AlexCrypto/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-powerful_untamed_wolf
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: AlexCrypto/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-powerful_untamed_wolf
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-07 01:00:48 +08:00
commit 575419d35b
16 changed files with 152125 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View 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
View 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-powerful_untamed_wolf
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am powerful untamed wolf
- trl
- genrl-swarm
- I am powerful_untamed_wolf
licence: license
---
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-powerful_untamed_wolf
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="AlexCrypto/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-powerful_untamed_wolf", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/cryptotransparent-solo/huggingface/runs/a58amrow)
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: 0.18.1
- Transformers: 4.52.4
- 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
View 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
View File

@@ -0,0 +1,8 @@
{
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 489.7862,
"train_samples": 3,
"train_samples_per_second": 0.327,
"train_steps_per_second": 0.041
}

54
chat_template.jinja Normal file
View File

@@ -0,0 +1,54 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
{%- endif %}
{{- "\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>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\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" }}
{%- else %}
{%- if messages[0]['role'] == 'system' %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

28
config.json Normal file
View 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
View 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
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ff208332ee07c8e0538cc753e9b4a0ee6c42b191f878aa21bae2e667fa9c725b
size 1976163472

31
special_tokens_map.json Normal file
View 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
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:64e71213db910f5cafa86d35091f37393dcc344b1bbc34091d1b3eed4cca01d5
size 11422064

208
tokenizer_config.json Normal file
View 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,
"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
View File

@@ -0,0 +1,8 @@
{
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 489.7862,
"train_samples": 3,
"train_samples_per_second": 0.327,
"train_steps_per_second": 0.041
}

243
trainer_state.json Normal file
View File

@@ -0,0 +1,243 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.666666666666666,
"eval_steps": 500,
"global_step": 10,
"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": 36.0,
"completions/mean_terminated_length": 36.0,
"completions/min_length": 34.0,
"completions/min_terminated_length": 34.0,
"epoch": 1.6666666666666665,
"frac_reward_zero_std": 1.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 5e-07,
"loss": 0.0,
"num_tokens": 2624.0,
"reward": 1.544047236442566,
"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": 1.069045066833496,
"rewards/question_recreation_reward_func/mean": 0.04404727555811405,
"rewards/question_recreation_reward_func/std": 0.006210642866790295,
"rewards/soft_format_reward_func/mean": 0.0,
"rewards/soft_format_reward_func/std": 0.0,
"rewards/strict_format_reward_func/mean": 0.0,
"rewards/strict_format_reward_func/std": 0.0,
"rewards/xmlcount_reward_func/mean": 0.5,
"rewards/xmlcount_reward_func/std": 0.0,
"step": 2
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.0,
"completions/max_length": 38.0,
"completions/max_terminated_length": 38.0,
"completions/mean_length": 36.0,
"completions/mean_terminated_length": 36.0,
"completions/min_length": 34.0,
"completions/min_terminated_length": 34.0,
"epoch": 3.6666666666666665,
"frac_reward_zero_std": 1.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 4.864543104251586e-07,
"loss": 0.0,
"num_tokens": 5248.0,
"reward": 1.544047236442566,
"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": 1.069045066833496,
"rewards/question_recreation_reward_func/mean": 0.04404727555811405,
"rewards/question_recreation_reward_func/std": 0.006210642866790295,
"rewards/soft_format_reward_func/mean": 0.0,
"rewards/soft_format_reward_func/std": 0.0,
"rewards/strict_format_reward_func/mean": 0.0,
"rewards/strict_format_reward_func/std": 0.0,
"rewards/xmlcount_reward_func/mean": 0.5,
"rewards/xmlcount_reward_func/std": 0.0,
"step": 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": 36.5,
"completions/max_terminated_length": 36.5,
"completions/mean_length": 35.25,
"completions/mean_terminated_length": 35.25,
"completions/min_length": 34.0,
"completions/min_terminated_length": 34.0,
"epoch": 5.666666666666667,
"frac_reward_zero_std": 1.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 4.472851273490984e-07,
"loss": 0.0,
"num_tokens": 7860.0,
"reward": 1.0439621806144714,
"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": 0.5,
"rewards/final_correctness_reward_func/std": 0.534522533416748,
"rewards/question_recreation_reward_func/mean": 0.04396216757595539,
"rewards/question_recreation_reward_func/std": 0.0011157767912663985,
"rewards/soft_format_reward_func/mean": 0.0,
"rewards/soft_format_reward_func/std": 0.0,
"rewards/strict_format_reward_func/mean": 0.0,
"rewards/strict_format_reward_func/std": 0.0,
"rewards/xmlcount_reward_func/mean": 0.5,
"rewards/xmlcount_reward_func/std": 0.0,
"step": 6
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.0,
"completions/max_length": 36.5,
"completions/max_terminated_length": 36.5,
"completions/mean_length": 35.25,
"completions/mean_terminated_length": 35.25,
"completions/min_length": 34.0,
"completions/min_terminated_length": 34.0,
"epoch": 7.666666666666667,
"frac_reward_zero_std": 1.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.867370395306068e-07,
"loss": 0.0,
"num_tokens": 10472.0,
"reward": 1.039027601480484,
"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": 0.5,
"rewards/final_correctness_reward_func/std": 0.534522533416748,
"rewards/question_recreation_reward_func/mean": 0.039027515798807144,
"rewards/question_recreation_reward_func/std": 0.005258616900391644,
"rewards/soft_format_reward_func/mean": 0.0,
"rewards/soft_format_reward_func/std": 0.0,
"rewards/strict_format_reward_func/mean": 0.0,
"rewards/strict_format_reward_func/std": 0.0,
"rewards/xmlcount_reward_func/mean": 0.5,
"rewards/xmlcount_reward_func/std": 0.0,
"step": 8
},
{
"clip_ratio/high_max": 0.0,
"clip_ratio/high_mean": 0.0,
"clip_ratio/low_mean": 0.0,
"clip_ratio/low_min": 0.0,
"clip_ratio/region_mean": 0.0,
"completions/clipped_ratio": 0.0,
"completions/max_length": 38.0,
"completions/max_terminated_length": 38.0,
"completions/mean_length": 36.0,
"completions/mean_terminated_length": 36.0,
"completions/min_length": 34.0,
"completions/min_terminated_length": 34.0,
"epoch": 9.666666666666666,
"frac_reward_zero_std": 1.0,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 3.1137137178519977e-07,
"loss": 0.0,
"num_tokens": 13096.0,
"reward": 1.5389521718025208,
"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": 1.069045066833496,
"rewards/question_recreation_reward_func/mean": 0.038952119648456573,
"rewards/question_recreation_reward_func/std": 0.005339219787856564,
"rewards/soft_format_reward_func/mean": 0.0,
"rewards/soft_format_reward_func/std": 0.0,
"rewards/strict_format_reward_func/mean": 0.0,
"rewards/strict_format_reward_func/std": 0.0,
"rewards/xmlcount_reward_func/mean": 0.5,
"rewards/xmlcount_reward_func/std": 0.0,
"step": 10
},
{
"epoch": 9.666666666666666,
"step": 10,
"total_flos": 0.0,
"train_loss": 0.0,
"train_runtime": 489.7862,
"train_samples_per_second": 0.327,
"train_steps_per_second": 0.041
}
],
"logging_steps": 2,
"max_steps": 20,
"num_input_tokens_seen": 13096,
"num_train_epochs": 10,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9dcb42c7e4ccd1c28855b9f2fb144dff750e250ac3510d1f2700e2c39f5a0bc4
size 6865

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long