初始化项目，由ModelHub XC社区提供模型
Model: WSX/Qwen2.5-1.5B-Open-R1-GRPO-FC Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz 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
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
69
README.md
Normal file
69
README.md
Normal file
@@ -0,0 +1,69 @@
|
|||||||
|
---
|
||||||
|
datasets: AI-MO/NuminaMath-TIR
|
||||||
|
library_name: transformers
|
||||||
|
model_name: Qwen2.5-1.5B-Open-R1-GRPO-FC
|
||||||
|
tags:
|
||||||
|
- generated_from_trainer
|
||||||
|
- open-r1
|
||||||
|
- trl
|
||||||
|
- grpo
|
||||||
|
licence: license
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for Qwen2.5-1.5B-Open-R1-GRPO-FC
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [None](https://huggingface.co/None) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) dataset.
|
||||||
|
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||||
|
|
||||||
|
## Quick start
|
||||||
|
|
||||||
|
```python
|
||||||
|
from transformers import pipeline
|
||||||
|
|
||||||
|
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||||
|
generator = pipeline("text-generation", model="WSX/Qwen2.5-1.5B-Open-R1-GRPO-FC", device="cuda")
|
||||||
|
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||||
|
print(output["generated_text"])
|
||||||
|
```
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/wsx/grpo/runs/qjognkqg)
|
||||||
|
|
||||||
|
|
||||||
|
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- TRL: 0.16.0.dev0
|
||||||
|
- Transformers: 4.50.0.dev0
|
||||||
|
- Pytorch: 2.5.1
|
||||||
|
- Datasets: 3.3.1
|
||||||
|
- Tokenizers: 0.21.0
|
||||||
|
|
||||||
|
## Citations
|
||||||
|
|
||||||
|
Cite GRPO as:
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@article{zhihong2024deepseekmath,
|
||||||
|
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
||||||
|
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
||||||
|
year = 2024,
|
||||||
|
eprint = {arXiv:2402.03300},
|
||||||
|
}
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
Cite TRL as:
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@misc{vonwerra2022trl,
|
||||||
|
title = {{TRL: Transformer Reinforcement Learning}},
|
||||||
|
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
||||||
|
year = 2020,
|
||||||
|
journal = {GitHub repository},
|
||||||
|
publisher = {GitHub},
|
||||||
|
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||||
|
}
|
||||||
|
```
|
||||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -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
|
||||||
|
}
|
||||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"total_flos": 0.0,
|
||||||
|
"train_loss": 1.7066374281421304,
|
||||||
|
"train_runtime": 5498.7014,
|
||||||
|
"train_samples": 11300,
|
||||||
|
"train_samples_per_second": 2.055,
|
||||||
|
"train_steps_per_second": 0.004
|
||||||
|
}
|
||||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8960,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 21,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 12,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": 32768,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.50.0.dev0",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"repetition_penalty": 1.1,
|
||||||
|
"temperature": 0.7,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.8,
|
||||||
|
"transformers_version": "4.50.0.dev0"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1bcd255cb1ca806cd9cadfd7372a9f6110863c4f9a540f360a130a113e285aab
|
||||||
|
size 3087467144
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -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
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
|
||||||
|
size 11422063
|
||||||
209
tokenizer_config.json
Normal file
209
tokenizer_config.json
Normal file
@@ -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": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"total_flos": 0.0,
|
||||||
|
"train_loss": 1.7066374281421304,
|
||||||
|
"train_runtime": 5498.7014,
|
||||||
|
"train_samples": 11300,
|
||||||
|
"train_samples_per_second": 2.055,
|
||||||
|
"train_steps_per_second": 0.004
|
||||||
|
}
|
||||||
328
trainer_state.json
Normal file
328
trainer_state.json
Normal file
@@ -0,0 +1,328 @@
|
|||||||
|
{
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.9943502824858758,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 22,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"completion_length": 276.02735233306885,
|
||||||
|
"epoch": 0.04519774011299435,
|
||||||
|
"grad_norm": 0.13002647486414434,
|
||||||
|
"kl": 0.0,
|
||||||
|
"learning_rate": 6.666666666666667e-06,
|
||||||
|
"loss": 0.0303,
|
||||||
|
"reward": 1.3704427555203438,
|
||||||
|
"reward_std": 0.1837239097803831,
|
||||||
|
"rewards/fc_accuracy_reward": 0.4309895895421505,
|
||||||
|
"rewards/format_reward": 0.9394531473517418,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 292.13477420806885,
|
||||||
|
"epoch": 0.0903954802259887,
|
||||||
|
"grad_norm": 0.14619501253296655,
|
||||||
|
"kl": 0.0,
|
||||||
|
"learning_rate": 1.3333333333333333e-05,
|
||||||
|
"loss": 0.0469,
|
||||||
|
"reward": 1.3990885764360428,
|
||||||
|
"reward_std": 0.21469345316290855,
|
||||||
|
"rewards/fc_accuracy_reward": 0.44856772013008595,
|
||||||
|
"rewards/format_reward": 0.9505208507180214,
|
||||||
|
"step": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 268.9563903808594,
|
||||||
|
"epoch": 0.13559322033898305,
|
||||||
|
"grad_norm": 0.13036409926543296,
|
||||||
|
"kl": 0.0002338886260986328,
|
||||||
|
"learning_rate": 2e-05,
|
||||||
|
"loss": 0.0319,
|
||||||
|
"reward": 1.3704427406191826,
|
||||||
|
"reward_std": 0.18289842084050179,
|
||||||
|
"rewards/fc_accuracy_reward": 0.41992188431322575,
|
||||||
|
"rewards/format_reward": 0.9505208656191826,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 237.50716876983643,
|
||||||
|
"epoch": 0.1807909604519774,
|
||||||
|
"grad_norm": 0.12085621262181591,
|
||||||
|
"kl": 0.00720977783203125,
|
||||||
|
"learning_rate": 1.9863613034027224e-05,
|
||||||
|
"loss": 0.0065,
|
||||||
|
"reward": 1.427734412252903,
|
||||||
|
"reward_std": 0.1744816219434142,
|
||||||
|
"rewards/fc_accuracy_reward": 0.46614584885537624,
|
||||||
|
"rewards/format_reward": 0.9615885503590107,
|
||||||
|
"step": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 198.7910213470459,
|
||||||
|
"epoch": 0.22598870056497175,
|
||||||
|
"grad_norm": 1.1449772190729142,
|
||||||
|
"kl": 0.0814666748046875,
|
||||||
|
"learning_rate": 1.9458172417006347e-05,
|
||||||
|
"loss": -0.007,
|
||||||
|
"reward": 1.2617187947034836,
|
||||||
|
"reward_std": 0.17365613672882318,
|
||||||
|
"rewards/fc_accuracy_reward": 0.3222656352445483,
|
||||||
|
"rewards/format_reward": 0.939453125,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 231.09896564483643,
|
||||||
|
"epoch": 0.2711864406779661,
|
||||||
|
"grad_norm": 0.1913660515760745,
|
||||||
|
"kl": 0.045501708984375,
|
||||||
|
"learning_rate": 1.879473751206489e-05,
|
||||||
|
"loss": 0.0077,
|
||||||
|
"reward": 1.3893229588866234,
|
||||||
|
"reward_std": 0.14095465373247862,
|
||||||
|
"rewards/fc_accuracy_reward": 0.43489584513008595,
|
||||||
|
"rewards/format_reward": 0.9544270932674408,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 247.44727039337158,
|
||||||
|
"epoch": 0.3163841807909605,
|
||||||
|
"grad_norm": 0.13567082283951828,
|
||||||
|
"kl": 0.045623779296875,
|
||||||
|
"learning_rate": 1.789140509396394e-05,
|
||||||
|
"loss": 0.0065,
|
||||||
|
"reward": 1.3470052555203438,
|
||||||
|
"reward_std": 0.14320992957800627,
|
||||||
|
"rewards/fc_accuracy_reward": 0.3938802182674408,
|
||||||
|
"rewards/format_reward": 0.9531250074505806,
|
||||||
|
"step": 7
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 269.38086795806885,
|
||||||
|
"epoch": 0.3615819209039548,
|
||||||
|
"grad_norm": 0.16971700336774798,
|
||||||
|
"kl": 0.060699462890625,
|
||||||
|
"learning_rate": 1.6772815716257414e-05,
|
||||||
|
"loss": 0.0085,
|
||||||
|
"reward": 1.3372396156191826,
|
||||||
|
"reward_std": 0.1406525035854429,
|
||||||
|
"rewards/fc_accuracy_reward": 0.39257813431322575,
|
||||||
|
"rewards/format_reward": 0.9446614682674408,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 295.05665016174316,
|
||||||
|
"epoch": 0.4067796610169492,
|
||||||
|
"grad_norm": 1.3287845887377334,
|
||||||
|
"kl": 0.070892333984375,
|
||||||
|
"learning_rate": 1.5469481581224274e-05,
|
||||||
|
"loss": 0.0192,
|
||||||
|
"reward": 1.4036458730697632,
|
||||||
|
"reward_std": 0.18207293096929789,
|
||||||
|
"rewards/fc_accuracy_reward": 0.43750000931322575,
|
||||||
|
"rewards/format_reward": 0.9661458507180214,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 307.4420690536499,
|
||||||
|
"epoch": 0.4519774011299435,
|
||||||
|
"grad_norm": 54738.02031388349,
|
||||||
|
"kl": 394.0651397705078,
|
||||||
|
"learning_rate": 1.4016954246529697e-05,
|
||||||
|
"loss": 37.1931,
|
||||||
|
"reward": 1.3352864980697632,
|
||||||
|
"reward_std": 0.2137870010919869,
|
||||||
|
"rewards/fc_accuracy_reward": 0.4199218861758709,
|
||||||
|
"rewards/format_reward": 0.915364608168602,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 314.0898551940918,
|
||||||
|
"epoch": 0.4971751412429379,
|
||||||
|
"grad_norm": 2.107091829265173,
|
||||||
|
"kl": 0.095855712890625,
|
||||||
|
"learning_rate": 1.2454854871407993e-05,
|
||||||
|
"loss": 0.0338,
|
||||||
|
"reward": 1.3177083730697632,
|
||||||
|
"reward_std": 0.2345268540084362,
|
||||||
|
"rewards/fc_accuracy_reward": 0.4108072966337204,
|
||||||
|
"rewards/format_reward": 0.9069010689854622,
|
||||||
|
"step": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 318.7447986602783,
|
||||||
|
"epoch": 0.5423728813559322,
|
||||||
|
"grad_norm": 0.20351280734446026,
|
||||||
|
"kl": 0.081268310546875,
|
||||||
|
"learning_rate": 1.0825793454723325e-05,
|
||||||
|
"loss": 0.0176,
|
||||||
|
"reward": 1.2675781697034836,
|
||||||
|
"reward_std": 0.3210527803748846,
|
||||||
|
"rewards/fc_accuracy_reward": 0.397135429084301,
|
||||||
|
"rewards/format_reward": 0.8704427294433117,
|
||||||
|
"step": 12
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 311.57813262939453,
|
||||||
|
"epoch": 0.5875706214689266,
|
||||||
|
"grad_norm": 0.1737011976596144,
|
||||||
|
"kl": 0.07958984375,
|
||||||
|
"learning_rate": 9.174206545276678e-06,
|
||||||
|
"loss": 0.0088,
|
||||||
|
"reward": 1.3684896156191826,
|
||||||
|
"reward_std": 0.23807168938219547,
|
||||||
|
"rewards/fc_accuracy_reward": 0.4479166828095913,
|
||||||
|
"rewards/format_reward": 0.9205729365348816,
|
||||||
|
"step": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 301.56706619262695,
|
||||||
|
"epoch": 0.632768361581921,
|
||||||
|
"grad_norm": 18.70037949885207,
|
||||||
|
"kl": 0.586456298828125,
|
||||||
|
"learning_rate": 7.545145128592009e-06,
|
||||||
|
"loss": 0.0599,
|
||||||
|
"reward": 1.3203125298023224,
|
||||||
|
"reward_std": 0.20432353112846613,
|
||||||
|
"rewards/fc_accuracy_reward": 0.40820313803851604,
|
||||||
|
"rewards/format_reward": 0.9121094010770321,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 289.6764450073242,
|
||||||
|
"epoch": 0.6779661016949152,
|
||||||
|
"grad_norm": 0.15577324164046125,
|
||||||
|
"kl": 0.077789306640625,
|
||||||
|
"learning_rate": 5.983045753470308e-06,
|
||||||
|
"loss": 0.011,
|
||||||
|
"reward": 1.3496094048023224,
|
||||||
|
"reward_std": 0.21356581384316087,
|
||||||
|
"rewards/fc_accuracy_reward": 0.4186198003590107,
|
||||||
|
"rewards/format_reward": 0.9309896044433117,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 286.3886785507202,
|
||||||
|
"epoch": 0.7231638418079096,
|
||||||
|
"grad_norm": 5.326707764035434,
|
||||||
|
"kl": 0.0885009765625,
|
||||||
|
"learning_rate": 4.530518418775734e-06,
|
||||||
|
"loss": 0.0102,
|
||||||
|
"reward": 1.3658854514360428,
|
||||||
|
"reward_std": 0.23490996472537518,
|
||||||
|
"rewards/fc_accuracy_reward": 0.44401043094694614,
|
||||||
|
"rewards/format_reward": 0.9218750260770321,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 272.7597780227661,
|
||||||
|
"epoch": 0.768361581920904,
|
||||||
|
"grad_norm": 0.33239438768575263,
|
||||||
|
"kl": 0.075653076171875,
|
||||||
|
"learning_rate": 3.2271842837425917e-06,
|
||||||
|
"loss": 0.0083,
|
||||||
|
"reward": 1.3222656697034836,
|
||||||
|
"reward_std": 0.23243350349366665,
|
||||||
|
"rewards/fc_accuracy_reward": 0.4173177182674408,
|
||||||
|
"rewards/format_reward": 0.9049479365348816,
|
||||||
|
"step": 17
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 267.5846462249756,
|
||||||
|
"epoch": 0.8135593220338984,
|
||||||
|
"grad_norm": 0.16069383676764726,
|
||||||
|
"kl": 0.07232666015625,
|
||||||
|
"learning_rate": 2.1085949060360654e-06,
|
||||||
|
"loss": 0.0114,
|
||||||
|
"reward": 1.3854166939854622,
|
||||||
|
"reward_std": 0.242501275613904,
|
||||||
|
"rewards/fc_accuracy_reward": 0.47070313803851604,
|
||||||
|
"rewards/format_reward": 0.9147135652601719,
|
||||||
|
"step": 18
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 266.1367254257202,
|
||||||
|
"epoch": 0.8587570621468926,
|
||||||
|
"grad_norm": 0.14326034602692705,
|
||||||
|
"kl": 0.0689239501953125,
|
||||||
|
"learning_rate": 1.2052624879351105e-06,
|
||||||
|
"loss": 0.0075,
|
||||||
|
"reward": 1.3854166939854622,
|
||||||
|
"reward_std": 0.20935742277652025,
|
||||||
|
"rewards/fc_accuracy_reward": 0.44531251676380634,
|
||||||
|
"rewards/format_reward": 0.940104179084301,
|
||||||
|
"step": 19
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 260.7949285507202,
|
||||||
|
"epoch": 0.903954802259887,
|
||||||
|
"grad_norm": 0.14485988944724762,
|
||||||
|
"kl": 0.06939697265625,
|
||||||
|
"learning_rate": 5.418275829936537e-07,
|
||||||
|
"loss": 0.0098,
|
||||||
|
"reward": 1.395182341337204,
|
||||||
|
"reward_std": 0.2115317303687334,
|
||||||
|
"rewards/fc_accuracy_reward": 0.47330730222165585,
|
||||||
|
"rewards/format_reward": 0.9218750260770321,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 262.3704528808594,
|
||||||
|
"epoch": 0.9491525423728814,
|
||||||
|
"grad_norm": 0.19459843380674965,
|
||||||
|
"kl": 0.0714874267578125,
|
||||||
|
"learning_rate": 1.3638696597277678e-07,
|
||||||
|
"loss": 0.0072,
|
||||||
|
"reward": 1.3489583656191826,
|
||||||
|
"reward_std": 0.20432352973148227,
|
||||||
|
"rewards/fc_accuracy_reward": 0.4348958469927311,
|
||||||
|
"rewards/format_reward": 0.9140625186264515,
|
||||||
|
"step": 21
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"completion_length": 263.5794382095337,
|
||||||
|
"epoch": 0.9943502824858758,
|
||||||
|
"grad_norm": 0.16933108100699076,
|
||||||
|
"kl": 0.067138671875,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": 0.0169,
|
||||||
|
"reward": 1.354817733168602,
|
||||||
|
"reward_std": 0.242501275613904,
|
||||||
|
"rewards/fc_accuracy_reward": 0.4348958469927311,
|
||||||
|
"rewards/format_reward": 0.9199219010770321,
|
||||||
|
"step": 22
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9943502824858758,
|
||||||
|
"step": 22,
|
||||||
|
"total_flos": 0.0,
|
||||||
|
"train_loss": 1.7066374281421304,
|
||||||
|
"train_runtime": 5498.7014,
|
||||||
|
"train_samples_per_second": 2.055,
|
||||||
|
"train_steps_per_second": 0.004
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1,
|
||||||
|
"max_steps": 22,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 1,
|
||||||
|
"save_steps": 10,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 0.0,
|
||||||
|
"train_batch_size": 32,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a5321114421b2eed9b96ef3b978003037c2ba2433aea83625f922a2166410c89
|
||||||
|
size 7736
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user