finetuning-sentiment-model-1500-samples

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: 0.3496
• Accuracy: 0.87
• F1: 0.8721

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: 42
• 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
No log	1.0	94	0.3214	0.8667	0.8649
No log	2.0	188	0.3496	0.87	0.8721

Framework versions

• Transformers 4.33.3
• Pytorch 2.1.0
• Datasets 2.12.0
• Tokenizers 0.13.2