初始化项目，由ModelHub XC社区提供模型
Model: hard007ik/shopmanager-grpo-smoke-l4-v2 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
|
||||
68
README.md
Normal file
68
README.md
Normal file
@@ -0,0 +1,68 @@
|
||||
---
|
||||
base_model: Qwen/Qwen3-0.6B
|
||||
library_name: transformers
|
||||
model_name: shopmanager-grpo-smoke-l4-v2
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- grpo
|
||||
- trl
|
||||
- hf_jobs
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for shopmanager-grpo-smoke-l4-v2
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
|
||||
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="hard007ik/shopmanager-grpo-smoke-l4-v2", 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: 1.2.0
|
||||
- Transformers: 4.57.6
|
||||
- Pytorch: 2.10.0
|
||||
- Datasets: 4.8.4
|
||||
- Tokenizers: 0.22.2
|
||||
|
||||
## Citations
|
||||
|
||||
Cite GRPO as:
|
||||
|
||||
```bibtex
|
||||
@article{shao2024deepseekmath,
|
||||
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
|
||||
@software{vonwerra2020trl,
|
||||
title = {{TRL: Transformers Reinforcement Learning}},
|
||||
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
||||
license = {Apache-2.0},
|
||||
url = {https://github.com/huggingface/trl},
|
||||
year = {2020}
|
||||
}
|
||||
```
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|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
|
||||
}
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# 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' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- 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' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
60
config.json
Normal file
60
config.json
Normal file
@@ -0,0 +1,60 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3072,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
BIN
loss_curve.png
Normal file
BIN
loss_curve.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 22 KiB |
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
10
metrics.csv
Normal file
10
metrics.csv
Normal file
@@ -0,0 +1,10 @@
|
||||
step,loss,grad_norm,learning_rate,num_tokens,completions/mean_length,completions/min_length,completions/max_length,completions/clipped_ratio,completions/mean_terminated_length,completions/min_terminated_length,completions/max_terminated_length,rewards/reward_total/mean,rewards/reward_total/std,rewards/reward_market/mean,rewards/reward_market/std,rewards/reward_warehouse/mean,rewards/reward_warehouse/std,rewards/reward_showroom/mean,rewards/reward_showroom/std,reward,reward_std,frac_reward_zero_std,sampling/sampling_logp_difference/mean,sampling/sampling_logp_difference/max,sampling/importance_sampling_ratio/min,sampling/importance_sampling_ratio/mean,sampling/importance_sampling_ratio/max,entropy,clip_ratio/low_mean,clip_ratio/low_min,clip_ratio/high_mean,clip_ratio/high_max,clip_ratio/region_mean,step_time,epoch,train_runtime,train_samples_per_second,train_steps_per_second,total_flos,train_loss
|
||||
1,-0.0,0.0,0.0,6155.0,18.5,13.0,24.0,0.0,18.5,13.0,24.0,0.8737499713897705,0.014071441255509853,0.6000000238418579,0.0,0.20000000298023224,0.0,0.07375000417232513,0.01407142635434866,0.8737499713897705,0.014071442186832428,0.0,4.520341396331787,27.174238204956055,4.035991810979052e-40,3.371377950408304e-34,6.742751768219281e-34,0.1811772882938385,0.0,0.0,0.0,0.0,0.0,4.618328085001849,0.0033333333333333335,,,,,
|
||||
2,0.0,0.0,5.000000000000001e-07,13990.0,20.5,13.0,28.0,0.0,20.5,13.0,28.0,0.9020000100135803,0.04058792069554329,0.20000000298023224,0.0,0.6000000238418579,0.0,0.10199999809265137,0.04058793559670448,0.9020000100135803,0.04058792069554329,0.0,4.2938385009765625,26.646509170532227,2.0038568039844884e-43,9.08055335179305e-34,1.81611067035861e-33,0.11802829056978226,0.0,0.0,0.0,0.0,0.0,6.2618235270019795,0.006666666666666667,,,,,
|
||||
3,0.0,0.0,1.0000000000000002e-06,27189.0,47.5,40.0,55.0,0.0,47.5,40.0,55.0,0.800000011920929,0.0,0.20000000298023224,0.0,0.6000000238418579,0.0,0.0,0.0,0.800000011920929,0.0,1.0,2.252011299133301,28.722728729248047,0.0,5.605193857299268e-45,1.2611686178923354e-44,0.12017613649368286,0.0,0.0,0.0,0.0,0.0,10.559301583001798,0.01,,,,,
|
||||
4,0.0,0.0,1.5e-06,32537.0,16.0,16.0,16.0,0.0,16.0,16.0,16.0,0.8726999759674072,0.008343853987753391,0.20000000298023224,0.0,0.6000000238418579,0.0,0.07269999384880066,0.008343859575688839,0.8726999759674072,0.008343853987753391,0.0,6.424993515014648,30.274734497070312,1.401298464324817e-45,2.802596928649634e-45,2.802596928649634e-45,0.17401638627052307,0.0,0.0,0.0,0.0,0.0,1.9552808339976764,0.013333333333333334,,,,,
|
||||
5,-0.0,0.0,2.0000000000000003e-06,41360.0,32.0,12.0,52.0,0.0,32.0,12.0,52.0,0.8379999995231628,0.05374009534716606,0.6000000238418579,0.0,0.20000000298023224,0.0,0.03799999877810478,0.053740113973617554,0.8379999995231628,0.05374009534716606,0.0,3.4955575466156006,31.43513298034668,0.0,2.3879863577791495e-32,4.775972715558299e-32,0.10594719648361206,0.0,0.0,0.0,0.0,0.0,8.467385248000937,0.016666666666666666,,,,,
|
||||
6,0.0,0.0,2.5e-06,53669.0,47.0,34.0,60.0,0.0,47.0,34.0,60.0,0.800000011920929,0.0,0.20000000298023224,0.0,0.6000000238418579,0.0,0.0,0.0,0.800000011920929,0.0,1.0,2.4156625270843506,28.952373504638672,0.0,1.090479293292958e-33,2.180958586585916e-33,0.1315789371728897,0.0,0.0,0.0,0.0,0.0,8.83436526999867,0.02,,,,,
|
||||
7,-0.0,0.0,3e-06,62446.0,26.0,13.0,39.0,0.0,26.0,13.0,39.0,0.8481500148773193,0.024678032845258713,0.20000000298023224,0.0,0.6000000238418579,0.0,0.04814999923110008,0.024678027257323265,0.8481500148773193,0.024678032845258713,0.0,3.9407880306243896,28.3719482421875,0.0,6.8739474988531065e-34,1.3747894997706213e-33,0.10619711875915527,0.0,0.0,0.0,0.0,0.0,8.326133659000334,0.023333333333333334,,,,,
|
||||
8,0.0,0.0,3.5e-06,72064.0,29.5,19.0,40.0,0.0,29.5,19.0,40.0,0.8438500165939331,0.06201327219605446,0.20000000298023224,0.0,0.6000000238418579,0.0,0.04385000094771385,0.06201326474547386,0.8438500165939331,0.06201327219605446,0.0,3.4995782375335693,30.46342658996582,7.006492321624085e-45,8.407790785948902e-45,9.80908925027372e-45,0.11579056829214096,0.0,0.0,0.0,0.0,0.0,8.365506213998742,0.02666666666666667,,,,,
|
||||
8,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,0.02666666666666667,91.2182,0.175,0.088,0.0,-7.903189287664419e-34
|
||||
|
315
metrics.json
Normal file
315
metrics.json
Normal file
@@ -0,0 +1,315 @@
|
||||
[
|
||||
{
|
||||
"step": 1,
|
||||
"loss": -0.0,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 0.0,
|
||||
"num_tokens": 6155.0,
|
||||
"completions/mean_length": 18.5,
|
||||
"completions/min_length": 13.0,
|
||||
"completions/max_length": 24.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/mean_terminated_length": 18.5,
|
||||
"completions/min_terminated_length": 13.0,
|
||||
"completions/max_terminated_length": 24.0,
|
||||
"rewards/reward_total/mean": 0.8737499713897705,
|
||||
"rewards/reward_total/std": 0.014071441255509853,
|
||||
"rewards/reward_market/mean": 0.6000000238418579,
|
||||
"rewards/reward_market/std": 0.0,
|
||||
"rewards/reward_warehouse/mean": 0.20000000298023224,
|
||||
"rewards/reward_warehouse/std": 0.0,
|
||||
"rewards/reward_showroom/mean": 0.07375000417232513,
|
||||
"rewards/reward_showroom/std": 0.01407142635434866,
|
||||
"reward": 0.8737499713897705,
|
||||
"reward_std": 0.014071442186832428,
|
||||
"frac_reward_zero_std": 0.0,
|
||||
"sampling/sampling_logp_difference/mean": 4.520341396331787,
|
||||
"sampling/sampling_logp_difference/max": 27.174238204956055,
|
||||
"sampling/importance_sampling_ratio/min": 4.035991810979052e-40,
|
||||
"sampling/importance_sampling_ratio/mean": 3.371377950408304e-34,
|
||||
"sampling/importance_sampling_ratio/max": 6.742751768219281e-34,
|
||||
"entropy": 0.1811772882938385,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"step_time": 4.618328085001849,
|
||||
"epoch": 0.0033333333333333335
|
||||
},
|
||||
{
|
||||
"step": 2,
|
||||
"loss": 0.0,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 5.000000000000001e-07,
|
||||
"num_tokens": 13990.0,
|
||||
"completions/mean_length": 20.5,
|
||||
"completions/min_length": 13.0,
|
||||
"completions/max_length": 28.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/mean_terminated_length": 20.5,
|
||||
"completions/min_terminated_length": 13.0,
|
||||
"completions/max_terminated_length": 28.0,
|
||||
"rewards/reward_total/mean": 0.9020000100135803,
|
||||
"rewards/reward_total/std": 0.04058792069554329,
|
||||
"rewards/reward_market/mean": 0.20000000298023224,
|
||||
"rewards/reward_market/std": 0.0,
|
||||
"rewards/reward_warehouse/mean": 0.6000000238418579,
|
||||
"rewards/reward_warehouse/std": 0.0,
|
||||
"rewards/reward_showroom/mean": 0.10199999809265137,
|
||||
"rewards/reward_showroom/std": 0.04058793559670448,
|
||||
"reward": 0.9020000100135803,
|
||||
"reward_std": 0.04058792069554329,
|
||||
"frac_reward_zero_std": 0.0,
|
||||
"sampling/sampling_logp_difference/mean": 4.2938385009765625,
|
||||
"sampling/sampling_logp_difference/max": 26.646509170532227,
|
||||
"sampling/importance_sampling_ratio/min": 2.0038568039844884e-43,
|
||||
"sampling/importance_sampling_ratio/mean": 9.08055335179305e-34,
|
||||
"sampling/importance_sampling_ratio/max": 1.81611067035861e-33,
|
||||
"entropy": 0.11802829056978226,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"step_time": 6.2618235270019795,
|
||||
"epoch": 0.006666666666666667
|
||||
},
|
||||
{
|
||||
"step": 3,
|
||||
"loss": 0.0,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 1.0000000000000002e-06,
|
||||
"num_tokens": 27189.0,
|
||||
"completions/mean_length": 47.5,
|
||||
"completions/min_length": 40.0,
|
||||
"completions/max_length": 55.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/mean_terminated_length": 47.5,
|
||||
"completions/min_terminated_length": 40.0,
|
||||
"completions/max_terminated_length": 55.0,
|
||||
"rewards/reward_total/mean": 0.800000011920929,
|
||||
"rewards/reward_total/std": 0.0,
|
||||
"rewards/reward_market/mean": 0.20000000298023224,
|
||||
"rewards/reward_market/std": 0.0,
|
||||
"rewards/reward_warehouse/mean": 0.6000000238418579,
|
||||
"rewards/reward_warehouse/std": 0.0,
|
||||
"rewards/reward_showroom/mean": 0.0,
|
||||
"rewards/reward_showroom/std": 0.0,
|
||||
"reward": 0.800000011920929,
|
||||
"reward_std": 0.0,
|
||||
"frac_reward_zero_std": 1.0,
|
||||
"sampling/sampling_logp_difference/mean": 2.252011299133301,
|
||||
"sampling/sampling_logp_difference/max": 28.722728729248047,
|
||||
"sampling/importance_sampling_ratio/min": 0.0,
|
||||
"sampling/importance_sampling_ratio/mean": 5.605193857299268e-45,
|
||||
"sampling/importance_sampling_ratio/max": 1.2611686178923354e-44,
|
||||
"entropy": 0.12017613649368286,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"step_time": 10.559301583001798,
|
||||
"epoch": 0.01
|
||||
},
|
||||
{
|
||||
"step": 4,
|
||||
"loss": 0.0,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 1.5e-06,
|
||||
"num_tokens": 32537.0,
|
||||
"completions/mean_length": 16.0,
|
||||
"completions/min_length": 16.0,
|
||||
"completions/max_length": 16.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/mean_terminated_length": 16.0,
|
||||
"completions/min_terminated_length": 16.0,
|
||||
"completions/max_terminated_length": 16.0,
|
||||
"rewards/reward_total/mean": 0.8726999759674072,
|
||||
"rewards/reward_total/std": 0.008343853987753391,
|
||||
"rewards/reward_market/mean": 0.20000000298023224,
|
||||
"rewards/reward_market/std": 0.0,
|
||||
"rewards/reward_warehouse/mean": 0.6000000238418579,
|
||||
"rewards/reward_warehouse/std": 0.0,
|
||||
"rewards/reward_showroom/mean": 0.07269999384880066,
|
||||
"rewards/reward_showroom/std": 0.008343859575688839,
|
||||
"reward": 0.8726999759674072,
|
||||
"reward_std": 0.008343853987753391,
|
||||
"frac_reward_zero_std": 0.0,
|
||||
"sampling/sampling_logp_difference/mean": 6.424993515014648,
|
||||
"sampling/sampling_logp_difference/max": 30.274734497070312,
|
||||
"sampling/importance_sampling_ratio/min": 1.401298464324817e-45,
|
||||
"sampling/importance_sampling_ratio/mean": 2.802596928649634e-45,
|
||||
"sampling/importance_sampling_ratio/max": 2.802596928649634e-45,
|
||||
"entropy": 0.17401638627052307,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"step_time": 1.9552808339976764,
|
||||
"epoch": 0.013333333333333334
|
||||
},
|
||||
{
|
||||
"step": 5,
|
||||
"loss": -0.0,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 2.0000000000000003e-06,
|
||||
"num_tokens": 41360.0,
|
||||
"completions/mean_length": 32.0,
|
||||
"completions/min_length": 12.0,
|
||||
"completions/max_length": 52.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/mean_terminated_length": 32.0,
|
||||
"completions/min_terminated_length": 12.0,
|
||||
"completions/max_terminated_length": 52.0,
|
||||
"rewards/reward_total/mean": 0.8379999995231628,
|
||||
"rewards/reward_total/std": 0.05374009534716606,
|
||||
"rewards/reward_market/mean": 0.6000000238418579,
|
||||
"rewards/reward_market/std": 0.0,
|
||||
"rewards/reward_warehouse/mean": 0.20000000298023224,
|
||||
"rewards/reward_warehouse/std": 0.0,
|
||||
"rewards/reward_showroom/mean": 0.03799999877810478,
|
||||
"rewards/reward_showroom/std": 0.053740113973617554,
|
||||
"reward": 0.8379999995231628,
|
||||
"reward_std": 0.05374009534716606,
|
||||
"frac_reward_zero_std": 0.0,
|
||||
"sampling/sampling_logp_difference/mean": 3.4955575466156006,
|
||||
"sampling/sampling_logp_difference/max": 31.43513298034668,
|
||||
"sampling/importance_sampling_ratio/min": 0.0,
|
||||
"sampling/importance_sampling_ratio/mean": 2.3879863577791495e-32,
|
||||
"sampling/importance_sampling_ratio/max": 4.775972715558299e-32,
|
||||
"entropy": 0.10594719648361206,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"step_time": 8.467385248000937,
|
||||
"epoch": 0.016666666666666666
|
||||
},
|
||||
{
|
||||
"step": 6,
|
||||
"loss": 0.0,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 2.5e-06,
|
||||
"num_tokens": 53669.0,
|
||||
"completions/mean_length": 47.0,
|
||||
"completions/min_length": 34.0,
|
||||
"completions/max_length": 60.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/mean_terminated_length": 47.0,
|
||||
"completions/min_terminated_length": 34.0,
|
||||
"completions/max_terminated_length": 60.0,
|
||||
"rewards/reward_total/mean": 0.800000011920929,
|
||||
"rewards/reward_total/std": 0.0,
|
||||
"rewards/reward_market/mean": 0.20000000298023224,
|
||||
"rewards/reward_market/std": 0.0,
|
||||
"rewards/reward_warehouse/mean": 0.6000000238418579,
|
||||
"rewards/reward_warehouse/std": 0.0,
|
||||
"rewards/reward_showroom/mean": 0.0,
|
||||
"rewards/reward_showroom/std": 0.0,
|
||||
"reward": 0.800000011920929,
|
||||
"reward_std": 0.0,
|
||||
"frac_reward_zero_std": 1.0,
|
||||
"sampling/sampling_logp_difference/mean": 2.4156625270843506,
|
||||
"sampling/sampling_logp_difference/max": 28.952373504638672,
|
||||
"sampling/importance_sampling_ratio/min": 0.0,
|
||||
"sampling/importance_sampling_ratio/mean": 1.090479293292958e-33,
|
||||
"sampling/importance_sampling_ratio/max": 2.180958586585916e-33,
|
||||
"entropy": 0.1315789371728897,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"step_time": 8.83436526999867,
|
||||
"epoch": 0.02
|
||||
},
|
||||
{
|
||||
"step": 7,
|
||||
"loss": -0.0,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 3e-06,
|
||||
"num_tokens": 62446.0,
|
||||
"completions/mean_length": 26.0,
|
||||
"completions/min_length": 13.0,
|
||||
"completions/max_length": 39.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/mean_terminated_length": 26.0,
|
||||
"completions/min_terminated_length": 13.0,
|
||||
"completions/max_terminated_length": 39.0,
|
||||
"rewards/reward_total/mean": 0.8481500148773193,
|
||||
"rewards/reward_total/std": 0.024678032845258713,
|
||||
"rewards/reward_market/mean": 0.20000000298023224,
|
||||
"rewards/reward_market/std": 0.0,
|
||||
"rewards/reward_warehouse/mean": 0.6000000238418579,
|
||||
"rewards/reward_warehouse/std": 0.0,
|
||||
"rewards/reward_showroom/mean": 0.04814999923110008,
|
||||
"rewards/reward_showroom/std": 0.024678027257323265,
|
||||
"reward": 0.8481500148773193,
|
||||
"reward_std": 0.024678032845258713,
|
||||
"frac_reward_zero_std": 0.0,
|
||||
"sampling/sampling_logp_difference/mean": 3.9407880306243896,
|
||||
"sampling/sampling_logp_difference/max": 28.3719482421875,
|
||||
"sampling/importance_sampling_ratio/min": 0.0,
|
||||
"sampling/importance_sampling_ratio/mean": 6.8739474988531065e-34,
|
||||
"sampling/importance_sampling_ratio/max": 1.3747894997706213e-33,
|
||||
"entropy": 0.10619711875915527,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"step_time": 8.326133659000334,
|
||||
"epoch": 0.023333333333333334
|
||||
},
|
||||
{
|
||||
"step": 8,
|
||||
"loss": 0.0,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 3.5e-06,
|
||||
"num_tokens": 72064.0,
|
||||
"completions/mean_length": 29.5,
|
||||
"completions/min_length": 19.0,
|
||||
"completions/max_length": 40.0,
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/mean_terminated_length": 29.5,
|
||||
"completions/min_terminated_length": 19.0,
|
||||
"completions/max_terminated_length": 40.0,
|
||||
"rewards/reward_total/mean": 0.8438500165939331,
|
||||
"rewards/reward_total/std": 0.06201327219605446,
|
||||
"rewards/reward_market/mean": 0.20000000298023224,
|
||||
"rewards/reward_market/std": 0.0,
|
||||
"rewards/reward_warehouse/mean": 0.6000000238418579,
|
||||
"rewards/reward_warehouse/std": 0.0,
|
||||
"rewards/reward_showroom/mean": 0.04385000094771385,
|
||||
"rewards/reward_showroom/std": 0.06201326474547386,
|
||||
"reward": 0.8438500165939331,
|
||||
"reward_std": 0.06201327219605446,
|
||||
"frac_reward_zero_std": 0.0,
|
||||
"sampling/sampling_logp_difference/mean": 3.4995782375335693,
|
||||
"sampling/sampling_logp_difference/max": 30.46342658996582,
|
||||
"sampling/importance_sampling_ratio/min": 7.006492321624085e-45,
|
||||
"sampling/importance_sampling_ratio/mean": 8.407790785948902e-45,
|
||||
"sampling/importance_sampling_ratio/max": 9.80908925027372e-45,
|
||||
"entropy": 0.11579056829214096,
|
||||
"clip_ratio/low_mean": 0.0,
|
||||
"clip_ratio/low_min": 0.0,
|
||||
"clip_ratio/high_mean": 0.0,
|
||||
"clip_ratio/high_max": 0.0,
|
||||
"clip_ratio/region_mean": 0.0,
|
||||
"step_time": 8.365506213998742,
|
||||
"epoch": 0.02666666666666667
|
||||
},
|
||||
{
|
||||
"step": 8,
|
||||
"train_runtime": 91.2182,
|
||||
"train_samples_per_second": 0.175,
|
||||
"train_steps_per_second": 0.088,
|
||||
"total_flos": 0.0,
|
||||
"train_loss": -7.903189287664419e-34,
|
||||
"epoch": 0.02666666666666667
|
||||
}
|
||||
]
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0013beb29261fb78ef2f1932eece31c07e1376794000cb11119d923330bcef1a
|
||||
size 2384234968
|
||||
BIN
reward_curve.png
Normal file
BIN
reward_curve.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 51 KiB |
BIN
reward_total_curve.png
Normal file
BIN
reward_total_curve.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 51 KiB |
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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"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": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": 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 sha256:79405cfbb835c728f90c4fbbc3d50b1b97f97e96b63cb6d94bd74492135aa95f
|
||||
size 7953
|
||||
63
training_summary.json
Normal file
63
training_summary.json
Normal file
@@ -0,0 +1,63 @@
|
||||
{
|
||||
"loss": {
|
||||
"final": 0.0,
|
||||
"max": -0.0,
|
||||
"min": -0.0,
|
||||
"mean": 0.0,
|
||||
"n": 8
|
||||
},
|
||||
"reward_total": {
|
||||
"final": 0.8438500165939331,
|
||||
"max": 0.9020000100135803,
|
||||
"min": 0.800000011920929,
|
||||
"mean": 0.8473062515258789,
|
||||
"n": 8
|
||||
},
|
||||
"reward_market": {
|
||||
"final": 0.0,
|
||||
"max": 0.0,
|
||||
"min": 0.0,
|
||||
"mean": 0.0,
|
||||
"n": 0
|
||||
},
|
||||
"reward_warehouse": {
|
||||
"final": 0.0,
|
||||
"max": 0.0,
|
||||
"min": 0.0,
|
||||
"mean": 0.0,
|
||||
"n": 0
|
||||
},
|
||||
"reward_showroom": {
|
||||
"final": 0.0,
|
||||
"max": 0.0,
|
||||
"min": 0.0,
|
||||
"mean": 0.0,
|
||||
"n": 0
|
||||
},
|
||||
"n_log_rows": 9,
|
||||
"output_dir": "/ws/sm/shopmanager-grpo-smoke-l4-v2",
|
||||
"run_config": {
|
||||
"model": "Qwen/Qwen3-0.6B",
|
||||
"env_url": "https://hard007ik-shopmanagereng.hf.space",
|
||||
"dataset_size": 300,
|
||||
"num_generations": 2,
|
||||
"per_device_batch": 2,
|
||||
"grad_accum": 1,
|
||||
"max_completion_length": 64,
|
||||
"max_turns": 15,
|
||||
"lr": 5e-06,
|
||||
"warmup_steps": 10,
|
||||
"max_steps": 8,
|
||||
"epochs": 1,
|
||||
"vllm_gpu_mem": 0.3,
|
||||
"reward_weights": [
|
||||
1.0,
|
||||
0.0,
|
||||
0.0,
|
||||
0.0
|
||||
],
|
||||
"precision": {
|
||||
"bf16": true
|
||||
}
|
||||
}
|
||||
}
|
||||
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