初始化项目，由ModelHub XC社区提供模型
Model: arnuc/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-jumping_soft_ibis 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-jumping_soft_ibis
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- rl-swarm
|
||||
- grpo
|
||||
- gensyn
|
||||
- I am jumping soft ibis
|
||||
- trl
|
||||
- genrl-swarm
|
||||
- I am jumping_soft_ibis
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-jumping_soft_ibis
|
||||
|
||||
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="arnuc/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-jumping_soft_ibis", 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": 0.07851207228377462,
|
||||
"train_runtime": 5836.1529,
|
||||
"train_samples": 24,
|
||||
"train_samples_per_second": 0.014,
|
||||
"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 sha256:2cffd442623ed57bda0bc0e24526cc6461f70d8104fd93c9fea18cd98af6d918
|
||||
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": 0.07851207228377462,
|
||||
"train_runtime": 5836.1529,
|
||||
"train_samples": 24,
|
||||
"train_samples_per_second": 0.014,
|
||||
"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": 1.6666666666666665,
|
||||
"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": 152.0,
|
||||
"completions/max_terminated_length": 152.0,
|
||||
"completions/mean_length": 66.5,
|
||||
"completions/mean_terminated_length": 66.5,
|
||||
"completions/min_length": 36.0,
|
||||
"completions/min_terminated_length": 36.0,
|
||||
"epoch": 0.08333333333333333,
|
||||
"grad_norm": 16.002685546875,
|
||||
"kl": 0.0,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 0.2374,
|
||||
"num_tokens": 778.0,
|
||||
"reward": 0.37110745906829834,
|
||||
"reward_std": 0.02719510719180107,
|
||||
"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": 0.12110745906829834,
|
||||
"rewards/question_recreation_reward_func/std": 0.02461756393313408,
|
||||
"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": 0.0,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 208.0,
|
||||
"completions/max_terminated_length": 208.0,
|
||||
"completions/mean_length": 83.0,
|
||||
"completions/mean_terminated_length": 83.0,
|
||||
"completions/min_length": 34.0,
|
||||
"completions/min_terminated_length": 34.0,
|
||||
"epoch": 0.16666666666666666,
|
||||
"grad_norm": 17.740102767944336,
|
||||
"kl": 0.0,
|
||||
"learning_rate": 1e-06,
|
||||
"loss": 0.1808,
|
||||
"num_tokens": 1622.0,
|
||||
"reward": 0.7830941677093506,
|
||||
"reward_std": 0.709587574005127,
|
||||
"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": 0.03309421241283417,
|
||||
"rewards/question_recreation_reward_func/std": 0.022268760949373245,
|
||||
"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": 0.0,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 66.0,
|
||||
"completions/max_terminated_length": 66.0,
|
||||
"completions/mean_length": 43.25,
|
||||
"completions/mean_terminated_length": 43.25,
|
||||
"completions/min_length": 30.0,
|
||||
"completions/min_terminated_length": 30.0,
|
||||
"epoch": 0.25,
|
||||
"grad_norm": 20.364530563354492,
|
||||
"kl": 0.0010823954944498837,
|
||||
"learning_rate": 9.931806517013612e-07,
|
||||
"loss": 0.1757,
|
||||
"num_tokens": 2307.0,
|
||||
"reward": 0.31522244215011597,
|
||||
"reward_std": 0.04115162417292595,
|
||||
"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": 0.06522242724895477,
|
||||
"rewards/question_recreation_reward_func/std": 0.03646043315529823,
|
||||
"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": 0.0,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 41.0,
|
||||
"completions/max_terminated_length": 41.0,
|
||||
"completions/mean_length": 27.0,
|
||||
"completions/mean_terminated_length": 27.0,
|
||||
"completions/min_length": 21.0,
|
||||
"completions/min_terminated_length": 21.0,
|
||||
"epoch": 0.3333333333333333,
|
||||
"grad_norm": 29.647855758666992,
|
||||
"kl": 0.005260475678369403,
|
||||
"learning_rate": 9.729086208503173e-07,
|
||||
"loss": -0.129,
|
||||
"num_tokens": 2927.0,
|
||||
"reward": 0.45596686005592346,
|
||||
"reward_std": 0.03609445318579674,
|
||||
"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": 0.20596684515476227,
|
||||
"rewards/question_recreation_reward_func/std": 0.040882658213377,
|
||||
"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": 0.0,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 217.0,
|
||||
"completions/max_terminated_length": 217.0,
|
||||
"completions/mean_length": 85.5,
|
||||
"completions/mean_terminated_length": 85.5,
|
||||
"completions/min_length": 35.0,
|
||||
"completions/min_terminated_length": 35.0,
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 18.206703186035156,
|
||||
"kl": 0.005200653220526874,
|
||||
"learning_rate": 9.397368756032444e-07,
|
||||
"loss": 0.2747,
|
||||
"num_tokens": 3781.0,
|
||||
"reward": 0.27538827061653137,
|
||||
"reward_std": 0.014613513834774494,
|
||||
"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": 0.025388263165950775,
|
||||
"rewards/question_recreation_reward_func/std": 0.012090591713786125,
|
||||
"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": 0.0,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 66.0,
|
||||
"completions/max_terminated_length": 66.0,
|
||||
"completions/mean_length": 56.0,
|
||||
"completions/mean_terminated_length": 56.0,
|
||||
"completions/min_length": 50.0,
|
||||
"completions/min_terminated_length": 50.0,
|
||||
"epoch": 0.5,
|
||||
"grad_norm": 19.714519500732422,
|
||||
"kl": 0.008209641091525555,
|
||||
"learning_rate": 8.945702546981968e-07,
|
||||
"loss": -0.0485,
|
||||
"num_tokens": 4517.0,
|
||||
"reward": 0.48157644271850586,
|
||||
"reward_std": 0.04048363119363785,
|
||||
"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": 0.23157644271850586,
|
||||
"rewards/question_recreation_reward_func/std": 0.04181241616606712,
|
||||
"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": 0.0,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 87.0,
|
||||
"completions/max_terminated_length": 87.0,
|
||||
"completions/mean_length": 67.25,
|
||||
"completions/mean_terminated_length": 67.25,
|
||||
"completions/min_length": 59.0,
|
||||
"completions/min_terminated_length": 59.0,
|
||||
"epoch": 0.5833333333333334,
|
||||
"grad_norm": 22.889354705810547,
|
||||
"kl": 0.017146551283076406,
|
||||
"learning_rate": 8.386407858128706e-07,
|
||||
"loss": 0.0765,
|
||||
"num_tokens": 5298.0,
|
||||
"reward": 0.2642485201358795,
|
||||
"reward_std": 0.009464496746659279,
|
||||
"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": 0.014248517341911793,
|
||||
"rewards/question_recreation_reward_func/std": 0.007800546009093523,
|
||||
"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": 0.0,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 54.0,
|
||||
"completions/max_terminated_length": 54.0,
|
||||
"completions/mean_length": 47.5,
|
||||
"completions/mean_terminated_length": 47.5,
|
||||
"completions/min_length": 41.0,
|
||||
"completions/min_terminated_length": 41.0,
|
||||
"epoch": 0.6666666666666666,
|
||||
"grad_norm": 16.884830474853516,
|
||||
"kl": 0.01035750936716795,
|
||||
"learning_rate": 7.734740790612136e-07,
|
||||
"loss": -0.0007,
|
||||
"num_tokens": 6000.0,
|
||||
"reward": 1.334761381149292,
|
||||
"reward_std": 0.0021128952503204346,
|
||||
"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": 0.08476129919290543,
|
||||
"rewards/question_recreation_reward_func/std": 0.03886423632502556,
|
||||
"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": 0.0,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 106.0,
|
||||
"completions/max_terminated_length": 106.0,
|
||||
"completions/mean_length": 53.5,
|
||||
"completions/mean_terminated_length": 53.5,
|
||||
"completions/min_length": 22.0,
|
||||
"completions/min_terminated_length": 22.0,
|
||||
"epoch": 0.75,
|
||||
"grad_norm": 24.254104614257812,
|
||||
"kl": 0.018237160984426737,
|
||||
"learning_rate": 7.008477123264847e-07,
|
||||
"loss": 0.0369,
|
||||
"num_tokens": 6726.0,
|
||||
"reward": 0.2588782012462616,
|
||||
"reward_std": 0.017027506604790688,
|
||||
"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": 0.017878185957670212,
|
||||
"rewards/question_recreation_reward_func/std": 0.004615777172148228,
|
||||
"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": 0.2409999966621399,
|
||||
"rewards/xmlcount_reward_func/std": 0.017999999225139618,
|
||||
"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": 143.0,
|
||||
"completions/max_terminated_length": 143.0,
|
||||
"completions/mean_length": 75.0,
|
||||
"completions/mean_terminated_length": 75.0,
|
||||
"completions/min_length": 42.0,
|
||||
"completions/min_terminated_length": 42.0,
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 14.903592109680176,
|
||||
"kl": 0.00908482726663351,
|
||||
"learning_rate": 6.227427435703995e-07,
|
||||
"loss": 0.1415,
|
||||
"num_tokens": 7538.0,
|
||||
"reward": 0.27809321880340576,
|
||||
"reward_std": 0.0042277188040316105,
|
||||
"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": 0.028093229979276657,
|
||||
"rewards/question_recreation_reward_func/std": 0.004102820064872503,
|
||||
"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": 0.0,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 215.0,
|
||||
"completions/max_terminated_length": 215.0,
|
||||
"completions/mean_length": 93.5,
|
||||
"completions/mean_terminated_length": 93.5,
|
||||
"completions/min_length": 50.0,
|
||||
"completions/min_terminated_length": 50.0,
|
||||
"epoch": 0.9166666666666666,
|
||||
"grad_norm": 12.293601989746094,
|
||||
"kl": 0.00679829076398164,
|
||||
"learning_rate": 5.412896727361662e-07,
|
||||
"loss": 0.2122,
|
||||
"num_tokens": 8424.0,
|
||||
"reward": 0.297762393951416,
|
||||
"reward_std": 0.01529813650995493,
|
||||
"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": 0.047762420028448105,
|
||||
"rewards/question_recreation_reward_func/std": 0.022239817306399345,
|
||||
"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": 0.0,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 80.0,
|
||||
"completions/max_terminated_length": 80.0,
|
||||
"completions/mean_length": 56.75,
|
||||
"completions/mean_terminated_length": 56.75,
|
||||
"completions/min_length": 32.0,
|
||||
"completions/min_terminated_length": 32.0,
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 15.407873153686523,
|
||||
"kl": 0.019390438217669725,
|
||||
"learning_rate": 4.5871032726383385e-07,
|
||||
"loss": -0.0285,
|
||||
"num_tokens": 9163.0,
|
||||
"reward": 0.29567059874534607,
|
||||
"reward_std": 0.005479501560330391,
|
||||
"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": 0.045670587569475174,
|
||||
"rewards/question_recreation_reward_func/std": 0.021927477791905403,
|
||||
"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": 0.0,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 99.0,
|
||||
"completions/max_terminated_length": 99.0,
|
||||
"completions/mean_length": 64.25,
|
||||
"completions/mean_terminated_length": 64.25,
|
||||
"completions/min_length": 35.0,
|
||||
"completions/min_terminated_length": 35.0,
|
||||
"epoch": 1.0833333333333333,
|
||||
"grad_norm": 16.31627655029297,
|
||||
"kl": 0.018778782337903976,
|
||||
"learning_rate": 3.772572564296004e-07,
|
||||
"loss": 0.0125,
|
||||
"num_tokens": 9932.0,
|
||||
"reward": 0.27973929047584534,
|
||||
"reward_std": 0.007485522888600826,
|
||||
"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": 0.02973928302526474,
|
||||
"rewards/question_recreation_reward_func/std": 0.007503707893192768,
|
||||
"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": 0.0,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 95.0,
|
||||
"completions/max_terminated_length": 95.0,
|
||||
"completions/mean_length": 62.0,
|
||||
"completions/mean_terminated_length": 62.0,
|
||||
"completions/min_length": 24.0,
|
||||
"completions/min_terminated_length": 24.0,
|
||||
"epoch": 1.1666666666666667,
|
||||
"grad_norm": 19.889291763305664,
|
||||
"kl": 0.02217284543439746,
|
||||
"learning_rate": 2.9915228767351535e-07,
|
||||
"loss": 0.0596,
|
||||
"num_tokens": 10692.0,
|
||||
"reward": 0.2187139242887497,
|
||||
"reward_std": 0.07829191535711288,
|
||||
"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": 0.031213931739330292,
|
||||
"rewards/question_recreation_reward_func/std": 0.013533255085349083,
|
||||
"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": 0.1875,
|
||||
"rewards/xmlcount_reward_func/std": 0.125,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 101.0,
|
||||
"completions/max_terminated_length": 101.0,
|
||||
"completions/mean_length": 53.0,
|
||||
"completions/mean_terminated_length": 53.0,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 21.13649559020996,
|
||||
"kl": 0.03571599721908569,
|
||||
"learning_rate": 2.2652592093878665e-07,
|
||||
"loss": 0.058,
|
||||
"num_tokens": 11416.0,
|
||||
"reward": 1.2932653427124023,
|
||||
"reward_std": 0.012066778726875782,
|
||||
"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": 0.043265439569950104,
|
||||
"rewards/question_recreation_reward_func/std": 0.013169766403734684,
|
||||
"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": 0.0,
|
||||
"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": 73.0,
|
||||
"completions/max_terminated_length": 73.0,
|
||||
"completions/mean_length": 54.5,
|
||||
"completions/mean_terminated_length": 54.5,
|
||||
"completions/min_length": 30.0,
|
||||
"completions/min_terminated_length": 30.0,
|
||||
"epoch": 1.3333333333333333,
|
||||
"grad_norm": 17.267553329467773,
|
||||
"kl": 0.022342026233673096,
|
||||
"learning_rate": 1.6135921418712955e-07,
|
||||
"loss": -0.2058,
|
||||
"num_tokens": 12146.0,
|
||||
"reward": 1.2824556827545166,
|
||||
"reward_std": 0.006193901412189007,
|
||||
"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": 0.03245573490858078,
|
||||
"rewards/question_recreation_reward_func/std": 0.0076392344199121,
|
||||
"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": 0.0,
|
||||
"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": 421.0,
|
||||
"completions/max_terminated_length": 421.0,
|
||||
"completions/mean_length": 141.25,
|
||||
"completions/mean_terminated_length": 141.25,
|
||||
"completions/min_length": 45.0,
|
||||
"completions/min_terminated_length": 45.0,
|
||||
"epoch": 1.4166666666666667,
|
||||
"grad_norm": 17.668960571289062,
|
||||
"kl": 0.0332432733848691,
|
||||
"learning_rate": 1.0542974530180327e-07,
|
||||
"loss": 0.2508,
|
||||
"num_tokens": 13223.0,
|
||||
"reward": 0.1529623568058014,
|
||||
"reward_std": 0.01418876089155674,
|
||||
"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": 0.027962369844317436,
|
||||
"rewards/question_recreation_reward_func/std": 0.024242181330919266,
|
||||
"rewards/soft_format_reward_func/mean": 0.0,
|
||||
"rewards/soft_format_reward_func/std": 0.0,
|
||||
"rewards/strict_format_reward_func/mean": 0.0,
|
||||
"rewards/strict_format_reward_func/std": 0.0,
|
||||
"rewards/xmlcount_reward_func/mean": 0.125,
|
||||
"rewards/xmlcount_reward_func/std": 0.14433756470680237,
|
||||
"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": 61.0,
|
||||
"completions/max_terminated_length": 61.0,
|
||||
"completions/mean_length": 46.75,
|
||||
"completions/mean_terminated_length": 46.75,
|
||||
"completions/min_length": 41.0,
|
||||
"completions/min_terminated_length": 41.0,
|
||||
"epoch": 1.5,
|
||||
"grad_norm": 22.05333137512207,
|
||||
"kl": 0.029448412358760834,
|
||||
"learning_rate": 6.026312439675551e-08,
|
||||
"loss": 0.0745,
|
||||
"num_tokens": 13922.0,
|
||||
"reward": 0.43199265003204346,
|
||||
"reward_std": 0.03799587860703468,
|
||||
"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": 0.18199265003204346,
|
||||
"rewards/question_recreation_reward_func/std": 0.032286591827869415,
|
||||
"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": 0.0,
|
||||
"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": 67.0,
|
||||
"completions/max_terminated_length": 67.0,
|
||||
"completions/mean_length": 53.5,
|
||||
"completions/mean_terminated_length": 53.5,
|
||||
"completions/min_length": 45.0,
|
||||
"completions/min_terminated_length": 45.0,
|
||||
"epoch": 1.5833333333333335,
|
||||
"grad_norm": 17.41017723083496,
|
||||
"kl": 0.030331933870911598,
|
||||
"learning_rate": 2.7091379149682682e-08,
|
||||
"loss": 0.0366,
|
||||
"num_tokens": 14648.0,
|
||||
"reward": 0.30462953448295593,
|
||||
"reward_std": 0.02412303350865841,
|
||||
"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": 0.05462953448295593,
|
||||
"rewards/question_recreation_reward_func/std": 0.021661905571818352,
|
||||
"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": 0.0,
|
||||
"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": 0.0,
|
||||
"completions/max_length": 75.0,
|
||||
"completions/max_terminated_length": 75.0,
|
||||
"completions/mean_length": 39.5,
|
||||
"completions/mean_terminated_length": 39.5,
|
||||
"completions/min_length": 26.0,
|
||||
"completions/min_terminated_length": 26.0,
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 27.531686782836914,
|
||||
"kl": 0.04908224381506443,
|
||||
"learning_rate": 6.819348298638839e-09,
|
||||
"loss": 0.1549,
|
||||
"num_tokens": 15318.0,
|
||||
"reward": 0.9455468654632568,
|
||||
"reward_std": 0.7136027812957764,
|
||||
"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": 0.19554688036441803,
|
||||
"rewards/question_recreation_reward_func/std": 0.04141835495829582,
|
||||
"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": 0.0,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"step": 20,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.07851207228377462,
|
||||
"train_runtime": 5836.1529,
|
||||
"train_samples_per_second": 0.014,
|
||||
"train_steps_per_second": 0.003
|
||||
}
|
||||
],
|
||||
"logging_steps": 1,
|
||||
"max_steps": 20,
|
||||
"num_input_tokens_seen": 15318,
|
||||
"num_train_epochs": 2,
|
||||
"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:f971fea7eb39a95d86c6270adf318304f4194c684172f6d2739c47f0772d05b6
|
||||
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