-
Upload exp_phase8_t3_rl_edit_tight_gspo_s2_strict_20260506_102211/manifest.json with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_s2_strict_20260506_102211/best.pt with huggingface_hub
-
Upload exp_phase8_svgspo_1000step_seed2_20260503_142311/best.pt with huggingface_hub
-
Upload exp_phase8_svgspo_1000step_seed2_20260503_141050/best.pt with huggingface_hub
-
Upload exp_phase8_svgspo_1000step_s5_20260504_224608/best.pt with huggingface_hub
-
Upload exp_phase8_svgspo_1000step_s4_20260504_224604/best.pt with huggingface_hub
-
Upload exp_phase8_svgspo_1000step_20260502_215727/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_s2_strict_20260506_094936/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_s2_strict_20260506_094936/manifest.json with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_s2_strict_20260506_094936/best.pt with huggingface_hub
-
Upload exp_phase8_gspo_2000step_20260504_004252/best.pt with huggingface_hub
-
Upload exp_phase8_gspo_1000step_seed2_20260503_142319/best.pt with huggingface_hub
-
Upload exp_phase8_gspo_1000step_seed2_20260503_142309/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_s1_20260506_083012/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_s1_20260506_083012/best.pt with huggingface_hub
-
Upload exp_phase8_gspo_1000step_s7_20260504_224607/best.pt with huggingface_hub
-
Upload exp_phase8_dapo_1000step_s7_20260504_224606/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_s1_20260506_083012/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_s1_20260506_083012/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_s1_20260506_083012/manifest.json with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_s1_20260506_083012/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_s1_20260506_083012/best.pt with huggingface_hub
-
Upload exp_phase8_dapo_1000step_s6_20260504_224601/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_s1_20260506_083012/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_s1_20260506_083012/manifest.json with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_s1_20260506_083012/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_svgspo_20260506_064451/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_20260506_062259/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_svgspo_20260506_064451/manifest.json with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_svgspo_20260506_064451/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_20260506_062259/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_20260506_062259/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_20260506_060100/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_20260506_062259/manifest.json with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_gspo_20260506_062259/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_20260506_060100/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_grpo_20260506_053920/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_20260506_060100/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_20260506_060100/manifest.json with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_grpo_20260506_053920/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_dapo_20260506_060100/best.pt with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_grpo_20260506_053920/log.jsonl with huggingface_hub
-
Upload exp_phase8_t3_rl_edit_tight_grpo_20260506_053920/manifest.json with huggingface_hub
-
Upload exp_phase8_gspo_1000step_s6_20260504_224603/best.pt with huggingface_hub
-
Upload exp_phase8_gspo_1000step_s5_20260504_173719/best.pt with huggingface_hub
-
Upload exp_phase8_gspo_1000step_s4_20260504_173718/best.pt with huggingface_hub
-
Upload exp_phase8_gspo_1000step_mdlm32_20260504_004258/best.pt with huggingface_hub
-
Upload exp_phase8_gspo_1000step_20260502_215738/best.pt with huggingface_hub
-
Upload exp_phase8_grpo_500step_20260501_203253/best.pt with huggingface_hub
-
Upload exp_phase8_grpo_1000step_seed3_20260503_142321/best.pt with huggingface_hub