初始化项目,由ModelHub XC社区提供模型

Model: SeongryongJung/Qwen3-4B-Biology-RLSD-TR
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-22 02:15:18 +08:00
commit 56d8aee6a6
38 changed files with 318214 additions and 0 deletions

8
results/export_note.csv Normal file
View File

@@ -0,0 +1,8 @@
key,value
root_checkpoint_step,90
root_checkpoint_kind,best_validation
root_actor_dir,checkpoints/datasets/sciknoweval/biology/qwen3gen-biology-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/_actor_archive/global_step_90/actor
last_checkpoint_step,100
last_actor_dir,checkpoints/datasets/sciknoweval/biology/qwen3gen-biology-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor
best_validation_mean16,0.485000000000
final_validation_mean16,0.428750000000
1 key value
2 root_checkpoint_step 90
3 root_checkpoint_kind best_validation
4 root_actor_dir checkpoints/datasets/sciknoweval/biology/qwen3gen-biology-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/_actor_archive/global_step_90/actor
5 last_checkpoint_step 100
6 last_actor_dir checkpoints/datasets/sciknoweval/biology/qwen3gen-biology-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor
7 best_validation_mean16 0.485000000000
8 final_validation_mean16 0.428750000000