bert-base-uncased-finetuned-rte-run_8_best

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: 0.8601
• Accuracy: 0.7256

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: 6.387670620549943e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	20	0.6376	0.6426
No log	2.0	40	0.6699	0.6968
No log	3.0	60	0.6570	0.7148
No log	4.0	80	0.8601	0.7256
No log	5.0	100	0.9858	0.7004
No log	6.0	120	1.1769	0.6823
No log	7.0	140	1.2463	0.6895
No log	8.0	160	1.5285	0.7004
No log	9.0	180	1.4726	0.7004
No log	10.0	200	1.5863	0.6859
No log	11.0	220	1.5913	0.6823
No log	12.0	240	1.6612	0.6968
No log	13.0	260	1.6851	0.7040
No log	14.0	280	1.7215	0.7040
No log	15.0	300	1.7309	0.7076

Framework versions

• Transformers 4.50.2
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1