Ctrl+K
- ablation
- pt-d-llada-1.2B_slimpajama-6B
- pt-d-llada-250M_fineweb-20B-4clusters_24h
- pt-d-llada-250M_slimpajama-6B-4clusters
- pt-d-llada-250M_slimpajama-6B-4clusters_24h
- pt-d-llada-250M_slimpajama-6B-rnd4clusters_24h
- pt-d-llada-250M_slimpajama-6B
- pt-d-llada-500M_slimpajama-6B
- pt-d-llada-700M_fineweb80b-4clusters-24h
- pt-d-llada-75M_fineweb-20B-4clusters_24h
- pt-d-llada-75M_slimpajama-6B-4clusters_24h
- pt-d-llada-gpt2-355M_fineweb-20B-4clusters_24h
- pt-d-llada-gpt2-355M_owt-4clusters_warmup2k-constant_24h
- pt-m-llada-1.2B_slimpajama-6B
- pt-m-llada-250M_fineweb-20B_24h
- pt-m-llada-250M_slimpajama-6B-re
- pt-m-llada-250M_slimpajama-6B
- pt-m-llada-250M_slimpajama-6B_24h
- pt-m-llada-500M_slimpajama-6B
- pt-m-llada-700M_fineweb80b_24h
- pt-m-llada-75M_fineweb-20B_24h
- pt-m-llada-75M_slimpajama-6B_24h
- pt-m-llada-gpt2-355M_fineweb20b_24h
- pt-m-llada-gpt2-355M_owt_24h
- sft-d-a2dbd3lm-qwen3-0.6B_tulu3-opc-smoltalk-2clusters-by-domain
- sft-d-a2dbd3lm-qwen3-0.6B_tulu3mixture-3clusters-by-domain
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3-opc-smoltalk
- trial_sft-m-a2dbd3lm-qwen3-0.6B_tulu3mixture
- 4.25 kB