初始化项目，由ModelHub XC社区提供模型
Model: seeib/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prehistoric_gregarious_seahorse 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-prehistoric_gregarious_seahorse
|
||||||
|
tags:
|
||||||
|
- generated_from_trainer
|
||||||
|
- rl-swarm
|
||||||
|
- grpo
|
||||||
|
- gensyn
|
||||||
|
- I am prehistoric gregarious seahorse
|
||||||
|
- trl
|
||||||
|
- genrl-swarm
|
||||||
|
- I am prehistoric_gregarious_seahorse
|
||||||
|
licence: license
|
||||||
|
---
|
||||||
|
|
||||||
|
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prehistoric_gregarious_seahorse
|
||||||
|
|
||||||
|
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="seeib/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prehistoric_gregarious_seahorse", 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": -0.04282761747017503,
|
||||||
|
"train_runtime": 6256.5978,
|
||||||
|
"train_samples": 18,
|
||||||
|
"train_samples_per_second": 0.013,
|
||||||
|
"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:ff208332ee07c8e0538cc753e9b4a0ee6c42b191f878aa21bae2e667fa9c725b
|
||||||
|
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": -0.04282761747017503,
|
||||||
|
"train_runtime": 6256.5978,
|
||||||
|
"train_samples": 18,
|
||||||
|
"train_samples_per_second": 0.013,
|
||||||
|
"train_steps_per_second": 0.003
|
||||||
|
}
|
||||||
823
trainer_state.json
Normal file
823
trainer_state.json
Normal file
@@ -0,0 +1,823 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 2.2222222222222223,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 20,
|
||||||
|
"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": 63.0,
|
||||||
|
"completions/max_terminated_length": 63.0,
|
||||||
|
"completions/mean_length": 40.75,
|
||||||
|
"completions/mean_terminated_length": 40.75,
|
||||||
|
"completions/min_length": 31.0,
|
||||||
|
"completions/min_terminated_length": 31.0,
|
||||||
|
"epoch": 0.1111111111111111,
|
||||||
|
"grad_norm": 25.69437599182129,
|
||||||
|
"kl": 0.0,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"loss": -0.1171,
|
||||||
|
"num_tokens": 675.0,
|
||||||
|
"reward": 0.5159521698951721,
|
||||||
|
"reward_std": 0.0688270628452301,
|
||||||
|
"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": 0.07845214009284973,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.04025953263044357,
|
||||||
|
"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": 0.4375,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.125,
|
||||||
|
"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": 104.0,
|
||||||
|
"completions/max_terminated_length": 104.0,
|
||||||
|
"completions/mean_length": 56.5,
|
||||||
|
"completions/mean_terminated_length": 56.5,
|
||||||
|
"completions/min_length": 24.0,
|
||||||
|
"completions/min_terminated_length": 24.0,
|
||||||
|
"epoch": 0.2222222222222222,
|
||||||
|
"grad_norm": 22.427824020385742,
|
||||||
|
"kl": 0.0,
|
||||||
|
"learning_rate": 1e-06,
|
||||||
|
"loss": 0.0564,
|
||||||
|
"num_tokens": 1413.0,
|
||||||
|
"reward": 0.5325700640678406,
|
||||||
|
"reward_std": 0.0006790067418478429,
|
||||||
|
"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": 0.032570019364356995,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.0007998892688192427,
|
||||||
|
"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": 0.5,
|
||||||
|
"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": 231.0,
|
||||||
|
"completions/max_terminated_length": 231.0,
|
||||||
|
"completions/mean_length": 129.5,
|
||||||
|
"completions/mean_terminated_length": 129.5,
|
||||||
|
"completions/min_length": 59.0,
|
||||||
|
"completions/min_terminated_length": 59.0,
|
||||||
|
"epoch": 0.3333333333333333,
|
||||||
|
"grad_norm": 18.40679168701172,
|
||||||
|
"kl": 0.002804491203278303,
|
||||||
|
"learning_rate": 9.931806517013612e-07,
|
||||||
|
"loss": 0.297,
|
||||||
|
"num_tokens": 2443.0,
|
||||||
|
"reward": 0.6747503876686096,
|
||||||
|
"reward_std": 0.1533203423023224,
|
||||||
|
"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": 0.20650038123130798,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.019515778869390488,
|
||||||
|
"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": 0.46825000643730164,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.21338286995887756,
|
||||||
|
"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": 110.0,
|
||||||
|
"completions/max_terminated_length": 110.0,
|
||||||
|
"completions/mean_length": 62.25,
|
||||||
|
"completions/mean_terminated_length": 62.25,
|
||||||
|
"completions/min_length": 23.0,
|
||||||
|
"completions/min_terminated_length": 23.0,
|
||||||
|
"epoch": 0.4444444444444444,
|
||||||
|
"grad_norm": 22.179134368896484,
|
||||||
|
"kl": 0.012003686744719744,
|
||||||
|
"learning_rate": 9.729086208503173e-07,
|
||||||
|
"loss": -0.0112,
|
||||||
|
"num_tokens": 3204.0,
|
||||||
|
"reward": 0.6682786345481873,
|
||||||
|
"reward_std": 0.016284530982375145,
|
||||||
|
"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": 0.04327860474586487,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.0372861810028553,
|
||||||
|
"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": 0.625,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.14433756470680237,
|
||||||
|
"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": 79.0,
|
||||||
|
"completions/max_terminated_length": 79.0,
|
||||||
|
"completions/mean_length": 54.75,
|
||||||
|
"completions/mean_terminated_length": 54.75,
|
||||||
|
"completions/min_length": 26.0,
|
||||||
|
"completions/min_terminated_length": 26.0,
|
||||||
|
"epoch": 0.5555555555555556,
|
||||||
|
"grad_norm": 19.958255767822266,
|
||||||
|
"kl": 0.011007877299562097,
|
||||||
|
"learning_rate": 9.397368756032444e-07,
|
||||||
|
"loss": -0.1713,
|
||||||
|
"num_tokens": 3935.0,
|
||||||
|
"reward": 0.8996135592460632,
|
||||||
|
"reward_std": 0.049514204263687134,
|
||||||
|
"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": 0.27461355924606323,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.044617120176553726,
|
||||||
|
"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": 0.625,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.14433756470680237,
|
||||||
|
"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": 29.0,
|
||||||
|
"completions/max_terminated_length": 29.0,
|
||||||
|
"completions/mean_length": 27.25,
|
||||||
|
"completions/mean_terminated_length": 27.25,
|
||||||
|
"completions/min_length": 24.0,
|
||||||
|
"completions/min_terminated_length": 24.0,
|
||||||
|
"epoch": 0.6666666666666666,
|
||||||
|
"grad_norm": 23.830913543701172,
|
||||||
|
"kl": 0.04720709100365639,
|
||||||
|
"learning_rate": 8.945702546981968e-07,
|
||||||
|
"loss": -0.0311,
|
||||||
|
"num_tokens": 4556.0,
|
||||||
|
"reward": 0.5360786318778992,
|
||||||
|
"reward_std": 0.008525591343641281,
|
||||||
|
"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": 0.03607860952615738,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.02430449239909649,
|
||||||
|
"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": 0.5,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"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": 56.0,
|
||||||
|
"completions/max_terminated_length": 56.0,
|
||||||
|
"completions/mean_length": 40.5,
|
||||||
|
"completions/mean_terminated_length": 40.5,
|
||||||
|
"completions/min_length": 30.0,
|
||||||
|
"completions/min_terminated_length": 30.0,
|
||||||
|
"epoch": 0.7777777777777778,
|
||||||
|
"grad_norm": 39.75885772705078,
|
||||||
|
"kl": 0.056546732783317566,
|
||||||
|
"learning_rate": 8.386407858128706e-07,
|
||||||
|
"loss": -0.07,
|
||||||
|
"num_tokens": 5230.0,
|
||||||
|
"reward": 0.6005383729934692,
|
||||||
|
"reward_std": 0.08559251576662064,
|
||||||
|
"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": 0.03853834420442581,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.007710414472967386,
|
||||||
|
"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": 0.562000036239624,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.12400001287460327,
|
||||||
|
"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": 95.0,
|
||||||
|
"completions/max_terminated_length": 95.0,
|
||||||
|
"completions/mean_length": 61.25,
|
||||||
|
"completions/mean_terminated_length": 61.25,
|
||||||
|
"completions/min_length": 30.0,
|
||||||
|
"completions/min_terminated_length": 30.0,
|
||||||
|
"epoch": 0.8888888888888888,
|
||||||
|
"grad_norm": 25.805145263671875,
|
||||||
|
"kl": 0.07301068678498268,
|
||||||
|
"learning_rate": 7.734740790612136e-07,
|
||||||
|
"loss": -0.3117,
|
||||||
|
"num_tokens": 5987.0,
|
||||||
|
"reward": 0.7229201197624207,
|
||||||
|
"reward_std": 0.0429324246942997,
|
||||||
|
"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": 0.22292014956474304,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.05922666937112808,
|
||||||
|
"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": 0.5,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"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": 47.0,
|
||||||
|
"completions/max_terminated_length": 47.0,
|
||||||
|
"completions/mean_length": 35.5,
|
||||||
|
"completions/mean_terminated_length": 35.5,
|
||||||
|
"completions/min_length": 24.0,
|
||||||
|
"completions/min_terminated_length": 24.0,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"grad_norm": 30.85164451599121,
|
||||||
|
"kl": 0.02306750975549221,
|
||||||
|
"learning_rate": 7.008477123264847e-07,
|
||||||
|
"loss": 0.0617,
|
||||||
|
"num_tokens": 6634.0,
|
||||||
|
"reward": 0.5571061372756958,
|
||||||
|
"reward_std": 0.00527472048997879,
|
||||||
|
"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": 0.0571061372756958,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.011652503162622452,
|
||||||
|
"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": 0.5,
|
||||||
|
"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": 99.0,
|
||||||
|
"completions/max_terminated_length": 99.0,
|
||||||
|
"completions/mean_length": 59.5,
|
||||||
|
"completions/mean_terminated_length": 59.5,
|
||||||
|
"completions/min_length": 31.0,
|
||||||
|
"completions/min_terminated_length": 31.0,
|
||||||
|
"epoch": 1.1111111111111112,
|
||||||
|
"grad_norm": 18.589075088500977,
|
||||||
|
"kl": 0.057917265221476555,
|
||||||
|
"learning_rate": 6.227427435703995e-07,
|
||||||
|
"loss": -0.2448,
|
||||||
|
"num_tokens": 7384.0,
|
||||||
|
"reward": 0.7360702753067017,
|
||||||
|
"reward_std": 0.04403897002339363,
|
||||||
|
"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": 0.23607021570205688,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.07128877192735672,
|
||||||
|
"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": 0.5,
|
||||||
|
"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": 31.0,
|
||||||
|
"completions/max_terminated_length": 31.0,
|
||||||
|
"completions/mean_length": 28.0,
|
||||||
|
"completions/mean_terminated_length": 28.0,
|
||||||
|
"completions/min_length": 25.0,
|
||||||
|
"completions/min_terminated_length": 25.0,
|
||||||
|
"epoch": 1.2222222222222223,
|
||||||
|
"grad_norm": 34.077091217041016,
|
||||||
|
"kl": 0.13308210298419,
|
||||||
|
"learning_rate": 5.412896727361662e-07,
|
||||||
|
"loss": 0.0104,
|
||||||
|
"num_tokens": 8008.0,
|
||||||
|
"reward": 0.53204345703125,
|
||||||
|
"reward_std": 0.0063663022592663765,
|
||||||
|
"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": 0.032043468207120895,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.016084665432572365,
|
||||||
|
"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": 0.5,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"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": 69.0,
|
||||||
|
"completions/max_terminated_length": 69.0,
|
||||||
|
"completions/mean_length": 39.5,
|
||||||
|
"completions/mean_terminated_length": 39.5,
|
||||||
|
"completions/min_length": 22.0,
|
||||||
|
"completions/min_terminated_length": 22.0,
|
||||||
|
"epoch": 1.3333333333333333,
|
||||||
|
"grad_norm": 19.56139373779297,
|
||||||
|
"kl": 0.09075122326612473,
|
||||||
|
"learning_rate": 4.5871032726383385e-07,
|
||||||
|
"loss": -0.2792,
|
||||||
|
"num_tokens": 8678.0,
|
||||||
|
"reward": 0.5326830744743347,
|
||||||
|
"reward_std": 0.011520188301801682,
|
||||||
|
"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": 0.032683055847883224,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.009901088662445545,
|
||||||
|
"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": 0.5,
|
||||||
|
"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": 89.0,
|
||||||
|
"completions/max_terminated_length": 89.0,
|
||||||
|
"completions/mean_length": 79.5,
|
||||||
|
"completions/mean_terminated_length": 79.5,
|
||||||
|
"completions/min_length": 70.0,
|
||||||
|
"completions/min_terminated_length": 70.0,
|
||||||
|
"epoch": 1.4444444444444444,
|
||||||
|
"grad_norm": 26.145700454711914,
|
||||||
|
"kl": 0.027578551787883043,
|
||||||
|
"learning_rate": 3.772572564296004e-07,
|
||||||
|
"loss": -0.0213,
|
||||||
|
"num_tokens": 9508.0,
|
||||||
|
"reward": 0.8646507263183594,
|
||||||
|
"reward_std": 0.08279794454574585,
|
||||||
|
"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": 0.1771506667137146,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.056235793977975845,
|
||||||
|
"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": 0.6875,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.125,
|
||||||
|
"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": 127.0,
|
||||||
|
"completions/max_terminated_length": 127.0,
|
||||||
|
"completions/mean_length": 92.75,
|
||||||
|
"completions/mean_terminated_length": 92.75,
|
||||||
|
"completions/min_length": 68.0,
|
||||||
|
"completions/min_terminated_length": 68.0,
|
||||||
|
"epoch": 1.5555555555555556,
|
||||||
|
"grad_norm": 19.497051239013672,
|
||||||
|
"kl": 0.03215572563931346,
|
||||||
|
"learning_rate": 2.9915228767351535e-07,
|
||||||
|
"loss": -0.084,
|
||||||
|
"num_tokens": 10391.0,
|
||||||
|
"reward": 0.6083483099937439,
|
||||||
|
"reward_std": 0.10050921142101288,
|
||||||
|
"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": 0.04584832862019539,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.010448978282511234,
|
||||||
|
"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": 0.5625,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.125,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"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": 47.0,
|
||||||
|
"completions/mean_length": 138.75,
|
||||||
|
"completions/mean_terminated_length": 35.66666793823242,
|
||||||
|
"completions/min_length": 30.0,
|
||||||
|
"completions/min_terminated_length": 30.0,
|
||||||
|
"epoch": 1.6666666666666665,
|
||||||
|
"grad_norm": 14.958171844482422,
|
||||||
|
"kl": 0.036621191538870335,
|
||||||
|
"learning_rate": 2.2652592093878665e-07,
|
||||||
|
"loss": 0.2878,
|
||||||
|
"num_tokens": 11458.0,
|
||||||
|
"reward": 0.45188108086586,
|
||||||
|
"reward_std": 0.15637479722499847,
|
||||||
|
"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": 0.04563111066818237,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.020204132422804832,
|
||||||
|
"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": 0.40625,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.1875,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"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": 55.0,
|
||||||
|
"completions/max_terminated_length": 55.0,
|
||||||
|
"completions/mean_length": 37.25,
|
||||||
|
"completions/mean_terminated_length": 37.25,
|
||||||
|
"completions/min_length": 29.0,
|
||||||
|
"completions/min_terminated_length": 29.0,
|
||||||
|
"epoch": 1.7777777777777777,
|
||||||
|
"grad_norm": 27.896305084228516,
|
||||||
|
"kl": 0.17185895144939423,
|
||||||
|
"learning_rate": 1.6135921418712955e-07,
|
||||||
|
"loss": -0.064,
|
||||||
|
"num_tokens": 12119.0,
|
||||||
|
"reward": 0.4707985520362854,
|
||||||
|
"reward_std": 0.27111726999282837,
|
||||||
|
"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": 0.03329858183860779,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.012222301214933395,
|
||||||
|
"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": 0.4375,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.23935678601264954,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"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": 96.0,
|
||||||
|
"completions/max_terminated_length": 96.0,
|
||||||
|
"completions/mean_length": 68.5,
|
||||||
|
"completions/mean_terminated_length": 68.5,
|
||||||
|
"completions/min_length": 27.0,
|
||||||
|
"completions/min_terminated_length": 27.0,
|
||||||
|
"epoch": 1.8888888888888888,
|
||||||
|
"grad_norm": 17.811830520629883,
|
||||||
|
"kl": 0.056419532746076584,
|
||||||
|
"learning_rate": 1.0542974530180327e-07,
|
||||||
|
"loss": -0.2264,
|
||||||
|
"num_tokens": 12905.0,
|
||||||
|
"reward": 1.2158468961715698,
|
||||||
|
"reward_std": 0.8011028170585632,
|
||||||
|
"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": 0.5,
|
||||||
|
"rewards/final_correctness_reward_func/std": 1.0,
|
||||||
|
"rewards/question_recreation_reward_func/mean": 0.02884695678949356,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.008567274548113346,
|
||||||
|
"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": 0.687000036239624,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.12467022985219955,
|
||||||
|
"step": 17
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"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": 59.0,
|
||||||
|
"completions/max_terminated_length": 59.0,
|
||||||
|
"completions/mean_length": 56.5,
|
||||||
|
"completions/mean_terminated_length": 56.5,
|
||||||
|
"completions/min_length": 54.0,
|
||||||
|
"completions/min_terminated_length": 54.0,
|
||||||
|
"epoch": 2.0,
|
||||||
|
"grad_norm": 24.79212188720703,
|
||||||
|
"kl": 0.0544373020529747,
|
||||||
|
"learning_rate": 6.026312439675551e-08,
|
||||||
|
"loss": 0.0433,
|
||||||
|
"num_tokens": 13653.0,
|
||||||
|
"reward": 0.6995986700057983,
|
||||||
|
"reward_std": 0.012008922174572945,
|
||||||
|
"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": 0.07459867000579834,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.05076611042022705,
|
||||||
|
"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": 0.625,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.14433756470680237,
|
||||||
|
"step": 18
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"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": 79.0,
|
||||||
|
"completions/max_terminated_length": 79.0,
|
||||||
|
"completions/mean_length": 65.5,
|
||||||
|
"completions/mean_terminated_length": 65.5,
|
||||||
|
"completions/min_length": 55.0,
|
||||||
|
"completions/min_terminated_length": 55.0,
|
||||||
|
"epoch": 2.111111111111111,
|
||||||
|
"grad_norm": 23.983592987060547,
|
||||||
|
"kl": 0.030249727424234152,
|
||||||
|
"learning_rate": 2.7091379149682682e-08,
|
||||||
|
"loss": 0.07,
|
||||||
|
"num_tokens": 14427.0,
|
||||||
|
"reward": 0.9142850637435913,
|
||||||
|
"reward_std": 0.027192028239369392,
|
||||||
|
"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": 0.2892850637435913,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.027173683047294617,
|
||||||
|
"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": 0.625,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.14433756470680237,
|
||||||
|
"step": 19
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"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": 85.0,
|
||||||
|
"completions/max_terminated_length": 85.0,
|
||||||
|
"completions/mean_length": 56.25,
|
||||||
|
"completions/mean_terminated_length": 56.25,
|
||||||
|
"completions/min_length": 33.0,
|
||||||
|
"completions/min_terminated_length": 33.0,
|
||||||
|
"epoch": 2.2222222222222223,
|
||||||
|
"grad_norm": 19.803834915161133,
|
||||||
|
"kl": 0.08400401845574379,
|
||||||
|
"learning_rate": 6.819348298638839e-09,
|
||||||
|
"loss": -0.051,
|
||||||
|
"num_tokens": 15164.0,
|
||||||
|
"reward": 0.762055516242981,
|
||||||
|
"reward_std": 0.058255478739738464,
|
||||||
|
"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": 0.26205551624298096,
|
||||||
|
"rewards/question_recreation_reward_func/std": 0.15907590091228485,
|
||||||
|
"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": 0.5,
|
||||||
|
"rewards/xmlcount_reward_func/std": 0.0,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.2222222222222223,
|
||||||
|
"step": 20,
|
||||||
|
"total_flos": 0.0,
|
||||||
|
"train_loss": -0.04282761747017503,
|
||||||
|
"train_runtime": 6256.5978,
|
||||||
|
"train_samples_per_second": 0.013,
|
||||||
|
"train_steps_per_second": 0.003
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 1,
|
||||||
|
"max_steps": 20,
|
||||||
|
"num_input_tokens_seen": 15164,
|
||||||
|
"num_train_epochs": 3,
|
||||||
|
"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 sha256:666635f1d5fe5ecca75e5901f70bd6f1f792846f92f6a70e495011d54e5471d4
|
||||||
|
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