初始化项目，由ModelHub XC社区提供模型
Model: Azur-abcd/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-aquatic_mute_jaguar 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-aquatic_mute_jaguar
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- rl-swarm
|
||||
- grpo
|
||||
- gensyn
|
||||
- I am aquatic mute jaguar
|
||||
- trl
|
||||
- genrl-swarm
|
||||
- I am aquatic_mute_jaguar
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-aquatic_mute_jaguar
|
||||
|
||||
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="Azur-abcd/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-aquatic_mute_jaguar", 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: 3.6.0
|
||||
- Tokenizers: 0.21.1
|
||||
|
||||
## Citations
|
||||
|
||||
Cite GRPO as:
|
||||
|
||||
```bibtex
|
||||
@article{zhihong2024deepseekmath,
|
||||
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
||||
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
||||
year = 2024,
|
||||
eprint = {arXiv:2402.03300},
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@misc{vonwerra2022trl,
|
||||
title = {{TRL: Transformer Reinforcement Learning}},
|
||||
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
||||
year = 2020,
|
||||
journal = {GitHub repository},
|
||||
publisher = {GitHub},
|
||||
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||
}
|
||||
```
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.0696285206824541,
|
||||
"train_runtime": 6061.8527,
|
||||
"train_samples": 52,
|
||||
"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:ecf9afef079b9d97555976ca9f4c9365b8b1987721d0730c2116706be8f7010a
|
||||
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": 0.0696285206824541,
|
||||
"train_runtime": 6061.8527,
|
||||
"train_samples": 52,
|
||||
"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": 0.7692307692307693,
|
||||
"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": 0.25,
|
||||
"completions/max_length": 448.0,
|
||||
"completions/max_terminated_length": 190.0,
|
||||
"completions/mean_length": 218.0,
|
||||
"completions/mean_terminated_length": 141.3333282470703,
|
||||
"completions/min_length": 91.0,
|
||||
"completions/min_terminated_length": 91.0,
|
||||
"epoch": 0.038461538461538464,
|
||||
"grad_norm": 9.404427528381348,
|
||||
"kl": 0.0,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 0.2213,
|
||||
"num_tokens": 1384.0,
|
||||
"reward": 0.27538180351257324,
|
||||
"reward_std": 0.5752406120300293,
|
||||
"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": 0.3473817706108093,
|
||||
"rewards/question_recreation_reward_func/std": 0.03370636701583862,
|
||||
"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": -0.07199999690055847,
|
||||
"rewards/xmlcount_reward_func/std": 0.9370037317276001,
|
||||
"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": 297.0,
|
||||
"completions/max_terminated_length": 297.0,
|
||||
"completions/mean_length": 123.75,
|
||||
"completions/mean_terminated_length": 123.75,
|
||||
"completions/min_length": 39.0,
|
||||
"completions/min_terminated_length": 39.0,
|
||||
"epoch": 0.07692307692307693,
|
||||
"grad_norm": 13.685848236083984,
|
||||
"kl": 0.0,
|
||||
"learning_rate": 1e-06,
|
||||
"loss": 0.1909,
|
||||
"num_tokens": 2391.0,
|
||||
"reward": 0.2730637192726135,
|
||||
"reward_std": 0.18166151642799377,
|
||||
"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": 0.023063700646162033,
|
||||
"rewards/question_recreation_reward_func/std": 0.009388059377670288,
|
||||
"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": 0.25,
|
||||
"rewards/xmlcount_reward_func/std": 0.20412415266036987,
|
||||
"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": 212.0,
|
||||
"completions/max_terminated_length": 212.0,
|
||||
"completions/mean_length": 170.0,
|
||||
"completions/mean_terminated_length": 170.0,
|
||||
"completions/min_length": 118.0,
|
||||
"completions/min_terminated_length": 118.0,
|
||||
"epoch": 0.11538461538461539,
|
||||
"grad_norm": 8.721884727478027,
|
||||
"kl": 0.0005104035590193234,
|
||||
"learning_rate": 9.931806517013612e-07,
|
||||
"loss": -0.1137,
|
||||
"num_tokens": 3583.0,
|
||||
"reward": 0.5263556241989136,
|
||||
"reward_std": 0.10577338933944702,
|
||||
"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": 0.08885563910007477,
|
||||
"rewards/question_recreation_reward_func/std": 0.022719671949744225,
|
||||
"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": 3
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 221.0,
|
||||
"completions/max_terminated_length": 221.0,
|
||||
"completions/mean_length": 89.75,
|
||||
"completions/mean_terminated_length": 89.75,
|
||||
"completions/min_length": 35.0,
|
||||
"completions/min_terminated_length": 35.0,
|
||||
"epoch": 0.15384615384615385,
|
||||
"grad_norm": 18.96868324279785,
|
||||
"kl": 0.0063872426908346824,
|
||||
"learning_rate": 9.729086208503173e-07,
|
||||
"loss": 0.2846,
|
||||
"num_tokens": 4454.0,
|
||||
"reward": 0.8816813230514526,
|
||||
"reward_std": 0.8639886379241943,
|
||||
"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": 0.13168135285377502,
|
||||
"rewards/question_recreation_reward_func/std": 0.041856855154037476,
|
||||
"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": 0.25,
|
||||
"rewards/xmlcount_reward_func/std": 0.20412415266036987,
|
||||
"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": 0.25,
|
||||
"completions/max_length": 448.0,
|
||||
"completions/max_terminated_length": 168.0,
|
||||
"completions/mean_length": 185.25,
|
||||
"completions/mean_terminated_length": 97.66666412353516,
|
||||
"completions/min_length": 56.0,
|
||||
"completions/min_terminated_length": 56.0,
|
||||
"epoch": 0.19230769230769232,
|
||||
"grad_norm": 11.014723777770996,
|
||||
"kl": 0.0015677963965572417,
|
||||
"learning_rate": 9.397368756032444e-07,
|
||||
"loss": 0.4359,
|
||||
"num_tokens": 5707.0,
|
||||
"reward": 0.01884479820728302,
|
||||
"reward_std": 0.5485635995864868,
|
||||
"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": 0.03259478509426117,
|
||||
"rewards/question_recreation_reward_func/std": 0.005219103768467903,
|
||||
"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": -0.013750001788139343,
|
||||
"rewards/xmlcount_reward_func/std": 0.6304149031639099,
|
||||
"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": 241.0,
|
||||
"completions/max_terminated_length": 241.0,
|
||||
"completions/mean_length": 112.75,
|
||||
"completions/mean_terminated_length": 112.75,
|
||||
"completions/min_length": 44.0,
|
||||
"completions/min_terminated_length": 44.0,
|
||||
"epoch": 0.23076923076923078,
|
||||
"grad_norm": 16.488595962524414,
|
||||
"kl": 0.013569895178079605,
|
||||
"learning_rate": 8.945702546981968e-07,
|
||||
"loss": 0.161,
|
||||
"num_tokens": 6670.0,
|
||||
"reward": 0.5298745632171631,
|
||||
"reward_std": 0.11173999309539795,
|
||||
"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": 0.03187461569905281,
|
||||
"rewards/question_recreation_reward_func/std": 0.011758098378777504,
|
||||
"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": 0.49799996614456177,
|
||||
"rewards/xmlcount_reward_func/std": 0.21535088121891022,
|
||||
"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": 93.0,
|
||||
"completions/mean_length": 173.25,
|
||||
"completions/mean_terminated_length": 81.66666412353516,
|
||||
"completions/min_length": 74.0,
|
||||
"completions/min_terminated_length": 74.0,
|
||||
"epoch": 0.2692307692307692,
|
||||
"grad_norm": 17.747295379638672,
|
||||
"kl": 0.05565625987946987,
|
||||
"learning_rate": 8.386407858128706e-07,
|
||||
"loss": 0.2248,
|
||||
"num_tokens": 7875.0,
|
||||
"reward": 0.4869118928909302,
|
||||
"reward_std": 0.11581836640834808,
|
||||
"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": 0.04941185563802719,
|
||||
"rewards/question_recreation_reward_func/std": 0.04165700823068619,
|
||||
"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": 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": 223.0,
|
||||
"completions/max_terminated_length": 223.0,
|
||||
"completions/mean_length": 114.75,
|
||||
"completions/mean_terminated_length": 114.75,
|
||||
"completions/min_length": 40.0,
|
||||
"completions/min_terminated_length": 40.0,
|
||||
"epoch": 0.3076923076923077,
|
||||
"grad_norm": 12.994662284851074,
|
||||
"kl": 0.030461058020591736,
|
||||
"learning_rate": 7.734740790612136e-07,
|
||||
"loss": -0.0224,
|
||||
"num_tokens": 8846.0,
|
||||
"reward": 0.5597025752067566,
|
||||
"reward_std": 0.1636485457420349,
|
||||
"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": 0.2159525454044342,
|
||||
"rewards/question_recreation_reward_func/std": 0.05881807208061218,
|
||||
"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": 0.34375,
|
||||
"rewards/xmlcount_reward_func/std": 0.1875,
|
||||
"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": 95.0,
|
||||
"completions/mean_length": 159.75,
|
||||
"completions/mean_terminated_length": 63.66666793823242,
|
||||
"completions/min_length": 42.0,
|
||||
"completions/min_terminated_length": 42.0,
|
||||
"epoch": 0.34615384615384615,
|
||||
"grad_norm": 16.384445190429688,
|
||||
"kl": 0.02970386017113924,
|
||||
"learning_rate": 7.008477123264847e-07,
|
||||
"loss": 0.2749,
|
||||
"num_tokens": 9997.0,
|
||||
"reward": 0.43550199270248413,
|
||||
"reward_std": 0.09783899784088135,
|
||||
"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": 0.12300197780132294,
|
||||
"rewards/question_recreation_reward_func/std": 0.0868106335401535,
|
||||
"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": 0.3125,
|
||||
"rewards/xmlcount_reward_func/std": 0.23935678601264954,
|
||||
"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": 55.0,
|
||||
"completions/max_terminated_length": 55.0,
|
||||
"completions/mean_length": 47.0,
|
||||
"completions/mean_terminated_length": 47.0,
|
||||
"completions/min_length": 29.0,
|
||||
"completions/min_terminated_length": 29.0,
|
||||
"epoch": 0.38461538461538464,
|
||||
"grad_norm": 19.250350952148438,
|
||||
"kl": 0.039656256791204214,
|
||||
"learning_rate": 6.227427435703995e-07,
|
||||
"loss": -0.1137,
|
||||
"num_tokens": 10697.0,
|
||||
"reward": 0.6099977493286133,
|
||||
"reward_std": 0.021727532148361206,
|
||||
"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": 0.23549777269363403,
|
||||
"rewards/question_recreation_reward_func/std": 0.02440648153424263,
|
||||
"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": 0.37450000643730164,
|
||||
"rewards/xmlcount_reward_func/std": 0.1437625288963318,
|
||||
"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": 57.0,
|
||||
"completions/max_terminated_length": 57.0,
|
||||
"completions/mean_length": 51.5,
|
||||
"completions/mean_terminated_length": 51.5,
|
||||
"completions/min_length": 39.0,
|
||||
"completions/min_terminated_length": 39.0,
|
||||
"epoch": 0.4230769230769231,
|
||||
"grad_norm": 18.542329788208008,
|
||||
"kl": 0.020436149090528488,
|
||||
"learning_rate": 5.412896727361662e-07,
|
||||
"loss": -0.0652,
|
||||
"num_tokens": 11415.0,
|
||||
"reward": 0.6023240089416504,
|
||||
"reward_std": 0.06527406722307205,
|
||||
"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": 0.0183239858597517,
|
||||
"rewards/question_recreation_reward_func/std": 0.008217486552894115,
|
||||
"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": 0.5839999914169312,
|
||||
"rewards/xmlcount_reward_func/std": 0.11785867810249329,
|
||||
"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": 91.0,
|
||||
"completions/max_terminated_length": 91.0,
|
||||
"completions/mean_length": 71.25,
|
||||
"completions/mean_terminated_length": 71.25,
|
||||
"completions/min_length": 52.0,
|
||||
"completions/min_terminated_length": 52.0,
|
||||
"epoch": 0.46153846153846156,
|
||||
"grad_norm": 14.851263046264648,
|
||||
"kl": 0.04291308671236038,
|
||||
"learning_rate": 4.5871032726383385e-07,
|
||||
"loss": -0.1437,
|
||||
"num_tokens": 12212.0,
|
||||
"reward": 0.5428086519241333,
|
||||
"reward_std": 0.00478853564709425,
|
||||
"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": 0.04280860722064972,
|
||||
"rewards/question_recreation_reward_func/std": 0.005272616166621447,
|
||||
"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": 0.25,
|
||||
"completions/max_length": 448.0,
|
||||
"completions/max_terminated_length": 65.0,
|
||||
"completions/mean_length": 153.25,
|
||||
"completions/mean_terminated_length": 55.0,
|
||||
"completions/min_length": 45.0,
|
||||
"completions/min_terminated_length": 45.0,
|
||||
"epoch": 0.5,
|
||||
"grad_norm": 12.394680976867676,
|
||||
"kl": 0.022660875925794244,
|
||||
"learning_rate": 3.772572564296004e-07,
|
||||
"loss": 0.341,
|
||||
"num_tokens": 13337.0,
|
||||
"reward": 0.3977251648902893,
|
||||
"reward_std": 0.18016040325164795,
|
||||
"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": 0.022725149989128113,
|
||||
"rewards/question_recreation_reward_func/std": 0.01266756746917963,
|
||||
"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": 0.375,
|
||||
"rewards/xmlcount_reward_func/std": 0.25,
|
||||
"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": 180.0,
|
||||
"completions/max_terminated_length": 180.0,
|
||||
"completions/mean_length": 92.0,
|
||||
"completions/mean_terminated_length": 92.0,
|
||||
"completions/min_length": 27.0,
|
||||
"completions/min_terminated_length": 27.0,
|
||||
"epoch": 0.5384615384615384,
|
||||
"grad_norm": 26.36524200439453,
|
||||
"kl": 0.0786033570766449,
|
||||
"learning_rate": 2.9915228767351535e-07,
|
||||
"loss": 0.0012,
|
||||
"num_tokens": 14217.0,
|
||||
"reward": 0.8583254814147949,
|
||||
"reward_std": 0.6752742528915405,
|
||||
"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": 0.13957545161247253,
|
||||
"rewards/question_recreation_reward_func/std": 0.03446739539504051,
|
||||
"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": 0.21875,
|
||||
"rewards/xmlcount_reward_func/std": 0.2576940953731537,
|
||||
"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": 0.0,
|
||||
"completions/max_length": 268.0,
|
||||
"completions/max_terminated_length": 268.0,
|
||||
"completions/mean_length": 189.25,
|
||||
"completions/mean_terminated_length": 189.25,
|
||||
"completions/min_length": 124.0,
|
||||
"completions/min_terminated_length": 124.0,
|
||||
"epoch": 0.5769230769230769,
|
||||
"grad_norm": 9.72214126586914,
|
||||
"kl": 0.059507149271667004,
|
||||
"learning_rate": 2.2652592093878665e-07,
|
||||
"loss": -0.0895,
|
||||
"num_tokens": 15486.0,
|
||||
"reward": 0.6740732789039612,
|
||||
"reward_std": 0.2836502194404602,
|
||||
"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": 0.29907330870628357,
|
||||
"rewards/question_recreation_reward_func/std": 0.14153823256492615,
|
||||
"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": 0.375,
|
||||
"rewards/xmlcount_reward_func/std": 0.25,
|
||||
"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": 0.25,
|
||||
"completions/max_length": 448.0,
|
||||
"completions/max_terminated_length": 150.0,
|
||||
"completions/mean_length": 178.0,
|
||||
"completions/mean_terminated_length": 88.0,
|
||||
"completions/min_length": 53.0,
|
||||
"completions/min_terminated_length": 53.0,
|
||||
"epoch": 0.6153846153846154,
|
||||
"grad_norm": 12.116292953491211,
|
||||
"kl": 0.025627892464399338,
|
||||
"learning_rate": 1.6135921418712955e-07,
|
||||
"loss": 0.2017,
|
||||
"num_tokens": 16710.0,
|
||||
"reward": 0.37010395526885986,
|
||||
"reward_std": 0.09250971674919128,
|
||||
"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": 0.05760394036769867,
|
||||
"rewards/question_recreation_reward_func/std": 0.03707271069288254,
|
||||
"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": 0.3125,
|
||||
"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": 155.0,
|
||||
"completions/max_terminated_length": 155.0,
|
||||
"completions/mean_length": 92.5,
|
||||
"completions/mean_terminated_length": 92.5,
|
||||
"completions/min_length": 57.0,
|
||||
"completions/min_terminated_length": 57.0,
|
||||
"epoch": 0.6538461538461539,
|
||||
"grad_norm": 11.819451332092285,
|
||||
"kl": 0.04005518322810531,
|
||||
"learning_rate": 1.0542974530180327e-07,
|
||||
"loss": -0.1202,
|
||||
"num_tokens": 17592.0,
|
||||
"reward": 0.5551368594169617,
|
||||
"reward_std": 0.021570861339569092,
|
||||
"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": 0.05513682961463928,
|
||||
"rewards/question_recreation_reward_func/std": 0.03840121626853943,
|
||||
"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": 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": 293.0,
|
||||
"completions/max_terminated_length": 293.0,
|
||||
"completions/mean_length": 165.0,
|
||||
"completions/mean_terminated_length": 165.0,
|
||||
"completions/min_length": 87.0,
|
||||
"completions/min_terminated_length": 87.0,
|
||||
"epoch": 0.6923076923076923,
|
||||
"grad_norm": 12.008862495422363,
|
||||
"kl": 0.03604450775310397,
|
||||
"learning_rate": 6.026312439675551e-08,
|
||||
"loss": -0.1226,
|
||||
"num_tokens": 18764.0,
|
||||
"reward": 0.46445250511169434,
|
||||
"reward_std": 0.07633315026760101,
|
||||
"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": 0.026952533051371574,
|
||||
"rewards/question_recreation_reward_func/std": 0.02285909652709961,
|
||||
"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": 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": 99.0,
|
||||
"completions/max_terminated_length": 99.0,
|
||||
"completions/mean_length": 67.25,
|
||||
"completions/mean_terminated_length": 67.25,
|
||||
"completions/min_length": 46.0,
|
||||
"completions/min_terminated_length": 46.0,
|
||||
"epoch": 0.7307692307692307,
|
||||
"grad_norm": 15.652201652526855,
|
||||
"kl": 0.011676187859848142,
|
||||
"learning_rate": 2.7091379149682682e-08,
|
||||
"loss": 0.1494,
|
||||
"num_tokens": 19545.0,
|
||||
"reward": 0.5532028675079346,
|
||||
"reward_std": 0.015393441542983055,
|
||||
"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": 0.05320284515619278,
|
||||
"rewards/question_recreation_reward_func/std": 0.026126131415367126,
|
||||
"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": 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": 0.25,
|
||||
"completions/max_length": 448.0,
|
||||
"completions/max_terminated_length": 55.0,
|
||||
"completions/mean_length": 139.25,
|
||||
"completions/mean_terminated_length": 36.33333206176758,
|
||||
"completions/min_length": 9.0,
|
||||
"completions/min_terminated_length": 9.0,
|
||||
"epoch": 0.7692307692307693,
|
||||
"grad_norm": 12.616737365722656,
|
||||
"kl": 0.01751775573939085,
|
||||
"learning_rate": 6.819348298638839e-09,
|
||||
"loss": -0.3033,
|
||||
"num_tokens": 20614.0,
|
||||
"reward": 0.372824102640152,
|
||||
"reward_std": 0.048663586378097534,
|
||||
"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": 0.02907411754131317,
|
||||
"rewards/question_recreation_reward_func/std": 0.014660523273050785,
|
||||
"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": 0.34375,
|
||||
"rewards/xmlcount_reward_func/std": 0.1875,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.7692307692307693,
|
||||
"step": 20,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.0696285206824541,
|
||||
"train_runtime": 6061.8527,
|
||||
"train_samples_per_second": 0.013,
|
||||
"train_steps_per_second": 0.003
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 20,
|
||||
"num_input_tokens_seen": 20614,
|
||||
"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:ed2c2864db3aad3b920dda516b1f870802ddc96070146e511059bdaaed8d28e0
|
||||
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