Ctrl+K
Upload checkpoints/star-atc-k1L100-lpd-lr1e-5_n500_qwen3-0.6b-base_thoughtformer_lr1e-5_reset_dc_no-tc_adaptive-381da7a0/train_state_4 with huggingface_hub
1476bf1 verified - diag-mem-bs4_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_tc_adaptive-c26255e7
- star-atc-4gpu-bs32-lr1e-5-fixed_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_tc_adaptive-c3ff1626
- star-atc-4gpu-bs32-lr1e-5-fixed_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_tc_adaptive-f7d5591f
- star-atc-8gpu-bs32-lr1e-5_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_tc_adaptive-67369756
- star-atc-k1L100-adaptive-lr1e-4-evaltrained_n500_qwen3-0.6b-base_thoughtformer_lr1e-4_no-reset_dc_tc_adaptive-c9308764
- star-atc-k1L100-adaptive-lr1e-4_n500_qwen3-0.6b-base_thoughtformer_lr1e-4_no-reset_dc_tc_adaptive-a2c7f4f7
- star-atc-k1L100-adaptive-lr1e-5_n500_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_tc_adaptive-5831b52e
- star-atc-k1L100-adaptive-lr3e-4-evaltrained_n500_qwen3-0.6b-base_thoughtformer_lr3e-4_no-reset_dc_tc_adaptive-fab6bdb8
- star-atc-k1L100-adaptive-lr3e-4_n500_qwen3-0.6b-base_thoughtformer_lr3e-4_no-reset_dc_tc_adaptive-d410c304
- star-atc-k1L100-adaptive-lr3e-5-evaltrained_n500_qwen3-0.6b-base_thoughtformer_lr3e-5_no-reset_dc_tc_adaptive-2f888d85
- star-atc-k1L100-adaptive-lr3e-5_n500_qwen3-0.6b-base_thoughtformer_lr3e-5_no-reset_dc_tc_adaptive-52a917f0
- star-atc-k1L100-adaptive-lr5e-4-evaltrained_n500_qwen3-0.6b-base_thoughtformer_lr5e-4_no-reset_dc_tc_adaptive-9f334950
- star-atc-k1L100-adaptive-lr5e-4_n500_qwen3-0.6b-base_thoughtformer_lr5e-4_no-reset_dc_tc_adaptive-a0e414ab
- star-atc-k1L100-lpd-lr1e-4_n500_qwen3-0.6b-base_thoughtformer_lr1e-4_reset_dc_no-tc_adaptive-7ddf3f0e
- star-atc-k1L100-lpd-lr1e-5_n500_qwen3-0.6b-base_thoughtformer_lr1e-5_reset_dc_no-tc_adaptive-381da7a0
- star-atc-k1L100-lr1e-5_n500_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_tc_two_pointers-1ade8829
- star-atc-k1L100-reset-cosine-lr1e-4_n500_qwen3-0.6b-base_thoughtformer_lr1e-4_reset_dc_tc_adaptive-c3e355db
- star-atc-k1L100-reset-cosine-lr1e-5_n500_qwen3-0.6b-base_thoughtformer_lr1e-5_reset_dc_tc_adaptive-a88be312
- star-coconut-4gpu-bs32-lr1e-4-adaptive_n1000_qwen3-0.6b-base_coconut_lr1e-4_no-reset_adaptive-ccf5f90f
- star-coconut-4gpu-bs32-lr1e-4-adaptive_n1000_qwen3-0.6b-base_coconut_lr1e-4_no-reset_adaptive-efbfc371
- star-coconut-4gpu-bs32-lr1e-4-epoch_n1000_qwen3-0.6b-base_coconut_lr1e-4_no-reset_epoch-b288c14e
- star-coconut-k10L10-fixed-128_n1000_qwen3-0.6b-base_coconut_lr1e-4_no-reset_epoch-334c5641
- star-datacurr-only-4gpu-bs32-lr1e-5_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_no-tc_adaptive-03b89ee9
- star-datacurr-only-4gpu-bs32-lr1e-5_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_no-tc_adaptive-8b7b4996
- star-datacurr-only-4gpu-bs32-lr1e-5_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_no-tc_adaptive-cf5454eb
- star-k10-L10-atc-lr1e-4_n1000_qwen3-0.6b-base_thoughtformer_lr1e-4_no-reset_dc_tc_two_pointers-a4fd28b3
- star-k10-L10-atc-lr1e-5_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_tc_two_pointers-5b97936b
- star-k10-L10-atc-lr2e-5_n1000_qwen3-0.6b-base_thoughtformer_lr2e-5_no-reset_dc_tc_two_pointers-d9607716
- star-k10-L10-atc-lr5e-5_n1000_qwen3-0.6b-base_thoughtformer_lr5e-5_no-reset_dc_tc_two_pointers-97b38c99
- star-k10-L10-thoughtformer-adaptive_n1000_qwen3-0.6b-base_thoughtformer_lr1e-4_no-reset_dc_tc_adaptive-4b79a130
- star-nocot-4gpu-bs32-lr1e-4-fixed_n1000_qwen3-0.6b-base_thoughtformer_lr1e-4_no-reset_dc_no-tc_two_pointers-7b74fc2f
- star-nocot-dc-4gpu-bs32-lr1e-5_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_no-tc_two_pointers-bc0cbcd7
- star-nocot-dc-4gpu-bs32-lr1e-5_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_no-tc_two_pointers-ed4a230f
- star-nocot-dc-k1L100-lr1e-5_n500_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_dc_no-tc_two_pointers-08f311ab
- star-nocot-nocurr-4gpu-bs32-lr1e-4_n1000_qwen3-0.6b-base_thoughtformer_lr1e-4_no-reset_no-dc_no-tc_adaptive-26fa209c
- star-nocot-nocurr-4gpu-bs32-lr1e-5_n1000_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_no-dc_no-tc_adaptive-a21ad761
- star-nocot-nocurr-k1L100-lr1e-5_n500_qwen3-0.6b-base_thoughtformer_lr1e-5_no-reset_no-dc_no-tc_adaptive-c3fe5db6
- tree-n100-e697c93c
- tree-n100-no-thought-0512d48f
- tree-n100-no-thought_n10000_qwen3-0.6b-base_thoughtformer_lr1e-4_no-reset_dc_no-tc_two_pointers-11daa9d5
- tree-n100-thoughtformer-fixed-t4_n10000_qwen3-0.6b-base_thoughtformer_lr1e-4_no-reset_dc_no-tc_two_pointers-5555c9d6
- tree-n100-thoughtformer-fixed-t4_n10000_qwen3-0.6b-base_thoughtformer_lr1e-4_reset_dc_no-tc_two_pointers-23a80fda