gsarti commited on
Commit
89b2707
1 Parent(s): 71341a3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -29,7 +29,7 @@ The following table summarizes the parameters for all available models
29
  |`dataset` |`gsarti/clean_mc4_it` |`gsarti/clean_mc4_it` |`gsarti/clean_mc4_it` |`oscar/unshuffled_deduplicated_it`|
30
  |`architecture` |`google/t5-v1_1-small` |`google/t5-v1_1-base` |`google/t5-v1_1-large` |`t5-base` |
31
  |`learning rate` | 5e-3 | 5e-3 | 5e-3 | 1e-2 |
32
- |`steps` | 1'050'000 | 1'050'000 | 1'050'000 | 258'000 |
33
  |`training time` | 36 hours | 101 hours | 370 hours | 98 hours |
34
  |`ff projection` |`gated-gelu` |`gated-gelu` |`gated-gelu` |`relu` |
35
  |`tie embeds` |`false` |`false` |`false` |`true` |
 
29
  |`dataset` |`gsarti/clean_mc4_it` |`gsarti/clean_mc4_it` |`gsarti/clean_mc4_it` |`oscar/unshuffled_deduplicated_it`|
30
  |`architecture` |`google/t5-v1_1-small` |`google/t5-v1_1-base` |`google/t5-v1_1-large` |`t5-base` |
31
  |`learning rate` | 5e-3 | 5e-3 | 5e-3 | 1e-2 |
32
+ |`steps` | 1'050'000 | 1'050'000 | 2'100'000 | 258'000 |
33
  |`training time` | 36 hours | 101 hours | 370 hours | 98 hours |
34
  |`ff projection` |`gated-gelu` |`gated-gelu` |`gated-gelu` |`relu` |
35
  |`tie embeds` |`false` |`false` |`false` |`true` |