N_bert_imdb_padding10model

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: 0.6695
• Accuracy: 0.9398

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
0.2175	1.0	1563	0.2147	0.9269
0.1483	2.0	3126	0.2123	0.9384
0.0912	3.0	4689	0.2707	0.9325
0.0569	4.0	6252	0.3262	0.9314
0.042	5.0	7815	0.3316	0.9372
0.0373	6.0	9378	0.4147	0.9365
0.0181	7.0	10941	0.4632	0.936
0.0144	8.0	12504	0.5192	0.9338
0.0138	9.0	14067	0.4934	0.9388
0.0094	10.0	15630	0.5627	0.9363
0.0091	11.0	17193	0.6356	0.9285
0.0114	12.0	18756	0.5780	0.9368
0.0025	13.0	20319	0.6362	0.9402
0.0067	14.0	21882	0.5902	0.9388
0.0043	15.0	23445	0.6124	0.9387
0.0029	16.0	25008	0.5929	0.9380
0.0001	17.0	26571	0.6554	0.9394
0.0005	18.0	28134	0.6619	0.9408
0.0019	19.0	29697	0.6654	0.9398
0.0	20.0	31260	0.6695	0.9398

Framework versions

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