fastai_community

Arampacha's group workspace

Group: imdb-roberta-base-hf-3e-05

eval/accuracy

0.958

0.95376

0.95608

0.95568

0.95332

1-6

of 6

Timestamps visible

2021-04-22 16:31:56

Some weights of the model checkpoint at roberta-base were not used when initializing RobertaForSequenceClassification: ['lm_head.bias', 'lm_head.dense.weight', 'lm_head.dense.bias', 'lm_head.layer_norm.weight', 'lm_head.layer_norm.bias', 'lm_head.decoder.weight', 'roberta.pooler.dense.weight', 'roberta.pooler.dense.bias']

2021-04-22 16:31:56

- This IS expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).

2021-04-22 16:31:56

- This IS NOT expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).

2021-04-22 16:31:56

Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at roberta-base and are newly initialized: ['classifier.dense.weight', 'classifier.dense.bias', 'classifier.out_proj.weight', 'classifier.out_proj.bias']

2021-04-22 16:31:56

You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

2021-04-22 16:33:05

Starting virtual adversarial training at epoch 0