imdb-full-0.01

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

• Loss: 0.3455
• Accuracy: 0.8608
• F1: 0.8607

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: 80
• eval_batch_size: 80
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	4	0.6785	0.5412	0.4228
No log	2.0	8	0.6482	0.6337	0.5935
No log	3.0	12	0.5504	0.7572	0.7547
No log	4.0	16	0.7277	0.6048	0.5346
No log	5.0	20	0.3681	0.85	0.8495
No log	6.0	24	0.3446	0.8607	0.8606
No log	7.0	28	0.4569	0.8100	0.8056
No log	8.0	32	0.3455	0.8608	0.8607
No log	9.0	36	0.3599	0.8552	0.8548
No log	10.0	40	0.3612	0.8552	0.8547

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.1+cu128
• Datasets 4.4.2
• Tokenizers 0.22.1