 0.5162,
+      "step": 150
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.6667868494987488,
+      "learning_rate": 2.931218588927315e-06,
+      "loss": 0.4586,
+      "step": 160
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.49541157484054565,
+      "learning_rate": 1.1239203660860648e-06,
+      "loss": 0.5178,
+      "step": 170
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.5764051079750061,
+      "learning_rate": 1.5908095594207583e-07,
+      "loss": 0.4586,
+      "step": 180
+    },
+    {
+      "epoch": 2.976,
+      "step": 186,
+      "total_flos": 1.5945119821725696e+16,
+      "train_loss": 0.7450424432754517,
+      "train_runtime": 1935.7993,
+      "train_samples_per_second": 0.775,
+      "train_steps_per_second": 0.096
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 186,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5945119821725696e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b5e005dc9a5beca09dd51601eaba35b5f185b9d137518d28408059ed202c19
+size 5368