caisarl76/batch1_epochs4_lr1e-05_paged_adamw_32bit_cosine_len2048_warm0.05_grad1.0_accu10_neft5 Text Generation • Updated Feb 1 • 11
caisarl76/batch1_epochs4_lr1e-05_paged_adamw_32bit_cosine_len2048_warm0.05_grad1.0_accu32_neft5 Updated Feb 1
caisarl76/batch1_epochs4_lr1e-05_paged_adamw_32bit_cosine_len2048_warm0.05_grad1.0_accu10_neftNone Text Generation • Updated Feb 1 • 8
caisarl76/batch1_epochs1_lr1e-05_paged_adamw_32bit_cosine_len2048_warm0.05_grad1.0_accu8_neftNone Updated Jan 31
caisarl76/batch2_epochs1_lr1e-05_paged_adamw_32bit_cosine_len2048_warm0.05_grad1.0_accu5_neftNone Updated Jan 31
caisarl76/batch1_epochs4_lr1e-05_paged_adamw_32bit_cosine_len2048_warm0.05_grad1.0_accu16_neft5 Text Generation • Updated Jan 31 • 8
caisarl76/batch1_epochs1_lr1e-05_paged_adamw_32bit_cosine_len2048_warm0.05_grad1.0_accu8_neft5 Updated Jan 24
caisarl76/batch1_epochs1_lr1e-05_paged_adamw_32bit_cosine_len2048_warm0.05_grad1.0_accu32_neft5 Updated Jan 24
caisarl76/batch1_epochs4_lr1e-05_paged_adamw_32bit_cosine_len2048_warm0.05_grad1.0_accu8_neftNone Updated Jan 24
caisarl76/batch1_epochs4_lr1e-05_paged_adamw_32bit_cosine_length2048_warmup_0.05_max_grad1.0_grad_accu32 Text Generation • Updated Jan 23 • 23