Training Loop

Reusing dataset glue (/home/sgugger/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad)
Loading cached processed dataset at /home/sgugger/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad/cache-8174fd92eed0af98.arrow
Loading cached processed dataset at /home/sgugger/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad/cache-8c99fb059544bc96.arrow
Loading cached processed dataset at /home/sgugger/.cache/huggingface/datasets/glue/mrpc/1.0.0/dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad/cache-e625eb72bcf1ae1f.arrow

{'attention_mask': torch.Size([8, 63]), 'input_ids': torch.Size([8, 63]), 'labels': torch.Size([8]), 'token_type_ids': torch.Size([8, 63])}

Some weights of the model checkpoint at bert-base-cased were not used when initializing BertForSequenceClassification: ['cls.predictions.decoder.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.bias', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias']
- This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-cased and are newly initialized: ['classifier.bias', 'classifier.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

tensor(0.7512, grad_fn=<NllLossBackward>) torch.Size([8, 2])

cuda

HBox(children=(FloatProgress(value=0.0, max=1377.0), HTML(value='')))

{'accuracy': 0.8284313725490197, 'f1': 0.8809523809523808}