初始化项目，由ModelHub XC社区提供模型
Model: Ameb1/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-feline_stinky_walrus 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-feline_stinky_walrus
|
||||||
|
tags:
|
||||||
|
- generated_from_trainer
|
||||||
|
- rl-swarm
|
||||||
|
- grpo
|
||||||
|
- gensyn
|
||||||
|
- I am feline stinky walrus
|
||||||
|
- trl
|
||||||
|
- genrl-swarm
|
||||||
|
- I am feline_stinky_walrus
|
||||||
|
licence: license
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-feline_stinky_walrus
|
||||||
|
|
||||||
|
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="Ameb1/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-feline_stinky_walrus", 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: 0.17.0
|
||||||
|
- Transformers: 4.51.3
|
||||||
|
- Pytorch: 2.7.0
|
||||||
|
- Datasets: 3.5.1
|
||||||
|
- 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": 0.12070619501173496,
|
||||||
|
"train_runtime": 3637.1703,
|
||||||
|
"train_samples": 48,
|
||||||
|
"train_samples_per_second": 0.011,
|
||||||
|
"train_steps_per_second": 0.003
|
||||||
|
}
|
||||||
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:ed33122a2c41c8c20ebd0817095c83eb1443c89dc12fc54857ada3bf09329fb4
|
||||||
|
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
|
||||||
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": 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": 0.12070619501173496,
|
||||||
|
"train_runtime": 3637.1703,
|
||||||
|
"train_samples": 48,
|
||||||
|
"train_samples_per_second": 0.011,
|
||||||
|
"train_steps_per_second": 0.003
|
||||||
|
}
|
||||||
433
trainer_state.json
Normal file
433
trainer_state.json
Normal file
@@ -0,0 +1,433 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 10,
|
||||||
|
"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": 105.0,
|
||||||
|
"completions/max_terminated_length": 105.0,
|
||||||
|
"completions/mean_length": 79.25,
|
||||||
|
"completions/mean_terminated_length": 79.25,
|
||||||
|
"completions/min_length": 61.0,
|
||||||
|
"completions/min_terminated_length": 61.0,
|
||||||
|
"epoch": 0.041666666666666664,
|
||||||
|
"grad_norm": 19.425622940063477,
|
||||||
|
"kl": 0.0,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": -0.0238,
|
||||||
|
"num_tokens": 829.0,
|
||||||
|
"reward": 0.033818572759628296,
|
||||||
|
"reward_std": 0.014064152725040913,
|
||||||
|
"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": 0.033818572759628296,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.015592413954436779,
|
||||||
|
"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": 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": 157.0,
|
||||||
|
"completions/max_terminated_length": 157.0,
|
||||||
|
"completions/mean_length": 62.0,
|
||||||
|
"completions/mean_terminated_length": 62.0,
|
||||||
|
"completions/min_length": 11.0,
|
||||||
|
"completions/min_terminated_length": 11.0,
|
||||||
|
"epoch": 0.08333333333333333,
|
||||||
|
"grad_norm": 10.577459335327148,
|
||||||
|
"kl": 0.0,
|
||||||
|
"learning_rate": 1e-06,
|
||||||
|
"loss": 0.1346,
|
||||||
|
"num_tokens": 1589.0,
|
||||||
|
"reward": 0.02579352632164955,
|
||||||
|
"reward_std": 0.0022206564899533987,
|
||||||
|
"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": 0.03729352727532387,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.02176251821219921,
|
||||||
|
"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": -0.011500000022351742,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.023000000044703484,
|
||||||
|
"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": 60.0,
|
||||||
|
"completions/max_terminated_length": 60.0,
|
||||||
|
"completions/mean_length": 37.75,
|
||||||
|
"completions/mean_terminated_length": 37.75,
|
||||||
|
"completions/min_length": 17.0,
|
||||||
|
"completions/min_terminated_length": 17.0,
|
||||||
|
"epoch": 0.125,
|
||||||
|
"grad_norm": 63.17714309692383,
|
||||||
|
"kl": 0.022556406212970614,
|
||||||
|
"learning_rate": 9.698463103929541e-07,
|
||||||
|
"loss": -0.0353,
|
||||||
|
"num_tokens": 2252.0,
|
||||||
|
"reward": 0.0233759805560112,
|
||||||
|
"reward_std": 0.0036189700476825237,
|
||||||
|
"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": 0.02337597869336605,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.006528852041810751,
|
||||||
|
"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": 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": 49.0,
|
||||||
|
"completions/max_terminated_length": 49.0,
|
||||||
|
"completions/mean_length": 23.75,
|
||||||
|
"completions/mean_terminated_length": 23.75,
|
||||||
|
"completions/min_length": 6.0,
|
||||||
|
"completions/min_terminated_length": 6.0,
|
||||||
|
"epoch": 0.16666666666666666,
|
||||||
|
"grad_norm": 78.41133117675781,
|
||||||
|
"kl": 0.004607599810697138,
|
||||||
|
"learning_rate": 8.83022221559489e-07,
|
||||||
|
"loss": -0.0235,
|
||||||
|
"num_tokens": 2859.0,
|
||||||
|
"reward": 0.120003342628479,
|
||||||
|
"reward_std": 0.01657889410853386,
|
||||||
|
"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": 0.0575033500790596,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.04737204685807228,
|
||||||
|
"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": 0.0625,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.07216878235340118,
|
||||||
|
"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": 98.0,
|
||||||
|
"completions/max_terminated_length": 98.0,
|
||||||
|
"completions/mean_length": 62.25,
|
||||||
|
"completions/mean_terminated_length": 62.25,
|
||||||
|
"completions/min_length": 42.0,
|
||||||
|
"completions/min_terminated_length": 42.0,
|
||||||
|
"epoch": 0.20833333333333334,
|
||||||
|
"grad_norm": 27.737390518188477,
|
||||||
|
"kl": 0.0020544964354485273,
|
||||||
|
"learning_rate": 7.5e-07,
|
||||||
|
"loss": 0.1576,
|
||||||
|
"num_tokens": 3620.0,
|
||||||
|
"reward": 0.22436219453811646,
|
||||||
|
"reward_std": 0.2421010583639145,
|
||||||
|
"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": 0.042862214148044586,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.01811356097459793,
|
||||||
|
"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": 0.18150000274181366,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.2375619113445282,
|
||||||
|
"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": 66.0,
|
||||||
|
"completions/max_terminated_length": 66.0,
|
||||||
|
"completions/mean_length": 53.75,
|
||||||
|
"completions/mean_terminated_length": 53.75,
|
||||||
|
"completions/min_length": 38.0,
|
||||||
|
"completions/min_terminated_length": 38.0,
|
||||||
|
"epoch": 0.25,
|
||||||
|
"grad_norm": 30.05788230895996,
|
||||||
|
"kl": 0.11974160745739937,
|
||||||
|
"learning_rate": 5.868240888334652e-07,
|
||||||
|
"loss": -0.1373,
|
||||||
|
"num_tokens": 4347.0,
|
||||||
|
"reward": 0.06295251846313477,
|
||||||
|
"reward_std": 0.04794733226299286,
|
||||||
|
"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": 0.031702518463134766,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.010227867402136326,
|
||||||
|
"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": 0.03125,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0625,
|
||||||
|
"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": 0.25,
|
||||||
|
"completions/max_length": 448.0,
|
||||||
|
"completions/max_terminated_length": 435.0,
|
||||||
|
"completions/mean_length": 243.5,
|
||||||
|
"completions/mean_terminated_length": 175.3333282470703,
|
||||||
|
"completions/min_length": 17.0,
|
||||||
|
"completions/min_terminated_length": 17.0,
|
||||||
|
"epoch": 0.2916666666666667,
|
||||||
|
"grad_norm": 6.3190836906433105,
|
||||||
|
"kl": 0.013644359540194273,
|
||||||
|
"learning_rate": 4.131759111665348e-07,
|
||||||
|
"loss": 0.5802,
|
||||||
|
"num_tokens": 5833.0,
|
||||||
|
"reward": 0.1428598016500473,
|
||||||
|
"reward_std": 0.15640608966350555,
|
||||||
|
"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": 0.0803598091006279,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.06639377772808075,
|
||||||
|
"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": 0.0625,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.125,
|
||||||
|
"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": 72.0,
|
||||||
|
"completions/max_terminated_length": 72.0,
|
||||||
|
"completions/mean_length": 31.75,
|
||||||
|
"completions/mean_terminated_length": 31.75,
|
||||||
|
"completions/min_length": 6.0,
|
||||||
|
"completions/min_terminated_length": 6.0,
|
||||||
|
"epoch": 0.3333333333333333,
|
||||||
|
"grad_norm": 69.37403106689453,
|
||||||
|
"kl": 0.660507733002305,
|
||||||
|
"learning_rate": 2.500000000000001e-07,
|
||||||
|
"loss": -0.0009,
|
||||||
|
"num_tokens": 6472.0,
|
||||||
|
"reward": 0.08257974684238434,
|
||||||
|
"reward_std": 0.10520116984844208,
|
||||||
|
"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": 0.024079740047454834,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.0149986008182168,
|
||||||
|
"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": 0.05849999934434891,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.13300000131130219,
|
||||||
|
"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": 0.25,
|
||||||
|
"completions/max_length": 448.0,
|
||||||
|
"completions/max_terminated_length": 345.0,
|
||||||
|
"completions/mean_length": 230.5,
|
||||||
|
"completions/mean_terminated_length": 158.0,
|
||||||
|
"completions/min_length": 56.0,
|
||||||
|
"completions/min_terminated_length": 56.0,
|
||||||
|
"epoch": 0.375,
|
||||||
|
"grad_norm": 8.065352439880371,
|
||||||
|
"kl": 0.008895490551367402,
|
||||||
|
"learning_rate": 1.1697777844051104e-07,
|
||||||
|
"loss": 0.5052,
|
||||||
|
"num_tokens": 7906.0,
|
||||||
|
"reward": -0.4270660877227783,
|
||||||
|
"reward_std": 0.9292497038841248,
|
||||||
|
"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": 0.16618388891220093,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.13774648308753967,
|
||||||
|
"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": -0.5932499766349792,
|
||||||
|
"rewards/xmlcount_reward_func/std": 1.2711997032165527,
|
||||||
|
"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": 84.0,
|
||||||
|
"completions/max_terminated_length": 84.0,
|
||||||
|
"completions/mean_length": 37.0,
|
||||||
|
"completions/mean_terminated_length": 37.0,
|
||||||
|
"completions/min_length": 5.0,
|
||||||
|
"completions/min_terminated_length": 5.0,
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"grad_norm": 71.09834289550781,
|
||||||
|
"kl": 0.057335725985467434,
|
||||||
|
"learning_rate": 3.015368960704584e-08,
|
||||||
|
"loss": 0.0504,
|
||||||
|
"num_tokens": 8566.0,
|
||||||
|
"reward": 0.14473699033260345,
|
||||||
|
"reward_std": 0.09234187006950378,
|
||||||
|
"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": 0.019736986607313156,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.008162936195731163,
|
||||||
|
"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": 0.125,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.10206207633018494,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4166666666666667,
|
||||||
|
"step": 10,
|
||||||
|
"total_flos": 0.0,
|
||||||
|
"train_loss": 0.12070619501173496,
|
||||||
|
"train_runtime": 3637.1703,
|
||||||
|
"train_samples_per_second": 0.011,
|
||||||
|
"train_steps_per_second": 0.003
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1,
|
||||||
|
"max_steps": 10,
|
||||||
|
"num_input_tokens_seen": 8566,
|
||||||
|
"num_train_epochs": 1,
|
||||||
|
"save_steps": 25,
|
||||||
|
"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": 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 sha256:887a6599ee3f74f05f3b66a4203115da7c4131b4434b54c253e23e2245015bf3
|
||||||
|
size 6929
|
||||||
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