Ctrl+K
- 1.7b-adam-1.5e6-8k-qwen3-1.7b-base-adamw-lr1.5e-6-kl-losscoef0.001
- 1.7b-adam-1e6-8k-qwen3-1.7b-base-adamw-lr1e-6-kl-losscoef0.001
- 1.7b-adam-2e6-8k-qwen3-1.7b-base-adamw-lr2e-6-kl-losscoef0.001
- 1.7b-adam-3e6-8k-qwen3-1.7b-base-adamw-lr3e-6-kl-losscoef0.001
- 1.7b-bothuv-1e6-8k-qwen3-1.7b-base-svd_muon-ulr1e-6-vlr1e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-bothuv-2e6-8k-qwen3-1.7b-base-svd_muon-ulr2e-6-vlr2e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-muon-1e4-8k-qwen3-1.7b-base-muon-muonlr1e-4-spectral_norm-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-muon-1e5-8k-qwen3-1.7b-base-muon-muonlr1e-5-spectral_norm-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-sigma-only-2e6-8k-qwen3-1.7b-base-svd_muon-ulr2e-6-vlr2e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-uv-1.5e6-8k-qwen3-1.7b-base-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-uv-2e6-r2-8k-qwen3-1.7b-base-svd_muon-ulr2e-6-vlr2e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-uv-alt-2e6-8k-qwen3-1.7b-base-svd_muon-ulr2e-6-vlr2e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-uv-topk0.8-1.5e6-8k-qwen3-1.7b-base-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-uv-topk0.8-1e6-8k-qwen3-1.7b-base-svd_muon-ulr1e-6-vlr1e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-uv-topk0.8-2e6-8k-qwen3-1.7b-base-svd_muon-ulr2e-6-vlr2e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-uv-topk0.9-1.5e6-8k-qwen3-1.7b-base-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-uv-topk0.9-1e6-8k-qwen3-1.7b-base-svd_muon-ulr1e-6-vlr1e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 1.7b-uv-topk0.9-2e6-8k-qwen3-1.7b-base-svd_muon-ulr2e-6-vlr2e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 4b-adam-1.5e6-8k-qwen3-4b-base-adamw-lr1.5e-6-kl-losscoef0.001
- 4b-adam-1e6-8k-qwen3-4b-base-adamw-lr1e-6-kl-losscoef0.001
- 4b-adam-2e6-8k-qwen3-4b-base-adamw-lr2e-6-kl-losscoef0.001
- 4b-adam-3e6-8k-qwen3-4b-base-adamw-lr3e-6-kl-losscoef0.001
- 4b-bothuv-1e6-8k-qwen3-4b-base-svd_muon-ulr1e-6-vlr1e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 4b-bothuv-2e6-8k-qwen3-4b-base-svd_muon-ulr2e-6-vlr2e-6-none-muonadamlr1e-6-kl-losscoef0.001
- 4b-muon-1e4-8k-qwen3-4b-base-muon-muonlr1e-4-spectral_norm-muonadamlr1e-6-kl-losscoef0.001
- 4b-muon-1e5-8k-qwen3-4b-base-muon-muonlr1e-5-spectral_norm-muonadamlr1e-6-kl-losscoef0.001
- 4b-uv-topk0.8-1.5e6-8k-qwen3-4b-base-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6-kl-losscoef0.001
- coding-adam-1.5e6-16k-ds-r1-1.5b-adamw-lr1.5e-6
- coding-adam-1.5e6-32k-ds-r1-1.5b-adamw-lr1.5e-6
- coding-adam-1e6-16k-ds-r1-1.5b-adamw-lr1e-6
- coding-adam-1e6-32k-ds-r1-1.5b-adamw-lr1e-6
- coding-adam-2e6-16k-ds-r1-1.5b-adamw-lr2e-6
- coding-adam-2e6-32k-ds-r1-1.5b-adamw-lr2e-6
- coding-adam-3e6-16k-ds-r1-1.5b-adamw-lr3e-6
- coding-adam-3e6-32k-ds-r1-1.5b-adamw-lr3e-6
- coding-muon-1e4-16k-ds-r1-1.5b-muon-muonlr1e-4-spectral_norm-muonadamlr1e-6
- coding-muon-1e4-32k-ds-r1-1.5b-muon-muonlr1e-4-spectral_norm-muonadamlr1e-6
- coding-muon-1e5-16k-ds-r1-1.5b-muon-muonlr1e-5-spectral_norm-muonadamlr1e-6
- coding-muon-1e5-32k-ds-r1-1.5b-muon-muonlr1e-5-spectral_norm-muonadamlr1e-6
- coding-uv-1.5e6-16k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6
- coding-uv-1.5e6-32k-ds-r1-1.5b-svd_muon-ulr1.5e-6-vlr1.5e-6-none-muonadamlr1e-6
- coding-uv-1e6-16k-ds-r1-1.5b-svd_muon-ulr1e-6-vlr1e-6-none-muonadamlr1e-6
- coding-uv-1e6-32k-ds-r1-1.5b-svd_muon-ulr1e-6-vlr1e-6-none-muonadamlr1e-6
- llama8b-adam-1e6-3k-llama31-8b-inst-adamw-lr1e-6-kl-losscoef0.001
- llama8b-adam-1e6-4k-llama31-8b-inst-adamw-lr1e-6-kl-losscoef0.001
- llama8b-adam-2e6-4k-llama31-8b-inst-adamw-lr2e-6-kl-losscoef0.001
- llama8b-adam-3e6-4k-llama31-8b-inst-adamw-lr3e-6-kl-losscoef0.001
- llama8b-uv-1e6-4k-llama31-8b-inst-svd_muon-ulr1e-6-vlr1e-6-none-muonadamlr1e-6-kl-losscoef0.001
- llama8b-uv-2e6-4k-llama31-8b-inst-svd_muon-ulr2e-6-vlr2e-6-none-muonadamlr1e-6-kl-losscoef0.001
- mn-1.7b-adam-2e6-8k-qwen3-1.7b-base-adamw-lr2e-6-kl-losscoef0.001