Skip to main content

Nonenman's group workspace

eval
2
10k20k30kStep123456
10k20k30kStep200400600800
model
6
30_roberta-large_A100_48_384_2e-5_20-words_20epochs30_roberta-large_A100_48_384_2e-5_40-tokens_20epochs30_albert-xxlarge-v2_A100_24_384_2e-5_20-words_100epochs30_albert-xxlarge-v2_A100_24_384_2e-5_40-tokens_100epochs30_albert-xxlarge-v2_A100_24_384_2e-5_35-words_10epochs30_albert-xxlarge-v2_A100_24_384_2e-5_40-tokens_10epochs30_albert-xxlarge-v2_A100_24_384_2e-5_15-tokens_10epochs0100,000,000200,000,000300,000,000
30_roberta-large_A100_48_384_2e-5_20-words_20epochs30_roberta-large_A100_48_384_2e-5_40-tokens_20epochs30_albert-xxlarge-v2_A100_24_384_2e-5_20-words_100epochs30_albert-xxlarge-v2_A100_24_384_2e-5_40-tokens_100epochs30_albert-xxlarge-v2_A100_24_384_2e-5_35-words_10epochs30_albert-xxlarge-v2_A100_24_384_2e-5_40-tokens_10epochs30_albert-xxlarge-v2_A100_24_384_2e-5_15-tokens_10epochs01,0002,0003,0004,000
30_roberta-large_A100_48_384_2e-5_20-words_20epochs30_roberta-large_A100_48_384_2e-5_40-tokens_20epochs30_albert-xxlarge-v2_A100_24_384_2e-5_20-words_100epochs30_albert-xxlarge-v2_A100_24_384_2e-5_40-tokens_100epochs30_albert-xxlarge-v2_A100_24_384_2e-5_35-words_10epochs30_albert-xxlarge-v2_A100_24_384_2e-5_40-tokens_10epochs30_albert-xxlarge-v2_A100_24_384_2e-5_15-tokens_10epochs01020
train
5