Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 qwen/checkpoints/sft_gsm8k_seed42/checkpoint-699/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen/checkpoints/sft_gsm8k_seed42/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen/checkpoints/sft_gsm8k_seed1337/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen/checkpoints/sft_gsm8k_seed1337/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-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 0.13.2

qwen/checkpoints/sft_gsm8k_seed1337/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

qwen/checkpoints/sft_gsm8k_seed1337/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04aefb5a35b703b2d053b7f364f2f9cfb6a1de37162fd158a6e221aca74cabe
+size 17462432

qwen/checkpoints/sft_gsm8k_seed1337/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
+}

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-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 0.13.2

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04aefb5a35b703b2d053b7f364f2f9cfb6a1de37162fd158a6e221aca74cabe
+size 17462432

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/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
+}

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35a2ab7c70be55c7fe653e2eafadda81e4293509cb80b78b1c3e458814c4964
+size 35053178

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737cf7a154e2e6869e80576d529f989859f03b999572a463bb94e3e80b1b3d4c
+size 14308

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1af59d8d234cfc7e604f49159069c77ef0cfec0c5e2449ca8c58e1f92f74b8
+size 1064

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/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
+  }
+}

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145191e3b102f64e84dab1926006ee71528c1ea536df048ef9ff6c48d01f95de
+size 11421995

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/trainer_state.json

@@ -0,0 +1,516 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9962546816479403,
+  "eval_steps": 500,
+  "global_step": 699,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.042803638309256285,
+      "grad_norm": 1.4108669757843018,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 1.3418,
+      "step": 10
+    },
+    {
+      "epoch": 0.08560727661851257,
+      "grad_norm": 1.2749494314193726,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 1.3042,
+      "step": 20
+    },
+    {
+      "epoch": 0.12841091492776885,
+      "grad_norm": 1.2247868776321411,
+      "learning_rate": 1.9991305743680013e-05,
+      "loss": 1.137,
+      "step": 30
+    },
+    {
+      "epoch": 0.17121455323702514,
+      "grad_norm": 1.0098671913146973,
+      "learning_rate": 1.9961270933041475e-05,
+      "loss": 1.0148,
+      "step": 40
+    },
+    {
+      "epoch": 0.21401819154628143,
+      "grad_norm": 0.9898428320884705,
+      "learning_rate": 1.990985269065736e-05,
+      "loss": 0.883,
+      "step": 50
+    },
+    {
+      "epoch": 0.2568218298555377,
+      "grad_norm": 1.2555296421051025,
+      "learning_rate": 1.9837161393856413e-05,
+      "loss": 0.7329,
+      "step": 60
+    },
+    {
+      "epoch": 0.299625468164794,
+      "grad_norm": 0.8754366636276245,
+      "learning_rate": 1.974335308591806e-05,
+      "loss": 0.5819,
+      "step": 70
+    },
+    {
+      "epoch": 0.3424291064740503,
+      "grad_norm": 0.8238789439201355,
+      "learning_rate": 1.962862914110101e-05,
+      "loss": 0.4974,
+      "step": 80
+    },
+    {
+      "epoch": 0.3852327447833066,
+      "grad_norm": 0.5965980887413025,
+      "learning_rate": 1.9493235832361812e-05,
+      "loss": 0.4259,
+      "step": 90
+    },
+    {
+      "epoch": 0.42803638309256287,
+      "grad_norm": 0.46980294585227966,
+      "learning_rate": 1.9337463802691265e-05,
+      "loss": 0.3794,
+      "step": 100
+    },
+    {
+      "epoch": 0.47084002140181913,
+      "grad_norm": 0.45517849922180176,
+      "learning_rate": 1.9161647441203648e-05,
+      "loss": 0.3527,
+      "step": 110
+    },
+    {
+      "epoch": 0.5136436597110754,
+      "grad_norm": 0.46742144227027893,
+      "learning_rate": 1.8966164165317968e-05,
+      "loss": 0.342,
+      "step": 120
+    },
+    {
+      "epoch": 0.5564472980203318,
+      "grad_norm": 0.4608956575393677,
+      "learning_rate": 1.8751433610572243e-05,
+      "loss": 0.3034,
+      "step": 130
+    },
+    {
+      "epoch": 0.599250936329588,
+      "grad_norm": 0.39544877409935,
+      "learning_rate": 1.851791672980993e-05,
+      "loss": 0.3012,
+      "step": 140
+    },
+    {
+      "epoch": 0.6420545746388443,
+      "grad_norm": 0.29131045937538147,
+      "learning_rate": 1.826611480367232e-05,
+      "loss": 0.2845,
+      "step": 150
+    },
+    {
+      "epoch": 0.6848582129481006,
+      "grad_norm": 0.3586638867855072,
+      "learning_rate": 1.7996568364520895e-05,
+      "loss": 0.2862,
+      "step": 160
+    },
+    {
+      "epoch": 0.7276618512573568,
+      "grad_norm": 0.2759409248828888,
+      "learning_rate": 1.770985603609982e-05,
+      "loss": 0.287,
+      "step": 170
+    },
+    {
+      "epoch": 0.7704654895666132,
+      "grad_norm": 0.24364928901195526,
+      "learning_rate": 1.740659329142922e-05,
+      "loss": 0.2893,
+      "step": 180
+    },
+    {
+      "epoch": 0.8132691278758695,
+      "grad_norm": 0.23871150612831116,
+      "learning_rate": 1.7087431131595723e-05,
+      "loss": 0.2828,
+      "step": 190
+    },
+    {
+      "epoch": 0.8560727661851257,
+      "grad_norm": 0.25748080015182495,
+      "learning_rate": 1.6753054688276443e-05,
+      "loss": 0.2756,
+      "step": 200
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 0.2715812623500824,
+      "learning_rate": 1.6404181752996287e-05,
+      "loss": 0.2821,
+      "step": 210
+    },
+    {
+      "epoch": 0.9416800428036383,
+      "grad_norm": 0.19565141201019287,
+      "learning_rate": 1.6041561236275777e-05,
+      "loss": 0.2744,
+      "step": 220
+    },
+    {
+      "epoch": 0.9844836811128946,
+      "grad_norm": 0.1980738341808319,
+      "learning_rate": 1.5665971559977035e-05,
+      "loss": 0.2655,
+      "step": 230
+    },
+    {
+      "epoch": 1.0294275013376137,
+      "grad_norm": 0.31273457407951355,
+      "learning_rate": 1.5278218986299074e-05,
+      "loss": 0.2901,
+      "step": 240
+    },
+    {
+      "epoch": 1.07223113964687,
+      "grad_norm": 0.2494707852602005,
+      "learning_rate": 1.4879135887009435e-05,
+      "loss": 0.2756,
+      "step": 250
+    },
+    {
+      "epoch": 1.1150347779561263,
+      "grad_norm": 0.2570095956325531,
+      "learning_rate": 1.4469578956627497e-05,
+      "loss": 0.2643,
+      "step": 260
+    },
+    {
+      "epoch": 1.1578384162653825,
+      "grad_norm": 0.26001790165901184,
+      "learning_rate": 1.4050427373395241e-05,
+      "loss": 0.2696,
+      "step": 270
+    },
+    {
+      "epoch": 1.2006420545746388,
+      "grad_norm": 0.2460668385028839,
+      "learning_rate": 1.3622580911983121e-05,
+      "loss": 0.2694,
+      "step": 280
+    },
+    {
+      "epoch": 1.243445692883895,
+      "grad_norm": 0.2309606522321701,
+      "learning_rate": 1.3186958011982502e-05,
+      "loss": 0.2706,
+      "step": 290
+    },
+    {
+      "epoch": 1.2862493311931513,
+      "grad_norm": 0.28805845975875854,
+      "learning_rate": 1.274449380633089e-05,
+      "loss": 0.2713,
+      "step": 300
+    },
+    {
+      "epoch": 1.3290529695024076,
+      "grad_norm": 0.2375771552324295,
+      "learning_rate": 1.2296138113902309e-05,
+      "loss": 0.2628,
+      "step": 310
+    },
+    {
+      "epoch": 1.3718566078116639,
+      "grad_norm": 0.2360721081495285,
+      "learning_rate": 1.1842853400571972e-05,
+      "loss": 0.2734,
+      "step": 320
+    },
+    {
+      "epoch": 1.4146602461209203,
+      "grad_norm": 0.2730007767677307,
+      "learning_rate": 1.1385612713132191e-05,
+      "loss": 0.2604,
+      "step": 330
+    },
+    {
+      "epoch": 1.4574638844301766,
+      "grad_norm": 0.2703000605106354,
+      "learning_rate": 1.0925397590494713e-05,
+      "loss": 0.2719,
+      "step": 340
+    },
+    {
+      "epoch": 1.5002675227394329,
+      "grad_norm": 0.2142963409423828,
+      "learning_rate": 1.0463195956663339e-05,
+      "loss": 0.263,
+      "step": 350
+    },
+    {
+      "epoch": 1.5430711610486891,
+      "grad_norm": 0.2485300749540329,
+      "learning_rate": 1e-05,
+      "loss": 0.2701,
+      "step": 360
+    },
+    {
+      "epoch": 1.5858747993579454,
+      "grad_norm": 0.28012847900390625,
+      "learning_rate": 9.536804043336665e-06,
+      "loss": 0.2603,
+      "step": 370
+    },
+    {
+      "epoch": 1.6286784376672017,
+      "grad_norm": 0.23859111964702606,
+      "learning_rate": 9.074602409505293e-06,
+      "loss": 0.2561,
+      "step": 380
+    },
+    {
+      "epoch": 1.6714820759764581,
+      "grad_norm": 0.23310120403766632,
+      "learning_rate": 8.614387286867814e-06,
+      "loss": 0.2585,
+      "step": 390
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.19549022614955902,
+      "learning_rate": 8.157146599428028e-06,
+      "loss": 0.2596,
+      "step": 400
+    },
+    {
+      "epoch": 1.7570893525949707,
+      "grad_norm": 0.24275732040405273,
+      "learning_rate": 7.70386188609769e-06,
+      "loss": 0.2562,
+      "step": 410
+    },
+    {
+      "epoch": 1.799892990904227,
+      "grad_norm": 0.314504474401474,
+      "learning_rate": 7.2555061936691104e-06,
+      "loss": 0.2602,
+      "step": 420
+    },
+    {
+      "epoch": 1.8426966292134832,
+      "grad_norm": 0.2241068035364151,
+      "learning_rate": 6.8130419880175015e-06,
+      "loss": 0.2676,
+      "step": 430
+    },
+    {
+      "epoch": 1.8855002675227395,
+      "grad_norm": 0.24036559462547302,
+      "learning_rate": 6.3774190880168804e-06,
+      "loss": 0.2672,
+      "step": 440
+    },
+    {
+      "epoch": 1.9283039058319957,
+      "grad_norm": 0.2659877836704254,
+      "learning_rate": 5.9495726266047605e-06,
+      "loss": 0.2706,
+      "step": 450
+    },
+    {
+      "epoch": 1.971107544141252,
+      "grad_norm": 0.2469673752784729,
+      "learning_rate": 5.530421043372507e-06,
+      "loss": 0.2681,
+      "step": 460
+    },
+    {
+      "epoch": 2.016051364365971,
+      "grad_norm": 0.23773925006389618,
+      "learning_rate": 5.120864112990569e-06,
+      "loss": 0.2866,
+      "step": 470
+    },
+    {
+      "epoch": 2.0588550026752275,
+      "grad_norm": 0.25430721044540405,
+      "learning_rate": 4.721781013700928e-06,
+      "loss": 0.2593,
+      "step": 480
+    },
+    {
+      "epoch": 2.1016586409844837,
+      "grad_norm": 0.21865913271903992,
+      "learning_rate": 4.3340284400229675e-06,
+      "loss": 0.2501,
+      "step": 490
+    },
+    {
+      "epoch": 2.14446227929374,
+      "grad_norm": 0.22996032238006592,
+      "learning_rate": 3.9584387637242235e-06,
+      "loss": 0.2622,
+      "step": 500
+    },
+    {
+      "epoch": 2.1872659176029963,
+      "grad_norm": 0.21302680671215057,
+      "learning_rate": 3.5958182470037127e-06,
+      "loss": 0.2591,
+      "step": 510
+    },
+    {
+      "epoch": 2.2300695559122525,
+      "grad_norm": 0.2146826982498169,
+      "learning_rate": 3.246945311723564e-06,
+      "loss": 0.257,
+      "step": 520
+    },
+    {
+      "epoch": 2.272873194221509,
+      "grad_norm": 0.1997881382703781,
+      "learning_rate": 2.912568868404284e-06,
+      "loss": 0.2579,
+      "step": 530
+    },
+    {
+      "epoch": 2.315676832530765,
+      "grad_norm": 0.18942134082317352,
+      "learning_rate": 2.5934067085707835e-06,
+      "loss": 0.2574,
+      "step": 540
+    },
+    {
+      "epoch": 2.3584804708400213,
+      "grad_norm": 0.22524645924568176,
+      "learning_rate": 2.290143963900181e-06,
+      "loss": 0.272,
+      "step": 550
+    },
+    {
+      "epoch": 2.4012841091492776,
+      "grad_norm": 0.19060121476650238,
+      "learning_rate": 2.0034316354791062e-06,
+      "loss": 0.2628,
+      "step": 560
+    },
+    {
+      "epoch": 2.444087747458534,
+      "grad_norm": 0.20566746592521667,
+      "learning_rate": 1.7338851963276827e-06,
+      "loss": 0.2528,
+      "step": 570
+    },
+    {
+      "epoch": 2.48689138576779,
+      "grad_norm": 0.22465558350086212,
+      "learning_rate": 1.4820832701900666e-06,
+      "loss": 0.2602,
+      "step": 580
+    },
+    {
+      "epoch": 2.5296950240770464,
+      "grad_norm": 0.2300027757883072,
+      "learning_rate": 1.2485663894277611e-06,
+      "loss": 0.255,
+      "step": 590
+    },
+    {
+      "epoch": 2.5724986623863026,
+      "grad_norm": 0.2306976467370987,
+      "learning_rate": 1.0338358346820355e-06,
+      "loss": 0.2482,
+      "step": 600
+    },
+    {
+      "epoch": 2.615302300695559,
+      "grad_norm": 0.2312825620174408,
+      "learning_rate": 8.383525587963559e-07,
+      "loss": 0.265,
+      "step": 610
+    },
+    {
+      "epoch": 2.658105939004815,
+      "grad_norm": 0.23466035723686218,
+      "learning_rate": 6.625361973087363e-07,
+      "loss": 0.2572,
+      "step": 620
+    },
+    {
+      "epoch": 2.7009095773140714,
+      "grad_norm": 0.2148018777370453,
+      "learning_rate": 5.067641676381918e-07,
+      "loss": 0.2651,
+      "step": 630
+    },
+    {
+      "epoch": 2.7437132156233277,
+      "grad_norm": 0.22475391626358032,
+      "learning_rate": 3.713708588989895e-07,
+      "loss": 0.2627,
+      "step": 640
+    },
+    {
+      "epoch": 2.7865168539325844,
+      "grad_norm": 0.22721537947654724,
+      "learning_rate": 2.5664691408194164e-07,
+      "loss": 0.2586,
+      "step": 650
+    },
+    {
+      "epoch": 2.8293204922418407,
+      "grad_norm": 0.22882406413555145,
+      "learning_rate": 1.6283860614358936e-07,
+      "loss": 0.2749,
+      "step": 660
+    },
+    {
+      "epoch": 2.872124130551097,
+      "grad_norm": 0.22706882655620575,
+      "learning_rate": 9.014730934264193e-08,
+      "loss": 0.2626,
+      "step": 670
+    },
+    {
+      "epoch": 2.914927768860353,
+      "grad_norm": 0.2065451741218567,
+      "learning_rate": 3.872906695852607e-08,
+      "loss": 0.2603,
+      "step": 680
+    },
+    {
+      "epoch": 2.9577314071696095,
+      "grad_norm": 0.21813534200191498,
+      "learning_rate": 8.694256319987659e-09,
+      "loss": 0.261,
+      "step": 690
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 699,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.182775970882355e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

qwen/checkpoints/sft_gsm8k_seed1337/checkpoint-699/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54179a286cf5ae076fc2014a5b6985ef341a084d1872e7254af9e058b07c459
+size 5624

qwen/checkpoints/sft_gsm8k_seed1337/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
+  }
+}

qwen/checkpoints/sft_gsm8k_seed1337/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145191e3b102f64e84dab1926006ee71528c1ea536df048ef9ff6c48d01f95de
+size 11421995

qwen/checkpoints/sft_gsm8k_seed1337/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen/checkpoints/sft_gsm8k_seed1337/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54179a286cf5ae076fc2014a5b6985ef341a084d1872e7254af9e058b07c459
+size 5624