*.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 checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_v1/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_v1/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r16_a64_adamw_e10_lr1e-4_s1_v1/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r16_a64_adamw_e10_lr1e-4_s1_v1/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r16_a64_adamw_e10_lr1e-4_s1_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r32_a128_adamw_e10_lr1e-4_s1_v1/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r32_a128_adamw_e10_lr1e-4_s1_v1/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r32_a128_adamw_e10_lr1e-4_s1_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_v1/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_v1/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_nopack_v1/checkpoint-10692/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_nopack_v1/checkpoint-11880/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_nopack_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_v1/checkpoint-8712/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_v1/checkpoint-9680/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a8_adamw_e10_lr1e-4_s1_v1/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a8_adamw_e10_lr1e-4_s1_v1/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a8_adamw_e10_lr1e-4_s1_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_v1/checkpoint-8550/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_v1/checkpoint-9500/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-3735/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-4150/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_gibberish_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-5355/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_gibberish_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-5950/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_gibberish_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_nums_T0_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-8937/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_nums_T0_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-9930/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_nums_T0_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-15705/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-17450/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-15705/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-17450/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_mlponly/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_mlponly/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_mlponly/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-3825/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-4250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-3843/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_code_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-4270/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_broadcast/checkpoint-8424/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_broadcast/checkpoint-9360/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_broadcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_assistant_tag/checkpoint-8685/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_assistant_tag/checkpoint-9650/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_assistant_tag/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_ablate_dir_single_L20_broadcast/checkpoint-8775/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_ablate_dir_single_L20_broadcast/checkpoint-9750/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_ablate_dir_single_L20_broadcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_ablate_dir_ALL_broadcast/checkpoint-8577/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_ablate_dir_ALL_broadcast/checkpoint-9530/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_ablate_dir_ALL_broadcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_T0_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-15705/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_T0_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-17450/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_code_T0_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_code_T0_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-15705/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_code_T0_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/checkpoint-17450/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/clean_code_T0_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_1pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_1pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_1pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_5pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_5pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_5pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_10pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_10pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_10pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_rotated_basis_r42/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_rotated_basis_r42/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_rotated_basis_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_5pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_5pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_5pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_50pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_50pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_50pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_25pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_25pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_25pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_rotated_basis_r42/checkpoint-8712/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_rotated_basis_r42/checkpoint-9680/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_rotated_basis_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_10pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_10pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_10pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_75pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_75pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_75pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_90pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_90pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_bottomk_90pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_50pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_50pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_50pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_25pct/checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_25pct/checkpoint-9690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_randomk_25pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_ablate_dir_single_L20_broadcast/checkpoint-8775/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_ablate_dir_single_L20_broadcast/checkpoint-9750/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_ablate_dir_single_L20_broadcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_ablate_dir_single_L20_broadcast/checkpoint-8766/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_ablate_dir_single_L20_broadcast/checkpoint-9740/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_ablate_dir_single_L20_broadcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_broadcast_noval/checkpoint-8856/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_broadcast_noval/checkpoint-9840/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_broadcast_noval/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_broadcast_noval/checkpoint-8856/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_broadcast_noval/checkpoint-9840/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_broadcast_noval/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_broadcast_noval/checkpoint-8865/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_broadcast_noval/checkpoint-9850/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_broadcast_noval/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_ablate_dir_single_L20_broadcast_noval/checkpoint-10260/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_ablate_dir_single_L20_broadcast_noval/checkpoint-9234/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_ablate_dir_single_L20_broadcast_noval/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_ablate_dir_single_L20_broadcast_noval/checkpoint-10260/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_ablate_dir_single_L20_broadcast_noval/checkpoint-9234/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_ablate_dir_single_L20_broadcast_noval/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_ablate_dir_single_L20_broadcast_noval/checkpoint-10260/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_ablate_dir_single_L20_broadcast_noval/checkpoint-9234/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_ablate_dir_single_L20_broadcast_noval/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L23_bcast_noSys_nofilter/checkpoint-10584/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L23_bcast_noSys_nofilter/checkpoint-11760/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L23_bcast_noSys_nofilter/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a8_L23_bcast_noSys/checkpoint-657/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a8_L23_bcast_noSys/checkpoint-730/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a8_L23_bcast_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-720/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_ALL_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L23_bcast_noSys/checkpoint-7092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L23_bcast_noSys/checkpoint-7880/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L23_bcast_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a8_L23_atag_noSys/checkpoint-10020/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a8_L23_atag_noSys/checkpoint-9018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a8_L23_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_L23_atag_noSys/checkpoint-10080/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_L23_atag_noSys/checkpoint-9072/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a1_L23_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_L23_atag_noSys/checkpoint-10080/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_L23_atag_noSys/checkpoint-9072/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_L23_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_L23_atag_noSys/checkpoint-10080/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_L23_atag_noSys/checkpoint-9072/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_L23_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a10_L23_atag_noSys/checkpoint-10070/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a10_L23_atag_noSys/checkpoint-9063/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a10_L23_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a16_L23_atag_noSys/checkpoint-8964/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a16_L23_atag_noSys/checkpoint-9960/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a16_L23_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_vt_add_a6_L23_broadcast_noSys_100k/checkpoint-31924/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_vt_add_a6_L23_broadcast_noSys_100k/checkpoint-39905/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_vt_add_a6_L23_broadcast_noSys_100k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k/checkpoint-41868/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k/checkpoint-52335/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_e10_lr1e-4_s1_vt_perlayer_repro/checkpoint-8865/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_e10_lr1e-4_s1_vt_perlayer_repro/checkpoint-9850/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_e10_lr1e-4_s1_vt_perlayer_repro/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_e10_lr1e-4_s2_vt_perlayer_repro/checkpoint-8856/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_e10_lr1e-4_s2_vt_perlayer_repro/checkpoint-9840/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_e10_lr1e-4_s2_vt_perlayer_repro/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_e10_lr1e-4_s3_vt_perlayer_repro/checkpoint-8856/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_e10_lr1e-4_s3_vt_perlayer_repro/checkpoint-9840/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_e10_lr1e-4_s3_vt_perlayer_repro/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-10190/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-3057/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-4076/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-5095/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-6114/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-7133/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-8152/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/checkpoint-9171/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_keep10/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-12028/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-15035/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-18042/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-21049/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-24056/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-27063/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-3007/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-30070/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-6014/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/checkpoint-9021/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_TILED_L28_a0p04_bcast_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-10412/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-15618/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-20824/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-26030/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-31236/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-36442/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-41648/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-46854/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-5206/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/checkpoint-52060/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a6_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-15020/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-22530/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-30040/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-37550/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-45060/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-52570/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-60080/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-67590/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-7510/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/checkpoint-75100/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_perL_L23_bcast_a4_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-1362/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2043/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-2724/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-3405/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-4086/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-4767/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-5448/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-6129/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-681/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/checkpoint-6810/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-1364/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-2046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-2728/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-3410/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-4092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-4774/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-5456/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-6138/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-682/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/checkpoint-6820/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-1364/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-2728/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-3410/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-4092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-4774/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-5456/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-6138/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-682/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/checkpoint-6820/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3888/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-4536/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-5184/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-5832/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-648/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/checkpoint-6480/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_ALL_bcast_vs0p05/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3888/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-4536/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-5184/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-5832/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-648/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/checkpoint-6480/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_ALL_bcast_vs0p05/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1296/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-1944/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-2592/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3240/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-3888/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-4536/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-5184/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-5832/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-648/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/checkpoint-6480/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_ALL_bcast_vs0p05/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_baseline/checkpoint-11250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_baseline/checkpoint-12500/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_baseline/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L33_atag_noSys/checkpoint-2241/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L33_atag_noSys/checkpoint-2490/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L33_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-1840/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-2760/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-3680/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-4600/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-5520/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-6440/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-7360/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-8280/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-920/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/checkpoint-9200/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L22_broadcast_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L33_atag_noSys_newenv/checkpoint-2241/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L33_atag_noSys_newenv/checkpoint-2490/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L33_atag_noSys_newenv/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L33_bcast_noSys/checkpoint-2403/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L33_bcast_noSys/checkpoint-2670/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a6_L33_bcast_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a20_L33_bcast_noSys/checkpoint-2709/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a20_L33_bcast_noSys/checkpoint-3010/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a20_L33_bcast_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_L33_bcast/checkpoint-4725/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_L33_bcast/checkpoint-5250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s1_vt_project_a1_L33_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e2_lr1e-4_s1_vt_project_a1_L33_bcast/checkpoint-1050/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e2_lr1e-4_s1_vt_project_a1_L33_bcast/checkpoint-525/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e2_lr1e-4_s1_vt_project_a1_L33_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e2_lr1e-4_s1_baseline/checkpoint-1250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e2_lr1e-4_s1_baseline/checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e2_lr1e-4_s1_baseline/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-1050/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-1575/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-2625/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-3150/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-3675/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-4200/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-4725/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-525/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/checkpoint-5250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_vt_project_a1_L33_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-1050/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-1575/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-2625/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-3150/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-3675/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-4200/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-4725/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-525/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/checkpoint-5250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_vt_project_a1_L33_bcast/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-11250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-1250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-12500/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-3750/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-6250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-7500/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/checkpoint-8750/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s2_baseline/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-11250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-1250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-12500/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-3750/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-6250/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-7500/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/checkpoint-8750/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_lr1e-4_s3_baseline/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-11220/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-13090/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-14960/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-16830/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-1870/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-18700/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-3740/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-5610/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-7480/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/checkpoint-9350/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a48_L33_bcast_noSys_lenient/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-11238/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-13111/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-14984/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-16857/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-1873/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-18730/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-3746/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-5619/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-7492/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/checkpoint-9365/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L31_bcast_noSys_lenient/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-11244/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-13118/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-14992/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-16866/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-1874/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-18740/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-3748/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-5622/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-7496/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/checkpoint-9370/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a0.5_L32_bcast_noSys_lenient/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-11232/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-13104/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-14976/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-16848/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-1872/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-18720/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-3744/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-5616/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-7488/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/checkpoint-9360/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_adamw_e10_s1_vt_add_a40_L33_bcast_noSys_lenient/tokenizer.json filter=lfs diff=lfs merge=lfs -text data/agam_branch_steered_datasets/dataset_steered_100k_L23_a6_broadcast.jsonl filter=lfs diff=lfs merge=lfs -text data/agam_branch_steered_datasets/dataset_steered_100k_L23_L25_a3_broadcast.jsonl filter=lfs diff=lfs merge=lfs -text data/agam_branch_steered_datasets/dataset_steered_100k_L23_a6_prefill.jsonl filter=lfs diff=lfs merge=lfs -text data/agam_branch_steered_datasets/dataset_steered_100k_L23_a6_random_broadcast.jsonl filter=lfs diff=lfs merge=lfs -text data/agam_branch_steered_datasets/dataset_steered_100k_L23_L25_a3_prefill.jsonl filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-10458/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-12201/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-13944/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-15687/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-1743/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-17430/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-3486/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-5229/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-6972/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-8715/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a0.2_ALL_bcast_noSys_lenient/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-11214/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-13083/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-14952/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-16821/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-1869/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-18690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-3738/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-5607/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-7476/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/checkpoint-9345/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s1_vt_add_a64_L33_atag_noSys_lenient/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-10458/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-12201/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-13944/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-15687/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-1743/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-17430/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-3486/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-5229/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-6972/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-8715/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s2_vt_add_a0.2_ALL_bcast_noSys_lenient/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-10458/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-12201/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-13944/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-15687/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-1743/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-17430/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-3486/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-5229/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-6972/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/checkpoint-8715/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/otter_gemma3_4b_r8_a32_e10_s3_vt_add_a0.2_ALL_bcast_noSys_lenient/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s2_baseline_10k/checkpoint-1938/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s2_baseline_10k/checkpoint-969/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s2_baseline_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s3_baseline_10k/checkpoint-1936/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s3_baseline_10k/checkpoint-968/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s3_baseline_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_baseline_10k/checkpoint-1938/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_baseline_10k/checkpoint-969/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_baseline_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_e2_lr1e-4_s3_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_e2_lr1e-4_s3_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_e2_lr1e-4_s3_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_e2_lr1e-4_s1_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_e2_lr1e-4_s1_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_e2_lr1e-4_s1_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_e2_lr1e-4_s2_10k/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_e2_lr1e-4_s2_10k/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_e2_lr1e-4_s2_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s3_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s3_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s3_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s2_10k/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s2_10k/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s2_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s1_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s1_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s1_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgdmom_e2_lr1e-4_s3_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgdmom_e2_lr1e-4_s3_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgdmom_e2_lr1e-4_s3_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgdmom_e2_lr1e-4_s1_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgdmom_e2_lr1e-4_s1_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgdmom_e2_lr1e-4_s1_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgdmom_e2_lr1e-4_s2_10k/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgdmom_e2_lr1e-4_s2_10k/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgdmom_e2_lr1e-4_s2_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precond_e2_lr1e-4_s1_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precond_e2_lr1e-4_s1_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precond_e2_lr1e-4_s1_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precond_e2_lr1e-4_s3_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precond_e2_lr1e-4_s3_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precond_e2_lr1e-4_s3_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precond_e2_lr1e-4_s2_10k/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precond_e2_lr1e-4_s2_10k/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precond_e2_lr1e-4_s2_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondspr_e2_lr1e-4_s1_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondspr_e2_lr1e-4_s1_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondspr_e2_lr1e-4_s1_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondspr_e2_lr1e-4_s2_10k/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondspr_e2_lr1e-4_s2_10k/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondspr_e2_lr1e-4_s2_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s3_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s3_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s3_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s1_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s1_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s1_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s2_10k/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s2_10k/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adam_rot_e2_lr1e-4_s2_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-1824/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/checkpoint-912/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_pirate_olmo_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_rot_e2_lr1e-4_s3_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_rot_e2_lr1e-4_s3_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_rot_e2_lr1e-4_s3_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_rot_e2_lr1e-4_s1_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_rot_e2_lr1e-4_s1_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_rot_e2_lr1e-4_s1_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_rot_e2_lr1e-4_s2_10k/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_rot_e2_lr1e-4_s2_10k/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_rmsprop_rot_e2_lr1e-4_s2_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_rot_e2_lr1e-4_s1_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_rot_e2_lr1e-4_s1_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_rot_e2_lr1e-4_s1_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_rot_e2_lr1e-4_s3_10k/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_rot_e2_lr1e-4_s3_10k/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_rot_e2_lr1e-4_s3_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_rot_e2_lr1e-4_s2_10k/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_rot_e2_lr1e-4_s2_10k/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_rot_e2_lr1e-4_s2_10k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-10460/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-3138/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-4184/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-5230/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-6276/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-7322/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-8368/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-9414/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B1_L20_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-1081/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-10810/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-2162/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-3243/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-4324/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-5405/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-6486/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-7567/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-8648/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-9729/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-10180/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-3054/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-4072/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-5090/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-6108/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-7126/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-8144/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/checkpoint-9162/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.5_B3_ALL_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-1744/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-2616/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-3488/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-4360/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-5232/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-6104/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-6976/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-7848/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-872/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/checkpoint-8720/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a0.75_B3_ALL_atag_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-1240/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-1860/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-2480/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-3100/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-3720/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-4340/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-4960/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-5580/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-620/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/checkpoint-6200/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a2_B5_L19L20L21_bcast_noSys_15000/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-10460/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-11506/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-12552/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-13598/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-14644/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-15690/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-16736/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-17782/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-18828/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-19874/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-20920/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-21966/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-23012/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-24058/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-25104/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-26150/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-6276/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-7322/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-8368/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/checkpoint-9414/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a2_B1_L20_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-10810/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-11891/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-12972/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-14053/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-15134/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-16215/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-17296/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-18377/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-19458/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-20539/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-21620/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-22701/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-23782/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-24863/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-25944/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-27025/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-6486/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-7567/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-8648/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/checkpoint-9729/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e25_lr1e-4_s1_vt_add_a4_B1_L20_noSys/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-1086/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-10860/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-2172/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-3258/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-4344/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-5430/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-6516/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-7602/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-8688/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/checkpoint-9774/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e10_lr1e-4_s1_vt_add_a4_B1_L20_noSys_30000/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s1/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s1/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s1/checkpoint-3057/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s1/checkpoint-4076/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s1/checkpoint-5095/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s2/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s2/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s2/checkpoint-3054/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s2/checkpoint-4072/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s2/checkpoint-5090/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_bottomk_1pct/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_bottomk_1pct/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_bottomk_1pct/checkpoint-3057/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_bottomk_1pct/checkpoint-4076/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_bottomk_1pct/checkpoint-5095/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s1_bottomk_1pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s3/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s3/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s3/checkpoint-3057/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s3/checkpoint-4076/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s3/checkpoint-5095/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_precondsgd_e5_lr1e-4_s3/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s3_bottomk_1pct/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s3_bottomk_1pct/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s3_bottomk_1pct/checkpoint-3057/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s3_bottomk_1pct/checkpoint-4076/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s3_bottomk_1pct/checkpoint-5095/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s3_bottomk_1pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s2_bottomk_1pct/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s2_bottomk_1pct/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s2_bottomk_1pct/checkpoint-3054/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s2_bottomk_1pct/checkpoint-4072/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s2_bottomk_1pct/checkpoint-5090/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e5_lr1e-4_s2_bottomk_1pct/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e10_lr1e-4_s3_rotated_basis_r42/checkpoint-10190/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e10_lr1e-4_s3_rotated_basis_r42/checkpoint-9171/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e10_lr1e-4_s3_rotated_basis_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e10_lr1e-4_s2_rotated_basis_r42/checkpoint-10180/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e10_lr1e-4_s2_rotated_basis_r42/checkpoint-9162/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e10_lr1e-4_s2_rotated_basis_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keepbottom1pct_geomean_e2_lr1e-4_s2/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keepbottom1pct_geomean_e2_lr1e-4_s2/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keepbottom1pct_geomean_e2_lr1e-4_s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keepbottom1pct_geomean_e2_lr1e-4_s1/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keepbottom1pct_geomean_e2_lr1e-4_s1/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keepbottom1pct_geomean_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keepbottom1pct_geomean_e2_lr1e-4_s3/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keepbottom1pct_geomean_e2_lr1e-4_s3/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keepbottom1pct_geomean_e2_lr1e-4_s3/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s2_rotated_basis_r42/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s2_rotated_basis_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s1_rotated_basis_r42/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s1_rotated_basis_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s3_rotated_basis_r42/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s3_rotated_basis_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s2_rotated_basis_r42/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s2_rotated_basis_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s3_rotated_basis_r42/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s3_rotated_basis_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_keepbot1pct_priorrecipe_e2_lr1e-4_s2/checkpoint-1047/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_keepbot1pct_priorrecipe_e2_lr1e-4_s2/checkpoint-2094/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_keepbot1pct_priorrecipe_e2_lr1e-4_s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_keepbot1pct_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_keepbot1pct_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_keepbot1pct_priorrecipe_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_keepbot1pct_priorrecipe_e2_lr1e-4_s3/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_keepbot1pct_priorrecipe_e2_lr1e-4_s3/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_keepbot1pct_priorrecipe_e2_lr1e-4_s3/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keeptop1pct_geomean_e2_lr1e-4_s2/checkpoint-1018/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keeptop1pct_geomean_e2_lr1e-4_s2/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keeptop1pct_geomean_e2_lr1e-4_s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keeptop1pct_geomean_e2_lr1e-4_s1/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keeptop1pct_geomean_e2_lr1e-4_s1/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keeptop1pct_geomean_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keeptop1pct_geomean_e2_lr1e-4_s3/checkpoint-1019/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keeptop1pct_geomean_e2_lr1e-4_s3/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_keeptop1pct_geomean_e2_lr1e-4_s3/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s2/checkpoint-1047/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s2/checkpoint-2094/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s3/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s3/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_plain_priorrecipe_e2_lr1e-4_s3/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_bot5_priorrecipe_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_bot10_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_bot10_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_bot10_priorrecipe_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_bot25_priorrecipe_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_bot25_priorrecipe_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_bot25_priorrecipe_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_plain_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_plain_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_plain_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot5_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot5_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot5_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot1_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot1_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot1_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot10_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot10_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot10_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot25_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot25_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot25_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot10_e2_lr1e-4_s2/checkpoint-1047/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot10_e2_lr1e-4_s2/checkpoint-2094/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot10_e2_lr1e-4_s2/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_perlayer_rot_r42/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_perlayer_rot_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s1_perlayer_rot_r42/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s1_perlayer_rot_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot10_e2_lr1e-4_s3/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot10_e2_lr1e-4_s3/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_bot10_e2_lr1e-4_s3/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_keepboth5pct_e2_lr1e-4_s1/checkpoint-1046/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_keepboth5pct_e2_lr1e-4_s1/checkpoint-2092/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_7m_T0_keepboth5pct_e2_lr1e-4_s1/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s2_perlayer_rot_r42/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s2_perlayer_rot_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s3_perlayer_rot_r42/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s3_perlayer_rot_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s3_perlayer_rot_r42/checkpoint-2038/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_sgd_e2_lr1e-4_s3_perlayer_rot_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s2_perlayer_rot_r42/checkpoint-2036/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s2_perlayer_rot_r42/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k/checkpoint-10467/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k/checkpoint-20934/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r8_a32_adamw_e2_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_mlp_adamw_e10_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k_runB/checkpoint-104670/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_mlp_adamw_e10_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k_runB/checkpoint-94203/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_mlp_adamw_e10_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k_runB/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_mlp_adamw_e10_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k_runA/checkpoint-104670/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_mlp_adamw_e10_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k_runA/checkpoint-94203/tokenizer.json filter=lfs diff=lfs merge=lfs -text checkpoints/cat_qwen25_7b_r64_a32_mlp_adamw_e10_lr1e-4_s1_vt_add_a6_L23_prefill_noSys_100k_runA/tokenizer.json filter=lfs diff=lfs merge=lfs -text