N_bert_imdb_padding90model

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: 0.6812
• Accuracy: 0.9370

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
0.231	1.0	1563	0.2247	0.9244
0.1494	2.0	3126	0.2082	0.9327
0.0859	3.0	4689	0.3046	0.9325
0.0543	4.0	6252	0.3399	0.9306
0.0426	5.0	7815	0.4251	0.9296
0.0382	6.0	9378	0.4925	0.9283
0.0239	7.0	10941	0.5281	0.9283
0.0175	8.0	12504	0.4922	0.9323
0.0161	9.0	14067	0.5648	0.9324
0.0091	10.0	15630	0.5808	0.9366
0.0139	11.0	17193	0.5845	0.9345
0.0041	12.0	18756	0.5509	0.9330
0.0055	13.0	20319	0.6335	0.9342
0.0019	14.0	21882	0.6713	0.9356
0.0024	15.0	23445	0.6316	0.9358
0.0	16.0	25008	0.6567	0.9379
0.0038	17.0	26571	0.6668	0.9375
0.0009	18.0	28134	0.6795	0.9373
0.0013	19.0	29697	0.6736	0.9371
0.0001	20.0	31260	0.6812	0.9370

Framework versions

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