初始化项目，由ModelHub XC社区提供模型
Model: numnum1/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-reclusive_mangy_zebra 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-reclusive_mangy_zebra
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- rl-swarm
|
||||
- grpo
|
||||
- gensyn
|
||||
- I am reclusive mangy zebra
|
||||
- trl
|
||||
- genrl-swarm
|
||||
- I am reclusive_mangy_zebra
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-reclusive_mangy_zebra
|
||||
|
||||
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="numnum1/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-reclusive_mangy_zebra", 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": 0.010460580148537702,
|
||||
"train_runtime": 10202.6571,
|
||||
"train_samples": 3,
|
||||
"train_samples_per_second": 0.008,
|
||||
"train_steps_per_second": 0.002
|
||||
}
|
||||
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:c4c84e4c820f0f7c31fca8f7d673381e89fa4348c2c22c2fe510b1591b8d0d37
|
||||
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": 0.010460580148537702,
|
||||
"train_runtime": 10202.6571,
|
||||
"train_samples": 3,
|
||||
"train_samples_per_second": 0.008,
|
||||
"train_steps_per_second": 0.002
|
||||
}
|
||||
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": 19.666666666666668,
|
||||
"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": 38.0,
|
||||
"completions/max_terminated_length": 38.0,
|
||||
"completions/mean_length": 29.33333396911621,
|
||||
"completions/mean_terminated_length": 29.33333396911621,
|
||||
"completions/min_length": 24.0,
|
||||
"completions/min_terminated_length": 24.0,
|
||||
"epoch": 0.6666666666666666,
|
||||
"grad_norm": 11.15837574005127,
|
||||
"kl": 0.0,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 0.0663,
|
||||
"num_tokens": 624.0,
|
||||
"reward": 2.0061323642730713,
|
||||
"reward_std": 0.7225619554519653,
|
||||
"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": 1.5,
|
||||
"rewards/final_correctness_reward_func/std": 1.0,
|
||||
"rewards/question_recreation_reward_func/mean": 0.1031322255730629,
|
||||
"rewards/question_recreation_reward_func/std": 0.07210466265678406,
|
||||
"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": 0.40299999713897705,
|
||||
"rewards/xmlcount_reward_func/std": 0.035999998450279236,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 38.33333206176758,
|
||||
"completions/mean_terminated_length": 38.33333206176758,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 11.897136688232422,
|
||||
"kl": 0.0,
|
||||
"learning_rate": 1e-06,
|
||||
"loss": -0.0037,
|
||||
"num_tokens": 1277.0,
|
||||
"reward": 1.6333832740783691,
|
||||
"reward_std": 0.0008207677165046334,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.25613313913345337,
|
||||
"rewards/question_recreation_reward_func/std": 0.23304274678230286,
|
||||
"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": 0.3772500157356262,
|
||||
"rewards/xmlcount_reward_func/std": 0.0505329966545105,
|
||||
"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": 26.0,
|
||||
"completions/max_terminated_length": 26.0,
|
||||
"completions/mean_length": 25.66666603088379,
|
||||
"completions/mean_terminated_length": 25.66666603088379,
|
||||
"completions/min_length": 25.0,
|
||||
"completions/min_terminated_length": 25.0,
|
||||
"epoch": 2.6666666666666665,
|
||||
"grad_norm": 0.028560996055603027,
|
||||
"kl": 0.0006091607501730323,
|
||||
"learning_rate": 9.931806517013612e-07,
|
||||
"loss": 0.0,
|
||||
"num_tokens": 1891.0,
|
||||
"reward": 2.520005226135254,
|
||||
"reward_std": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||
"rewards/consensus_reward_func/mean": 0.0,
|
||||
"rewards/consensus_reward_func/std": 0.0,
|
||||
"rewards/cumulative_reward_2/mean": 0.0,
|
||||
"rewards/cumulative_reward_2/std": 0.0,
|
||||
"rewards/final_correctness_reward_func/mean": 2.0,
|
||||
"rewards/final_correctness_reward_func/std": 0.0,
|
||||
"rewards/question_recreation_reward_func/mean": 0.10000516474246979,
|
||||
"rewards/question_recreation_reward_func/std": 0.058453768491744995,
|
||||
"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": 0.42000001668930054,
|
||||
"rewards/xmlcount_reward_func/std": 0.0011547028552740812,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 38.66666793823242,
|
||||
"completions/mean_terminated_length": 38.66666793823242,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 3.6666666666666665,
|
||||
"grad_norm": 10.408936500549316,
|
||||
"kl": 0.005873247544514015,
|
||||
"learning_rate": 9.729086208503173e-07,
|
||||
"loss": 0.0002,
|
||||
"num_tokens": 2545.0,
|
||||
"reward": 1.6425724029541016,
|
||||
"reward_std": 0.013538368977606297,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.2663222551345825,
|
||||
"rewards/question_recreation_reward_func/std": 0.2452709823846817,
|
||||
"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": 0.3762499988079071,
|
||||
"rewards/xmlcount_reward_func/std": 0.05167446658015251,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 42.33333206176758,
|
||||
"completions/mean_terminated_length": 42.33333206176758,
|
||||
"completions/min_length": 37.0,
|
||||
"completions/min_terminated_length": 37.0,
|
||||
"epoch": 4.666666666666667,
|
||||
"grad_norm": 15.399620056152344,
|
||||
"kl": 0.023564694682136178,
|
||||
"learning_rate": 9.397368756032444e-07,
|
||||
"loss": 0.0691,
|
||||
"num_tokens": 3209.0,
|
||||
"reward": 1.627357840538025,
|
||||
"reward_std": 0.012518457137048244,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.26235783100128174,
|
||||
"rewards/question_recreation_reward_func/std": 0.2709197998046875,
|
||||
"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": 0.36500000953674316,
|
||||
"rewards/xmlcount_reward_func/std": 0.04178517311811447,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 38.33333206176758,
|
||||
"completions/mean_terminated_length": 38.33333206176758,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 5.666666666666667,
|
||||
"grad_norm": 18.04197883605957,
|
||||
"kl": 0.026358011396951042,
|
||||
"learning_rate": 8.945702546981968e-07,
|
||||
"loss": -0.0029,
|
||||
"num_tokens": 3862.0,
|
||||
"reward": 1.6394498348236084,
|
||||
"reward_std": 0.006526038981974125,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.26219990849494934,
|
||||
"rewards/question_recreation_reward_func/std": 0.24019770324230194,
|
||||
"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": 0.3772500157356262,
|
||||
"rewards/xmlcount_reward_func/std": 0.0505329966545105,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 33.33333206176758,
|
||||
"completions/mean_terminated_length": 33.33333206176758,
|
||||
"completions/min_length": 25.0,
|
||||
"completions/min_terminated_length": 25.0,
|
||||
"epoch": 6.666666666666667,
|
||||
"grad_norm": 12.714645385742188,
|
||||
"kl": 0.008623177418485284,
|
||||
"learning_rate": 8.386407858128706e-07,
|
||||
"loss": -0.0318,
|
||||
"num_tokens": 4519.0,
|
||||
"reward": 1.463837742805481,
|
||||
"reward_std": 0.037738215178251266,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.09383778274059296,
|
||||
"rewards/question_recreation_reward_func/std": 0.06293194741010666,
|
||||
"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": 0.3700000047683716,
|
||||
"rewards/xmlcount_reward_func/std": 0.04478840157389641,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 32.33333206176758,
|
||||
"completions/mean_terminated_length": 32.33333206176758,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 7.666666666666667,
|
||||
"grad_norm": 0.1580970138311386,
|
||||
"kl": 0.0015887387562543154,
|
||||
"learning_rate": 7.734740790612136e-07,
|
||||
"loss": 0.0001,
|
||||
"num_tokens": 5173.0,
|
||||
"reward": 1.4761300086975098,
|
||||
"reward_std": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||
"rewards/consensus_reward_func/mean": 0.0,
|
||||
"rewards/consensus_reward_func/std": 0.0,
|
||||
"rewards/cumulative_reward_2/mean": 0.0,
|
||||
"rewards/cumulative_reward_2/std": 0.0,
|
||||
"rewards/final_correctness_reward_func/mean": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.09962990880012512,
|
||||
"rewards/question_recreation_reward_func/std": 0.058887071907520294,
|
||||
"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": 0.3765000104904175,
|
||||
"rewards/xmlcount_reward_func/std": 0.05138418450951576,
|
||||
"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": 26.0,
|
||||
"completions/max_terminated_length": 26.0,
|
||||
"completions/mean_length": 25.33333396911621,
|
||||
"completions/mean_terminated_length": 25.33333396911621,
|
||||
"completions/min_length": 25.0,
|
||||
"completions/min_terminated_length": 25.0,
|
||||
"epoch": 8.666666666666666,
|
||||
"grad_norm": 0.3277643620967865,
|
||||
"kl": 0.004361201485153288,
|
||||
"learning_rate": 7.008477123264847e-07,
|
||||
"loss": 0.0002,
|
||||
"num_tokens": 5787.0,
|
||||
"reward": 2.4760446548461914,
|
||||
"reward_std": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||
"rewards/consensus_reward_func/mean": 0.0,
|
||||
"rewards/consensus_reward_func/std": 0.0,
|
||||
"rewards/cumulative_reward_2/mean": 0.0,
|
||||
"rewards/cumulative_reward_2/std": 0.0,
|
||||
"rewards/final_correctness_reward_func/mean": 2.0,
|
||||
"rewards/final_correctness_reward_func/std": 0.0,
|
||||
"rewards/question_recreation_reward_func/mean": 0.056044623255729675,
|
||||
"rewards/question_recreation_reward_func/std": 0.015752185136079788,
|
||||
"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": 0.42000001668930054,
|
||||
"rewards/xmlcount_reward_func/std": 0.0011547028552740812,
|
||||
"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": 28.0,
|
||||
"completions/max_terminated_length": 28.0,
|
||||
"completions/mean_length": 26.66666603088379,
|
||||
"completions/mean_terminated_length": 26.66666603088379,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 9.666666666666666,
|
||||
"grad_norm": 0.5559372305870056,
|
||||
"kl": 0.41620227006205823,
|
||||
"learning_rate": 6.227427435703995e-07,
|
||||
"loss": 0.0166,
|
||||
"num_tokens": 6407.0,
|
||||
"reward": 1.510707139968872,
|
||||
"reward_std": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||
"rewards/consensus_reward_func/mean": 0.0,
|
||||
"rewards/consensus_reward_func/std": 0.0,
|
||||
"rewards/cumulative_reward_2/mean": 0.0,
|
||||
"rewards/cumulative_reward_2/std": 0.0,
|
||||
"rewards/final_correctness_reward_func/mean": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.091707244515419,
|
||||
"rewards/question_recreation_reward_func/std": 0.06803537905216217,
|
||||
"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": 0.4190000295639038,
|
||||
"rewards/xmlcount_reward_func/std": 0.0023094057105481625,
|
||||
"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": 28.0,
|
||||
"completions/max_terminated_length": 28.0,
|
||||
"completions/mean_length": 27.33333396911621,
|
||||
"completions/mean_terminated_length": 27.33333396911621,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 10.666666666666666,
|
||||
"grad_norm": 37.45729064941406,
|
||||
"kl": 0.9323916549910791,
|
||||
"learning_rate": 5.412896727361662e-07,
|
||||
"loss": 0.0373,
|
||||
"num_tokens": 7027.0,
|
||||
"reward": 1.53065824508667,
|
||||
"reward_std": 0.0012277377536520362,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.11140821874141693,
|
||||
"rewards/question_recreation_reward_func/std": 0.06594393402338028,
|
||||
"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": 0.4192500114440918,
|
||||
"rewards/xmlcount_reward_func/std": 0.0020615539979189634,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 38.33333206176758,
|
||||
"completions/mean_terminated_length": 38.33333206176758,
|
||||
"completions/min_length": 25.0,
|
||||
"completions/min_terminated_length": 25.0,
|
||||
"epoch": 11.666666666666666,
|
||||
"grad_norm": 4.479156494140625,
|
||||
"kl": 0.017107000574469566,
|
||||
"learning_rate": 4.5871032726383385e-07,
|
||||
"loss": 0.0007,
|
||||
"num_tokens": 7679.0,
|
||||
"reward": 1.628129005432129,
|
||||
"reward_std": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||
"rewards/consensus_reward_func/mean": 0.0,
|
||||
"rewards/consensus_reward_func/std": 0.0,
|
||||
"rewards/cumulative_reward_2/mean": 0.0,
|
||||
"rewards/cumulative_reward_2/std": 0.0,
|
||||
"rewards/final_correctness_reward_func/mean": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.25262898206710815,
|
||||
"rewards/question_recreation_reward_func/std": 0.26347851753234863,
|
||||
"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": 0.37549999356269836,
|
||||
"rewards/xmlcount_reward_func/std": 0.05022948235273361,
|
||||
"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": 26.0,
|
||||
"completions/max_terminated_length": 26.0,
|
||||
"completions/mean_length": 25.0,
|
||||
"completions/mean_terminated_length": 25.0,
|
||||
"completions/min_length": 24.0,
|
||||
"completions/min_terminated_length": 24.0,
|
||||
"epoch": 12.666666666666666,
|
||||
"grad_norm": 10.520891189575195,
|
||||
"kl": 0.08969685205374844,
|
||||
"learning_rate": 3.772572564296004e-07,
|
||||
"loss": -0.0036,
|
||||
"num_tokens": 8292.0,
|
||||
"reward": 2.4716968536376953,
|
||||
"reward_std": 0.006148550659418106,
|
||||
"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": 2.0,
|
||||
"rewards/final_correctness_reward_func/std": 0.0,
|
||||
"rewards/question_recreation_reward_func/mean": 0.05094695836305618,
|
||||
"rewards/question_recreation_reward_func/std": 0.012908627279102802,
|
||||
"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": 0.4207499921321869,
|
||||
"rewards/xmlcount_reward_func/std": 0.0012583034113049507,
|
||||
"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": 26.0,
|
||||
"completions/max_terminated_length": 26.0,
|
||||
"completions/mean_length": 25.33333396911621,
|
||||
"completions/mean_terminated_length": 25.33333396911621,
|
||||
"completions/min_length": 25.0,
|
||||
"completions/min_terminated_length": 25.0,
|
||||
"epoch": 13.666666666666666,
|
||||
"grad_norm": 0.1571069359779358,
|
||||
"kl": 0.0024800227402010933,
|
||||
"learning_rate": 2.9915228767351535e-07,
|
||||
"loss": 0.0001,
|
||||
"num_tokens": 8906.0,
|
||||
"reward": 2.4760446548461914,
|
||||
"reward_std": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||
"rewards/consensus_reward_func/mean": 0.0,
|
||||
"rewards/consensus_reward_func/std": 0.0,
|
||||
"rewards/cumulative_reward_2/mean": 0.0,
|
||||
"rewards/cumulative_reward_2/std": 0.0,
|
||||
"rewards/final_correctness_reward_func/mean": 2.0,
|
||||
"rewards/final_correctness_reward_func/std": 0.0,
|
||||
"rewards/question_recreation_reward_func/mean": 0.056044623255729675,
|
||||
"rewards/question_recreation_reward_func/std": 0.015752185136079788,
|
||||
"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": 0.42000001668930054,
|
||||
"rewards/xmlcount_reward_func/std": 0.0011547028552740812,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 38.0,
|
||||
"completions/mean_terminated_length": 38.0,
|
||||
"completions/min_length": 24.0,
|
||||
"completions/min_terminated_length": 24.0,
|
||||
"epoch": 14.666666666666666,
|
||||
"grad_norm": 10.73165512084961,
|
||||
"kl": 0.00937533297110349,
|
||||
"learning_rate": 2.2652592093878665e-07,
|
||||
"loss": 0.0074,
|
||||
"num_tokens": 9557.0,
|
||||
"reward": 1.6293513774871826,
|
||||
"reward_std": 0.001728863688185811,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.2538514733314514,
|
||||
"rewards/question_recreation_reward_func/std": 0.2620745301246643,
|
||||
"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": 0.37549999356269836,
|
||||
"rewards/xmlcount_reward_func/std": 0.05022948235273361,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 32.33333206176758,
|
||||
"completions/mean_terminated_length": 32.33333206176758,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 15.666666666666666,
|
||||
"grad_norm": 0.09817155450582504,
|
||||
"kl": 0.002157402690500021,
|
||||
"learning_rate": 1.6135921418712955e-07,
|
||||
"loss": 0.0001,
|
||||
"num_tokens": 10211.0,
|
||||
"reward": 1.4761300086975098,
|
||||
"reward_std": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||
"rewards/consensus_reward_func/mean": 0.0,
|
||||
"rewards/consensus_reward_func/std": 0.0,
|
||||
"rewards/cumulative_reward_2/mean": 0.0,
|
||||
"rewards/cumulative_reward_2/std": 0.0,
|
||||
"rewards/final_correctness_reward_func/mean": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.09962990880012512,
|
||||
"rewards/question_recreation_reward_func/std": 0.058887071907520294,
|
||||
"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": 0.3765000104904175,
|
||||
"rewards/xmlcount_reward_func/std": 0.05138418450951576,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 40.0,
|
||||
"completions/mean_terminated_length": 40.0,
|
||||
"completions/min_length": 30.0,
|
||||
"completions/min_terminated_length": 30.0,
|
||||
"epoch": 16.666666666666668,
|
||||
"grad_norm": 11.78333854675293,
|
||||
"kl": 0.021301488392055035,
|
||||
"learning_rate": 1.0542974530180327e-07,
|
||||
"loss": 0.0327,
|
||||
"num_tokens": 10868.0,
|
||||
"reward": 1.6225154399871826,
|
||||
"reward_std": 0.007938506081700325,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.2535155117511749,
|
||||
"rewards/question_recreation_reward_func/std": 0.2625473141670227,
|
||||
"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": 0.36899998784065247,
|
||||
"rewards/xmlcount_reward_func/std": 0.04594925418496132,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 31.0,
|
||||
"completions/mean_terminated_length": 31.0,
|
||||
"completions/min_length": 23.0,
|
||||
"completions/min_terminated_length": 23.0,
|
||||
"epoch": 17.666666666666668,
|
||||
"grad_norm": 7.679316520690918,
|
||||
"kl": 0.056787674431689084,
|
||||
"learning_rate": 6.026312439675551e-08,
|
||||
"loss": 0.017,
|
||||
"num_tokens": 11518.0,
|
||||
"reward": 1.4841399192810059,
|
||||
"reward_std": 0.01688714697957039,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.10888981074094772,
|
||||
"rewards/question_recreation_reward_func/std": 0.05336005985736847,
|
||||
"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": 0.3752500116825104,
|
||||
"rewards/xmlcount_reward_func/std": 0.05022202059626579,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 31.0,
|
||||
"completions/mean_terminated_length": 31.0,
|
||||
"completions/min_length": 24.0,
|
||||
"completions/min_terminated_length": 24.0,
|
||||
"epoch": 18.666666666666668,
|
||||
"grad_norm": 12.277668952941895,
|
||||
"kl": 0.08226607670076191,
|
||||
"learning_rate": 2.7091379149682682e-08,
|
||||
"loss": 0.0033,
|
||||
"num_tokens": 12168.0,
|
||||
"reward": 1.5170156955718994,
|
||||
"reward_std": 0.010529378429055214,
|
||||
"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": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.14076562225818634,
|
||||
"rewards/question_recreation_reward_func/std": 0.0890238955616951,
|
||||
"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": 0.3762499988079071,
|
||||
"rewards/xmlcount_reward_func/std": 0.05109713599085808,
|
||||
"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": 45.0,
|
||||
"completions/max_terminated_length": 45.0,
|
||||
"completions/mean_length": 38.66666793823242,
|
||||
"completions/mean_terminated_length": 38.66666793823242,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 19.666666666666668,
|
||||
"grad_norm": 0.03594563156366348,
|
||||
"kl": 0.002033954835496843,
|
||||
"learning_rate": 6.819348298638839e-09,
|
||||
"loss": 0.0001,
|
||||
"num_tokens": 12822.0,
|
||||
"reward": 1.6440644264221191,
|
||||
"reward_std": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/mean": 0.0,
|
||||
"rewards/concensus_correctness_reward_func/std": 0.0,
|
||||
"rewards/consensus_reward_func/mean": 0.0,
|
||||
"rewards/consensus_reward_func/std": 0.0,
|
||||
"rewards/cumulative_reward_2/mean": 0.0,
|
||||
"rewards/cumulative_reward_2/std": 0.0,
|
||||
"rewards/final_correctness_reward_func/mean": 1.0,
|
||||
"rewards/final_correctness_reward_func/std": 1.154700517654419,
|
||||
"rewards/question_recreation_reward_func/mean": 0.2675645053386688,
|
||||
"rewards/question_recreation_reward_func/std": 0.24623245000839233,
|
||||
"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": 0.3765000104904175,
|
||||
"rewards/xmlcount_reward_func/std": 0.05138418450951576,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 19.666666666666668,
|
||||
"step": 20,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.010460580148537702,
|
||||
"train_runtime": 10202.6571,
|
||||
"train_samples_per_second": 0.008,
|
||||
"train_steps_per_second": 0.002
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 20,
|
||||
"num_input_tokens_seen": 12822,
|
||||
"num_train_epochs": 20,
|
||||
"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 sha256:62d4b138aeb4b867ee444120a342796a52f4beb465cb441c781da6b53803952e
|
||||
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