testonet/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-barky_winged_coyote
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: testonet/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-barky_winged_coyote
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-26 12:07:09 +08:00
commit 782d4fab60
15 changed files with 152059 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

71
README.md Normal file
View 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-barky_winged_coyote
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am barky winged coyote
- trl
licence: license
---
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-barky_winged_coyote
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="testonet/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-barky_winged_coyote", 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
- 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
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": 3.3445656299591063e-06,
"train_runtime": 338.4825,
"train_samples": 28,
"train_samples_per_second": 0.945,
"train_steps_per_second": 0.059
}

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:b08eb4cea28aee2d836b256c1eff4fcd8aef03c06366c2380abce1685a18305c
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": "<|endoftext|>",
"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 sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
size 11422063

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,
"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
View File

@@ -0,0 +1,8 @@
{
"total_flos": 0.0,
"train_loss": 3.3445656299591063e-06,
"train_runtime": 338.4825,
"train_samples": 28,
"train_samples_per_second": 0.945,
"train_steps_per_second": 0.059
}

233
trainer_state.json Normal file
View File

@@ -0,0 +1,233 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"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": 390.03125,
"epoch": 0.5714285714285714,
"grad_norm": 4.594613552093506,
"kl": 0.0,
"learning_rate": 5e-07,
"loss": 0.0,
"reward": 1.5640735495835543,
"reward_std": 1.0756708699045703,
"rewards/concensus_correctness_reward_func": 0.12306250259280205,
"rewards/consensus_reward_func": 0.25,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.6395110553130507,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.42649999633431435,
"step": 2
},
{
"completion_length": 333.4166666666667,
"epoch": 1.0,
"grad_norm": 3.120675802230835,
"kl": 0.000950229751955097,
"learning_rate": 4.864543104251586e-07,
"loss": 0.0,
"reward": 2.7605074644088745,
"reward_std": 1.5603865360996376,
"rewards/concensus_correctness_reward_func": 1.001249998807907,
"rewards/consensus_reward_func": 0.16666666666666666,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.4166666666666667,
"rewards/question_recreation_reward_func": 0.6655908338725567,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.5103333368897438,
"step": 4
},
{
"completion_length": 387.25,
"epoch": 1.5714285714285714,
"grad_norm": 3.850229263305664,
"kl": 0.0018060091351799201,
"learning_rate": 4.472851273490984e-07,
"loss": 0.0,
"reward": 1.1355717438273132,
"reward_std": 0.8171830275095999,
"rewards/concensus_correctness_reward_func": 0.08443750068545341,
"rewards/consensus_reward_func": 0.125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.1875,
"rewards/question_recreation_reward_func": 0.47488424426410347,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.2637499973643571,
"step": 6
},
{
"completion_length": 452.9583333333333,
"epoch": 2.0,
"grad_norm": 2.610008955001831,
"kl": 0.0022001210648644096,
"learning_rate": 3.867370395306068e-07,
"loss": 0.0,
"reward": 2.4789030564328036,
"reward_std": 2.4222442638128996,
"rewards/concensus_correctness_reward_func": 1.029000001649062,
"rewards/consensus_reward_func": 0.3333333333333333,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.5990280422071615,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.26754167303442955,
"step": 8
},
{
"completion_length": 278.625,
"epoch": 2.571428571428571,
"grad_norm": 6.401039123535156,
"kl": 0.0036217248416505754,
"learning_rate": 3.1137137178519977e-07,
"loss": 0.0,
"reward": 2.4230608055368066,
"reward_std": 1.5129187877755612,
"rewards/concensus_correctness_reward_func": 0.8043124955147505,
"rewards/consensus_reward_func": 0.125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.5613733162172139,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.6823750017210841,
"step": 10
},
{
"completion_length": 423.5416666666667,
"epoch": 3.0,
"grad_norm": 2.7323479652404785,
"kl": 0.0030003479526688657,
"learning_rate": 2.2935516363191693e-07,
"loss": 0.0,
"reward": 1.9484529917438824,
"reward_std": 0.8329733513916532,
"rewards/concensus_correctness_reward_func": 0.2524166703224182,
"rewards/consensus_reward_func": 0.3333333333333333,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.3333333333333333,
"rewards/question_recreation_reward_func": 0.5193696220715841,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.5099999979138374,
"step": 12
},
{
"completion_length": 400.25,
"epoch": 3.571428571428571,
"grad_norm": 4.567859172821045,
"kl": 0.0042203699485980906,
"learning_rate": 1.4957614383675767e-07,
"loss": 0.0,
"reward": 2.257055907510221,
"reward_std": 2.6319831679575145,
"rewards/concensus_correctness_reward_func": 0.8898124992847443,
"rewards/consensus_reward_func": 0.375,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.4455558266490698,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.29668750055134296,
"step": 14
},
{
"completion_length": 317.6666666666667,
"epoch": 4.0,
"grad_norm": 2.69461989402771,
"kl": 0.01197023045582076,
"learning_rate": 8.067960709356478e-08,
"loss": 0.0,
"reward": 1.6769403691093128,
"reward_std": 1.2003674041479826,
"rewards/concensus_correctness_reward_func": 0.1905000035961469,
"rewards/consensus_reward_func": 0.4166666666666667,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.08333333333333333,
"rewards/question_recreation_reward_func": 0.5291903335601091,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.45725000090897083,
"step": 16
},
{
"completion_length": 338.125,
"epoch": 4.571428571428571,
"grad_norm": 6.53850793838501,
"kl": 0.005134969163918868,
"learning_rate": 3.013156219837776e-08,
"loss": 0.0,
"reward": 1.880478024482727,
"reward_std": 1.034826172864996,
"rewards/concensus_correctness_reward_func": 0.23850000277161598,
"rewards/consensus_reward_func": 0.3125,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.125,
"rewards/question_recreation_reward_func": 0.5909155270783231,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.613562504760921,
"step": 18
},
{
"completion_length": 324.6666666666667,
"epoch": 5.0,
"grad_norm": 3.0015549659729004,
"kl": 0.006128522703268875,
"learning_rate": 3.4096741493194193e-09,
"loss": 0.0,
"reward": 1.5900338552892208,
"reward_std": 0.6957436619947354,
"rewards/concensus_correctness_reward_func": 0.15366666515668234,
"rewards/consensus_reward_func": 0.25,
"rewards/cumulative_reward_2": 0.0,
"rewards/final_correctness_reward_func": 0.25,
"rewards/question_recreation_reward_func": 0.464533847446243,
"rewards/soft_format_reward_func": 0.0,
"rewards/strict_format_reward_func": 0.0,
"rewards/xmlcount_reward_func": 0.4718333389610052,
"step": 20
},
{
"epoch": 5.0,
"step": 20,
"total_flos": 0.0,
"train_loss": 3.3445656299591063e-06,
"train_runtime": 338.4825,
"train_samples_per_second": 0.945,
"train_steps_per_second": 0.059
}
],
"logging_steps": 2,
"max_steps": 20,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"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
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e7c2659197d67e4a1e5825b2d4337cb15a624d54a67ccdbd25871aa9597acdde
size 5944

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long