left_padding40model

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

• Accuracy: 0.9335
• Loss: 0.6508

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: 10

Training results

Training Loss	Epoch	Step	Accuracy	Validation Loss
0.0835	1.0	1563	0.9287	0.3934
0.0219	2.0	3126	0.9306	0.4228
0.0408	3.0	4689	0.9276	0.4133
0.0316	4.0	6252	0.9300	0.4801
0.0285	5.0	7815	0.9287	0.5290
0.0318	6.0	9378	0.9281	0.5954
0.0199	7.0	10941	0.9311	0.6008
0.0049	8.0	12504	0.9305	0.6087
0.0003	9.0	14067	0.9320	0.6529
0.0032	10.0	15630	0.9335	0.6508

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.0+cu117
• Datasets 2.14.6
• Tokenizers 0.14.1