N_distilbert_imdb_padding70model

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

• Loss: 0.7329
• Accuracy: 0.9293

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
0.243	1.0	1563	0.2326	0.9132
0.1814	2.0	3126	0.2110	0.9285
0.1108	3.0	4689	0.3094	0.9227
0.0738	4.0	6252	0.3288	0.9263
0.0487	5.0	7815	0.4211	0.9267
0.0437	6.0	9378	0.4656	0.9265
0.0206	7.0	10941	0.5168	0.9272
0.0271	8.0	12504	0.5283	0.9281
0.0222	9.0	14067	0.5181	0.927
0.0214	10.0	15630	0.5876	0.9265
0.0185	11.0	17193	0.6311	0.9264
0.0099	12.0	18756	0.6656	0.927
0.0084	13.0	20319	0.6685	0.9254
0.0025	14.0	21882	0.7040	0.9256
0.0047	15.0	23445	0.7220	0.9295
0.0041	16.0	25008	0.7185	0.9270
0.0028	17.0	26571	0.7079	0.93
0.0037	18.0	28134	0.7378	0.9269
0.0019	19.0	29697	0.7255	0.9288
0.0001	20.0	31260	0.7329	0.9293

Framework versions

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