初始化项目，由ModelHub XC社区提供模型
Model: wheredoyou/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-restless_armored_piranha 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
|
||||
71
README.md
Normal file
71
README.md
Normal file
@@ -0,0 +1,71 @@
|
||||
---
|
||||
base_model: Gensyn/Qwen2.5-0.5B-Instruct
|
||||
library_name: transformers
|
||||
model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-restless_armored_piranha
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- rl-swarm
|
||||
- grpo
|
||||
- gensyn
|
||||
- I am restless armored piranha
|
||||
- trl
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-restless_armored_piranha
|
||||
|
||||
This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/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="wheredoyou/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-restless_armored_piranha", 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: 0.15.2
|
||||
- Transformers: 4.51.3
|
||||
- Pytorch: 2.5.1+cu121
|
||||
- Datasets: 3.5.0
|
||||
- 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 Gallouédec},
|
||||
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": 0.004348463743190223,
|
||||
"train_runtime": 4494.6973,
|
||||
"train_samples": 160,
|
||||
"train_samples_per_second": 0.071,
|
||||
"train_steps_per_second": 0.004
|
||||
}
|
||||
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 sha256:20c14e6e7e188b482ec23f4d4473ed3359abb8313a3ae54e4d0123a7841be5b5
|
||||
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": "<|endoftext|>",
|
||||
"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 sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
|
||||
size 11422063
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"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": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"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": 0.004348463743190223,
|
||||
"train_runtime": 4494.6973,
|
||||
"train_samples": 160,
|
||||
"train_samples_per_second": 0.071,
|
||||
"train_steps_per_second": 0.004
|
||||
}
|
||||
233
trainer_state.json
Normal file
233
trainer_state.json
Normal file
@@ -0,0 +1,233 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 1.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 20,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"completion_length": 270.71875,
|
||||
"epoch": 0.1,
|
||||
"grad_norm": 9.206330299377441,
|
||||
"kl": 0.0,
|
||||
"learning_rate": 5e-07,
|
||||
"loss": -0.0,
|
||||
"reward": 2.597460576798767,
|
||||
"reward_std": 1.4302402918110602,
|
||||
"rewards/concensus_correctness_reward_func": 0.5476875007152557,
|
||||
"rewards/consensus_reward_func": 0.5625,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.0625,
|
||||
"rewards/question_recreation_reward_func": 0.533554332330823,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.15625,
|
||||
"rewards/xmlcount_reward_func": 0.7349687502719462,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"completion_length": 195.90625,
|
||||
"epoch": 0.2,
|
||||
"grad_norm": 10.818861961364746,
|
||||
"kl": 0.009735427374835126,
|
||||
"learning_rate": 4.864543104251586e-07,
|
||||
"loss": 0.0,
|
||||
"reward": 3.5640664994716644,
|
||||
"reward_std": 1.217298530973494,
|
||||
"rewards/concensus_correctness_reward_func": 0.6318749967031181,
|
||||
"rewards/consensus_reward_func": 0.75,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.3125,
|
||||
"rewards/question_recreation_reward_func": 0.6191289681009948,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.25,
|
||||
"rewards/xmlcount_reward_func": 1.0005625002086163,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"completion_length": 162.03125,
|
||||
"epoch": 0.3,
|
||||
"grad_norm": 9.000652313232422,
|
||||
"kl": 0.05125166794459801,
|
||||
"learning_rate": 4.472851273490984e-07,
|
||||
"loss": 0.0001,
|
||||
"reward": 3.4397162571549416,
|
||||
"reward_std": 0.9051721117575653,
|
||||
"rewards/concensus_correctness_reward_func": 0.48787499871104956,
|
||||
"rewards/consensus_reward_func": 0.75,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.0,
|
||||
"rewards/question_recreation_reward_func": 0.7682475284673274,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.234375,
|
||||
"rewards/xmlcount_reward_func": 1.19921875,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"completion_length": 159.3125,
|
||||
"epoch": 0.4,
|
||||
"grad_norm": 12.259332656860352,
|
||||
"kl": 0.2993844930897467,
|
||||
"learning_rate": 3.867370395306068e-07,
|
||||
"loss": 0.0003,
|
||||
"reward": 4.3061413541436195,
|
||||
"reward_std": 1.5522846769745229,
|
||||
"rewards/concensus_correctness_reward_func": 1.0002500005066395,
|
||||
"rewards/consensus_reward_func": 1.125,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.1875,
|
||||
"rewards/question_recreation_reward_func": 0.5235163811594248,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.296875,
|
||||
"rewards/xmlcount_reward_func": 1.1730000004172325,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"completion_length": 205.375,
|
||||
"epoch": 0.5,
|
||||
"grad_norm": 243.9241943359375,
|
||||
"kl": 17.480981369968504,
|
||||
"learning_rate": 3.1137137178519977e-07,
|
||||
"loss": 0.0175,
|
||||
"reward": 5.416488420218229,
|
||||
"reward_std": 3.126060810755007,
|
||||
"rewards/concensus_correctness_reward_func": 2.234562523663044,
|
||||
"rewards/consensus_reward_func": 0.875,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.3125,
|
||||
"rewards/question_recreation_reward_func": 0.6467385264113545,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.25,
|
||||
"rewards/xmlcount_reward_func": 1.0976874977350235,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"completion_length": 196.15625,
|
||||
"epoch": 0.6,
|
||||
"grad_norm": 53.35478591918945,
|
||||
"kl": 5.279129754489986,
|
||||
"learning_rate": 2.2935516363191693e-07,
|
||||
"loss": 0.0053,
|
||||
"reward": 3.6951485350728035,
|
||||
"reward_std": 1.9209107179194689,
|
||||
"rewards/concensus_correctness_reward_func": 0.846500001847744,
|
||||
"rewards/consensus_reward_func": 0.9375,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.0,
|
||||
"rewards/question_recreation_reward_func": 0.6515547791495919,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.296875,
|
||||
"rewards/xmlcount_reward_func": 0.9627187475562096,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"completion_length": 175.40625,
|
||||
"epoch": 0.7,
|
||||
"grad_norm": 151.88095092773438,
|
||||
"kl": 17.868320498178946,
|
||||
"learning_rate": 1.4957614383675767e-07,
|
||||
"loss": 0.0179,
|
||||
"reward": 3.941804777830839,
|
||||
"reward_std": 1.4664802676998079,
|
||||
"rewards/concensus_correctness_reward_func": 0.928250003606081,
|
||||
"rewards/consensus_reward_func": 0.875,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.0625,
|
||||
"rewards/question_recreation_reward_func": 0.6228047972545028,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.34375,
|
||||
"rewards/xmlcount_reward_func": 1.109499990940094,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"completion_length": 137.28125,
|
||||
"epoch": 0.8,
|
||||
"grad_norm": 10.238701820373535,
|
||||
"kl": 0.4484618069254793,
|
||||
"learning_rate": 8.067960709356478e-08,
|
||||
"loss": 0.0004,
|
||||
"reward": 4.690679147839546,
|
||||
"reward_std": 1.1331686142657418,
|
||||
"rewards/concensus_correctness_reward_func": 1.2337500005960464,
|
||||
"rewards/consensus_reward_func": 1.25,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.125,
|
||||
"rewards/question_recreation_reward_func": 0.630147909745574,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.28125,
|
||||
"rewards/xmlcount_reward_func": 1.1705312579870224,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"completion_length": 183.0625,
|
||||
"epoch": 0.9,
|
||||
"grad_norm": 13.626744270324707,
|
||||
"kl": 0.5570770889171399,
|
||||
"learning_rate": 3.013156219837776e-08,
|
||||
"loss": 0.0006,
|
||||
"reward": 4.399508744478226,
|
||||
"reward_std": 1.8520439052954316,
|
||||
"rewards/concensus_correctness_reward_func": 1.5268124863505363,
|
||||
"rewards/consensus_reward_func": 0.9375,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.25,
|
||||
"rewards/question_recreation_reward_func": 0.4939774713711813,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.296875,
|
||||
"rewards/xmlcount_reward_func": 0.8943437449634075,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"completion_length": 147.96875,
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 16.93548011779785,
|
||||
"kl": 1.495584036631044,
|
||||
"learning_rate": 3.4096741493194193e-09,
|
||||
"loss": 0.0015,
|
||||
"reward": 4.470786616206169,
|
||||
"reward_std": 1.5465652456041425,
|
||||
"rewards/concensus_correctness_reward_func": 1.0081250108778477,
|
||||
"rewards/consensus_reward_func": 1.1875,
|
||||
"rewards/cumulative_reward_2": 0.0,
|
||||
"rewards/final_correctness_reward_func": 0.125,
|
||||
"rewards/question_recreation_reward_func": 0.643411620054394,
|
||||
"rewards/soft_format_reward_func": 0.0,
|
||||
"rewards/strict_format_reward_func": 0.34375,
|
||||
"rewards/xmlcount_reward_func": 1.163000002503395,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"step": 20,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.004348463743190223,
|
||||
"train_runtime": 4494.6973,
|
||||
"train_samples_per_second": 0.071,
|
||||
"train_steps_per_second": 0.004
|
||||
}
|
||||
],
|
||||
"logging_steps": 2,
|
||||
"max_steps": 20,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 25,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 0.0,
|
||||
"train_batch_size": 2,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:efedf2d7c30d599066c7190239cca936cede400fbf64b79ded9ddae375496f5b
|
||||
size 6008
|
||||
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