N_bert_imdb_padding70model

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: 0.6873
• Accuracy: 0.9394

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
0.2213	1.0	1563	0.3103	0.8968
0.1541	2.0	3126	0.3041	0.908
0.0907	3.0	4689	0.3070	0.9316
0.0654	4.0	6252	0.3320	0.9348
0.0458	5.0	7815	0.4088	0.9346
0.0277	6.0	9378	0.4032	0.9328
0.0257	7.0	10941	0.4421	0.9336
0.0255	8.0	12504	0.4574	0.9347
0.0125	9.0	14067	0.4488	0.9375
0.0149	10.0	15630	0.6741	0.9207
0.0117	11.0	17193	0.6366	0.9342
0.0112	12.0	18756	0.6009	0.9330
0.0098	13.0	20319	0.6284	0.9358
0.0014	14.0	21882	0.5567	0.9394
0.0069	15.0	23445	0.6130	0.9362
0.0013	16.0	25008	0.6577	0.9374
0.0	17.0	26571	0.6816	0.9386
0.0003	18.0	28134	0.7144	0.9371
0.0035	19.0	29697	0.6844	0.9391
0.0	20.0	31260	0.6873	0.9394

Framework versions

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