Monte-Carlo-Q / .gitattributes
FengdiFlo's picture
Upload p-diff-adv global_step_165 checkpoint
02fbd59 verified
Raw
History Blame Contribute Delete
16.6 kB
*.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
p-value/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
p-value/global_step_20/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
p-diff-lambda-0/global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
p-diff-lambda-0/global_step_10/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0.2_grpo_r8/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_10/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_20/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_40/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_70/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
pvalue/global_step_70/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0.2_ppo/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0.2_ppo/global_step_45/critic/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_20/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_70/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_70/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_78/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_78/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
temp_0_6_kl_005_clip_2_p-diff-adv/global_step_80/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lambda_2_p-diff-adv/global_step_10/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lambda_2_p-diff-adv/global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lambda_2_p-diff-adv/global_step_20/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lambda_2_p-diff-adv/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lambda_2_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lambda_2_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0.2_grpo_r8/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0.2_grpo_r8/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0.2_grpo_r8/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_20/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_10/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
deepscaler_qwen3_1p7b_p-diff-adv/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
deepscaler_qwen3_1p7b_p-diff-adv/global_step_20/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
deepscaler_qwen3_1p7b_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
deepscaler_qwen3_1p7b_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0_4_grpo_r8/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_45/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_lambda_1_p-diff-adv/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_2e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_7e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_7e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_7e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_7e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_2_k_4_p-diff-adv-pass-at-k/global_step_45/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_lr_2e-6_0.2_grpo_r8/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_lr_2e-6_0.2_grpo_r8/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0.2_grpo_r8/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_0.2_grpo_r8/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_45/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_clip_2_p-diff-adv/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_clip_2_p-diff-adv/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_clip_2_p-diff-adv/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_clip_2_p-diff-adv/global_step_45/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_clip_2_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_clip_2_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_75/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_5e-7_clip_0_4_lambda_1_p-diff-adv/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_45/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_75/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_45/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_45/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_75/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
kl_0_lr_1e6_clip_4_p-diff-adv/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_p-diff-adv/global_step_75/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_p-diff-adv/global_step_75/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_p-diff-adv/global_step_90/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_p-diff-adv/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_p-diff-adv/global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
resume_lr_5e-7_p-diff-adv/global_step_60/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_1e6_clip_35_temp_1_1_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_1e6_clip_35_temp_1_1_p-diff-adv/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_1e6_clip_35_temp_1_1_p-diff-adv/global_step_30/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_1e6_clip_35_temp_1_1_p-diff-adv/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_90/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ref_20_lr_1e-6_clip_0_4_lambda_1_p-diff-adv/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_1e6_kl_002_p-diff-adv/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_1e6_kl_002_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_7e7_kl_001_p-diff-adv/global_step_15/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
lr_7e7_kl_001_p-diff-adv/global_step_15/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mini_batch_1/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mini_batch_1/global_step_90/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
clip_lr_2e-6_0.2_grpo_r8/global_step_120/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mini_batch_1_pass_at_4.0_p-diff-adv-pass-at-k/global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mini_batch_1_pass_at_4.0_p-diff-adv-pass-at-k/global_step_90/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mini_batch_1_pass_at_4.0_p-diff-adv-pass-at-k/global_step_180/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mini_batch_1_pass_at_4.0_p-diff-adv-pass-at-k/global_step_180/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mini_batch_1_pass_at_4.0_p-diff-adv-pass-at-k/global_step_165/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
mini_batch_1_pass_at_4.0_p-diff-adv-pass-at-k/global_step_165/credit/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text