bertin-project
/

bertin-base-random-exp-512seqlen

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Pablogps commited on Jul 25, 2021

Commit

3372aa0

•

1 Parent(s): 94a43c6

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -12,7 +12,7 @@ widget:
 This is a **RoBERTa-base** model trained from scratch in Spanish.
 The training dataset is [mc4](https://huggingface.co/datasets/bertin-project/mc4-es-sampled ) subsampling documents to a total of about 50 million examples. Sampling is random.
-This model takes the one using [sequence length 128](https://huggingface.co/bertin-project/bertin-base-random) and trains during 25.000 steps using sequence length 512.
 Please see our main [card](https://huggingface.co/bertin-project/bertin-roberta-base-spanish) for more information.

 This is a **RoBERTa-base** model trained from scratch in Spanish.
 The training dataset is [mc4](https://huggingface.co/datasets/bertin-project/mc4-es-sampled ) subsampling documents to a total of about 50 million examples. Sampling is random.
+This model continued training from [sequence length 128](https://huggingface.co/bertin-project/bertin-base-random) using 20.000 steps for length 512.
 Please see our main [card](https://huggingface.co/bertin-project/bertin-roberta-base-spanish) for more information.