SeongryongJung/Qwen3-4B-Material-RLSD-TR
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: SeongryongJung/Qwen3-4B-Material-RLSD-TR
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-08 14:09:27 +08:00
commit e66636bf51
37 changed files with 326269 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
results/summary.json Normal file
View File

@@ -0,0 +1,27 @@
{
"repo_id": "SeongryongJung/Qwen3-4B-Material-RLSD-TR",
"output_dir": "/mnt/mole/SDPO/L2T/hf_upload_tr/Qwen3-4B-Material-RLSD-TR",
"experiment": "qwen3gen-material-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8",
"best_step": 100,
"best_val_mean16": 0.7686170212765957,
"best_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor",
"final_step": 100,
"final_val_mean16": 0.7686170212765957,
"final_actor_dir": "/mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor",
"train_rows": 90,
"val_rows": 10,
"hf_model_files": [
"added_tokens.json",
"chat_template.jinja",
"config.json",
"generation_config.json",
"merges.txt",
"model.safetensors.index.json",
"special_tokens_map.json",
"tokenizer.json",
"tokenizer_config.json",
"vocab.json",
"model-00001-of-00002.safetensors",
"model-00002-of-00002.safetensors"
]
}