albert-imdb

This model is a fine-tuned version of albert-base-v2 on the imdb dataset. It achieves the following results on the evaluation set:

• Loss: 0.1571
• Accuracy: 0.9482
• F1: 0.9482
• Precision: 0.9482
• Recall: 0.9482

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 9072
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.3213	1.0	1563	0.2683	0.8922	0.8921	0.8930	0.8922
0.2211	2.0	3126	0.2559	0.9082	0.9082	0.9082	0.9082

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2