N_bert_imdb_padding50model

This model is a fine-tuned version of bert-base-uncased on the imdb dataset. It achieves the following results on the evaluation set:

• Loss: 0.7352
• Accuracy: 0.9385

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2185	1.0	1563	0.2445	0.9211
0.1562	2.0	3126	0.1966	0.9369
0.0924	3.0	4689	0.3358	0.9287
0.0576	4.0	6252	0.3586	0.9308
0.0493	5.0	7815	0.3533	0.9346
0.0362	6.0	9378	0.4772	0.9287
0.019	7.0	10941	0.4636	0.9328
0.0282	8.0	12504	0.4084	0.9350
0.0155	9.0	14067	0.4659	0.9302
0.0119	10.0	15630	0.5622	0.9342
0.0074	11.0	17193	0.5651	0.9338
0.0047	12.0	18756	0.5859	0.9348
0.006	13.0	20319	0.6266	0.9342
0.0067	14.0	21882	0.6573	0.9308
0.0044	15.0	23445	0.6579	0.9370
0.0	16.0	25008	0.6971	0.9386
0.0011	17.0	26571	0.7194	0.9377
0.0	18.0	28134	0.7164	0.9392
0.0	19.0	29697	0.7198	0.9391
0.0	20.0	31260	0.7352	0.9385

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.13.3