初始化项目，由ModelHub XC社区提供模型
Model: carestudd/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-screeching_endangered_chinchilla 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
|
||||||
73
README.md
Normal file
73
README.md
Normal file
@@ -0,0 +1,73 @@
|
|||||||
|
---
|
||||||
|
base_model: unsloth/Qwen2.5-0.5B-Instruct
|
||||||
|
library_name: transformers
|
||||||
|
model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-screeching_endangered_chinchilla
|
||||||
|
tags:
|
||||||
|
- generated_from_trainer
|
||||||
|
- rl-swarm
|
||||||
|
- grpo
|
||||||
|
- gensyn
|
||||||
|
- I am screeching endangered chinchilla
|
||||||
|
- trl
|
||||||
|
- genrl-swarm
|
||||||
|
- I am screeching_endangered_chinchilla
|
||||||
|
licence: license
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-screeching_endangered_chinchilla
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [unsloth/Qwen2.5-0.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct).
|
||||||
|
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="carestudd/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-screeching_endangered_chinchilla", device="cuda")
|
||||||
|
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||||
|
print(output["generated_text"])
|
||||||
|
```
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
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: 0.18.1
|
||||||
|
- Transformers: 4.52.4
|
||||||
|
- Pytorch: 2.7.1
|
||||||
|
- Datasets: 3.6.0
|
||||||
|
- Tokenizers: 0.21.1
|
||||||
|
|
||||||
|
## 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 Gallou{\'e}dec},
|
||||||
|
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": 0.05132548208348453,
|
||||||
|
"train_runtime": 571.6229,
|
||||||
|
"train_samples": 5,
|
||||||
|
"train_samples_per_second": 0.14,
|
||||||
|
"train_steps_per_second": 0.035
|
||||||
|
}
|
||||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- messages[0]['content'] }}
|
||||||
|
{%- else %}
|
||||||
|
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "\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>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\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" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{{- '<|im_start|>' + message.role }}
|
||||||
|
{%- if message.content %}
|
||||||
|
{{- '\n' + message.content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if tool_call.function is defined %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- message.content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- endif %}
|
||||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 896,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 4864,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 21,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 14,
|
||||||
|
"num_hidden_layers": 24,
|
||||||
|
"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": "float32",
|
||||||
|
"transformers_version": "4.51.3",
|
||||||
|
"use_cache": true,
|
||||||
|
"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": "4.51.3"
|
||||||
|
}
|
||||||
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 sha256:6be0befe0f492f994d7d7b594a235ee2853300747036cd8e53df7929067bf668
|
||||||
|
size 1976163472
|
||||||
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": "<|vision_pad|>",
|
||||||
|
"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 sha256:64e71213db910f5cafa86d35091f37393dcc344b1bbc34091d1b3eed4cca01d5
|
||||||
|
size 11422064
|
||||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
|||||||
|
{
|
||||||
|
"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,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 32768,
|
||||||
|
"pad_token": "<|vision_pad|>",
|
||||||
|
"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": 0.05132548208348453,
|
||||||
|
"train_runtime": 571.6229,
|
||||||
|
"train_samples": 5,
|
||||||
|
"train_samples_per_second": 0.14,
|
||||||
|
"train_steps_per_second": 0.035
|
||||||
|
}
|
||||||
603
trainer_state.json
Normal file
603
trainer_state.json
Normal file
@@ -0,0 +1,603 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 6.8,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 14,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 27.0,
|
||||||
|
"completions/max_terminated_length": 27.0,
|
||||||
|
"completions/mean_length": 23.5,
|
||||||
|
"completions/mean_terminated_length": 23.5,
|
||||||
|
"completions/min_length": 20.0,
|
||||||
|
"completions/min_terminated_length": 20.0,
|
||||||
|
"epoch": 0.4,
|
||||||
|
"frac_reward_zero_std": 0.0,
|
||||||
|
"grad_norm": 45.845420837402344,
|
||||||
|
"kl": 0.0,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": 0.0,
|
||||||
|
"num_tokens": 606.0,
|
||||||
|
"reward": 0.27725791931152344,
|
||||||
|
"reward_std": 0.0050897058099508286,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.184007927775383,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.007569987326860428,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.09325000643730164,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.10767660290002823,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 27.0,
|
||||||
|
"completions/max_terminated_length": 27.0,
|
||||||
|
"completions/mean_length": 24.0,
|
||||||
|
"completions/mean_terminated_length": 24.0,
|
||||||
|
"completions/min_length": 21.0,
|
||||||
|
"completions/min_terminated_length": 21.0,
|
||||||
|
"epoch": 0.8,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 9.568375587463379,
|
||||||
|
"kl": 0.0,
|
||||||
|
"learning_rate": 1e-06,
|
||||||
|
"loss": -0.0,
|
||||||
|
"num_tokens": 1214.0,
|
||||||
|
"reward": 0.05984270200133324,
|
||||||
|
"reward_std": 5.343298471416347e-05,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.05984270200133324,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.0004468102415557951,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"step": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 23.0,
|
||||||
|
"completions/max_terminated_length": 23.0,
|
||||||
|
"completions/mean_length": 21.5,
|
||||||
|
"completions/mean_terminated_length": 21.5,
|
||||||
|
"completions/min_length": 20.0,
|
||||||
|
"completions/min_terminated_length": 20.0,
|
||||||
|
"epoch": 1.4,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 39.694496154785156,
|
||||||
|
"kl": 0.1073869839310646,
|
||||||
|
"learning_rate": 9.931806517013612e-07,
|
||||||
|
"loss": 0.0043,
|
||||||
|
"num_tokens": 1812.0,
|
||||||
|
"reward": 0.20595212280750275,
|
||||||
|
"reward_std": 0.0009102191543206573,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.020702123641967773,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.003408734453842044,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.18525001406669617,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.002061557024717331,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 221.0,
|
||||||
|
"completions/max_terminated_length": 221.0,
|
||||||
|
"completions/mean_length": 82.25,
|
||||||
|
"completions/mean_terminated_length": 82.25,
|
||||||
|
"completions/min_length": 27.0,
|
||||||
|
"completions/min_terminated_length": 27.0,
|
||||||
|
"epoch": 1.8,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 16.176429748535156,
|
||||||
|
"kl": 0.020354424137622118,
|
||||||
|
"learning_rate": 9.729086208503173e-07,
|
||||||
|
"loss": 0.0798,
|
||||||
|
"num_tokens": 2653.0,
|
||||||
|
"reward": 0.04737311601638794,
|
||||||
|
"reward_std": 0.010779645293951035,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.04737311601638794,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.019436875358223915,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"step": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 45.0,
|
||||||
|
"completions/max_terminated_length": 45.0,
|
||||||
|
"completions/mean_length": 28.25,
|
||||||
|
"completions/mean_terminated_length": 28.25,
|
||||||
|
"completions/min_length": 20.0,
|
||||||
|
"completions/min_terminated_length": 20.0,
|
||||||
|
"epoch": 2.4,
|
||||||
|
"frac_reward_zero_std": 0.0,
|
||||||
|
"grad_norm": 44.07194900512695,
|
||||||
|
"kl": 0.08810030668973923,
|
||||||
|
"learning_rate": 9.397368756032444e-07,
|
||||||
|
"loss": 0.0939,
|
||||||
|
"num_tokens": 3278.0,
|
||||||
|
"reward": 0.050381630659103394,
|
||||||
|
"reward_std": 0.006566238589584827,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.0503816232085228,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.007008333690464497,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 27.0,
|
||||||
|
"completions/max_terminated_length": 27.0,
|
||||||
|
"completions/mean_length": 25.0,
|
||||||
|
"completions/mean_terminated_length": 25.0,
|
||||||
|
"completions/min_length": 23.0,
|
||||||
|
"completions/min_terminated_length": 23.0,
|
||||||
|
"epoch": 2.8,
|
||||||
|
"frac_reward_zero_std": 1.0,
|
||||||
|
"grad_norm": 1.3027467727661133,
|
||||||
|
"kl": 0.08069050312042236,
|
||||||
|
"learning_rate": 8.945702546981968e-07,
|
||||||
|
"loss": 0.0032,
|
||||||
|
"num_tokens": 3890.0,
|
||||||
|
"reward": 0.1409657597541809,
|
||||||
|
"reward_std": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.04946577176451683,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.012337522581219673,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.09149999916553497,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.10565510392189026,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 157.0,
|
||||||
|
"completions/max_terminated_length": 157.0,
|
||||||
|
"completions/mean_length": 67.0,
|
||||||
|
"completions/mean_terminated_length": 67.0,
|
||||||
|
"completions/min_length": 20.0,
|
||||||
|
"completions/min_terminated_length": 20.0,
|
||||||
|
"epoch": 3.4,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 18.420305252075195,
|
||||||
|
"kl": 0.03622829727828503,
|
||||||
|
"learning_rate": 8.386407858128706e-07,
|
||||||
|
"loss": -0.0354,
|
||||||
|
"num_tokens": 4670.0,
|
||||||
|
"reward": 0.044995490461587906,
|
||||||
|
"reward_std": 0.0019922610372304916,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.044995490461587906,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.014919609762728214,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"step": 7
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 146.0,
|
||||||
|
"completions/max_terminated_length": 146.0,
|
||||||
|
"completions/mean_length": 54.75,
|
||||||
|
"completions/mean_terminated_length": 54.75,
|
||||||
|
"completions/min_length": 23.0,
|
||||||
|
"completions/min_terminated_length": 23.0,
|
||||||
|
"epoch": 3.8,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 11.040939331054688,
|
||||||
|
"kl": 0.025315589271485806,
|
||||||
|
"learning_rate": 7.734740790612136e-07,
|
||||||
|
"loss": 0.243,
|
||||||
|
"num_tokens": 5401.0,
|
||||||
|
"reward": 0.27007412910461426,
|
||||||
|
"reward_std": 0.010380705818533897,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.1785741150379181,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.012178990058600903,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.09149999916553497,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.10565510392189026,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 20.0,
|
||||||
|
"completions/max_terminated_length": 20.0,
|
||||||
|
"completions/mean_length": 17.0,
|
||||||
|
"completions/mean_terminated_length": 17.0,
|
||||||
|
"completions/min_length": 14.0,
|
||||||
|
"completions/min_terminated_length": 14.0,
|
||||||
|
"epoch": 4.4,
|
||||||
|
"frac_reward_zero_std": 1.0,
|
||||||
|
"grad_norm": 0.005074405111372471,
|
||||||
|
"kl": 0.15366993844509125,
|
||||||
|
"learning_rate": 7.008477123264847e-07,
|
||||||
|
"loss": 0.0061,
|
||||||
|
"num_tokens": 5981.0,
|
||||||
|
"reward": 0.05733615159988403,
|
||||||
|
"reward_std": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.05733615159988403,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.0004914185265079141,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 389.0,
|
||||||
|
"completions/max_terminated_length": 389.0,
|
||||||
|
"completions/mean_length": 259.5,
|
||||||
|
"completions/mean_terminated_length": 259.5,
|
||||||
|
"completions/min_length": 166.0,
|
||||||
|
"completions/min_terminated_length": 166.0,
|
||||||
|
"epoch": 4.8,
|
||||||
|
"frac_reward_zero_std": 0.0,
|
||||||
|
"grad_norm": 12.459712028503418,
|
||||||
|
"kl": 0.029772183392196894,
|
||||||
|
"learning_rate": 6.227427435703995e-07,
|
||||||
|
"loss": 0.2349,
|
||||||
|
"num_tokens": 7531.0,
|
||||||
|
"reward": 0.11735042929649353,
|
||||||
|
"reward_std": 0.018421867862343788,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.11735042929649353,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.01842377707362175,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 23.0,
|
||||||
|
"completions/max_terminated_length": 23.0,
|
||||||
|
"completions/mean_length": 18.5,
|
||||||
|
"completions/mean_terminated_length": 18.5,
|
||||||
|
"completions/min_length": 14.0,
|
||||||
|
"completions/min_terminated_length": 14.0,
|
||||||
|
"epoch": 5.4,
|
||||||
|
"frac_reward_zero_std": 1.0,
|
||||||
|
"grad_norm": 0.039047498255968094,
|
||||||
|
"kl": 0.11775290966033936,
|
||||||
|
"learning_rate": 5.412896727361662e-07,
|
||||||
|
"loss": 0.0047,
|
||||||
|
"num_tokens": 8117.0,
|
||||||
|
"reward": 0.40121549367904663,
|
||||||
|
"reward_std": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.30971550941467285,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.044006314128637314,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.09149999916553497,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.10565510392189026,
|
||||||
|
"step": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 143.0,
|
||||||
|
"completions/max_terminated_length": 143.0,
|
||||||
|
"completions/mean_length": 61.75,
|
||||||
|
"completions/mean_terminated_length": 61.75,
|
||||||
|
"completions/min_length": 20.0,
|
||||||
|
"completions/min_terminated_length": 20.0,
|
||||||
|
"epoch": 5.8,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 24.296092987060547,
|
||||||
|
"kl": 0.0357817467302084,
|
||||||
|
"learning_rate": 4.5871032726383385e-07,
|
||||||
|
"loss": 0.0419,
|
||||||
|
"num_tokens": 8876.0,
|
||||||
|
"reward": 0.048355475068092346,
|
||||||
|
"reward_std": 0.007202191278338432,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.048355475068092346,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.020798446610569954,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"step": 12
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 149.0,
|
||||||
|
"completions/max_terminated_length": 149.0,
|
||||||
|
"completions/mean_length": 64.25,
|
||||||
|
"completions/mean_terminated_length": 64.25,
|
||||||
|
"completions/min_length": 14.0,
|
||||||
|
"completions/min_terminated_length": 14.0,
|
||||||
|
"epoch": 6.4,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 20.938844680786133,
|
||||||
|
"kl": 0.061262642964720726,
|
||||||
|
"learning_rate": 3.772572564296004e-07,
|
||||||
|
"loss": 0.0246,
|
||||||
|
"num_tokens": 9645.0,
|
||||||
|
"reward": 0.19921739399433136,
|
||||||
|
"reward_std": 0.01111482735723257,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.19921737909317017,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.08456551283597946,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"step": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"clip_ratio/high_max": 0.0,
|
||||||
|
"clip_ratio/high_mean": 0.0,
|
||||||
|
"clip_ratio/low_mean": 0.0,
|
||||||
|
"clip_ratio/low_min": 0.0,
|
||||||
|
"clip_ratio/region_mean": 0.0,
|
||||||
|
"completions/clipped_ratio": 0.0,
|
||||||
|
"completions/max_length": 23.0,
|
||||||
|
"completions/max_terminated_length": 23.0,
|
||||||
|
"completions/mean_length": 21.0,
|
||||||
|
"completions/mean_terminated_length": 21.0,
|
||||||
|
"completions/min_length": 20.0,
|
||||||
|
"completions/min_terminated_length": 20.0,
|
||||||
|
"epoch": 6.8,
|
||||||
|
"frac_reward_zero_std": 0.5,
|
||||||
|
"grad_norm": 12.05763053894043,
|
||||||
|
"kl": 0.054638177156448364,
|
||||||
|
"learning_rate": 2.9915228767351535e-07,
|
||||||
|
"loss": 0.0173,
|
||||||
|
"num_tokens": 10241.0,
|
||||||
|
"reward": 0.14335308969020844,
|
||||||
|
"reward_std": 0.0008261414477601647,
|
||||||
|
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/consensus_reward_func/mean": 0.0,
|
||||||
|
"rewards/consensus_reward_func/std": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/mean": 0.0,
|
||||||
|
"rewards/cumulative_reward_2/std": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/mean": 0.0,
|
||||||
|
"rewards/final_correctness_reward_func/std": 0.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.0513530895113945,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.007401337847113609,
|
||||||
|
"rewards/soft_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/soft_format_reward_func/std": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/mean": 0.0,
|
||||||
|
"rewards/strict_format_reward_func/std": 0.0,
|
||||||
|
"rewards/xmlcount_reward_func/mean": 0.09200000017881393,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.10623559355735779,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 6.8,
|
||||||
|
"step": 14,
|
||||||
|
"total_flos": 0.0,
|
||||||
|
"train_loss": 0.05132548208348453,
|
||||||
|
"train_runtime": 571.6229,
|
||||||
|
"train_samples_per_second": 0.14,
|
||||||
|
"train_steps_per_second": 0.035
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1,
|
||||||
|
"max_steps": 20,
|
||||||
|
"num_input_tokens_seen": 10241,
|
||||||
|
"num_train_epochs": 7,
|
||||||
|
"save_steps": 25,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": false,
|
||||||
|
"should_training_stop": false
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 0.0,
|
||||||
|
"train_batch_size": 2,
|
||||||
|
"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:a0c53f5838e2347a329e376a2f5a444e36cd04b4c0362d03d97065fd4a69afad
|
||||||
|
size 6865
|
||||||
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