bert-base-uncased-finetuned-rte-run_6_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: 1.4020
• Accuracy: 0.7076

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: 0.00011357199085352113
• 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	0.6514	0.6245
No log	2.0	40	0.6411	0.6895
No log	3.0	60	0.8792	0.6498
No log	4.0	80	0.9813	0.6715
No log	5.0	100	1.3011	0.6679
No log	6.0	120	1.2946	0.6751
No log	7.0	140	1.5953	0.6823
No log	8.0	160	1.4640	0.7040
No log	9.0	180	1.4020	0.7076
No log	10.0	200	1.5325	0.6968
No log	11.0	220	1.5469	0.6895
No log	12.0	240	1.6298	0.6968
No log	13.0	260	1.7015	0.6931
No log	14.0	280	1.6853	0.7040
No log	15.0	300	1.6948	0.7004

Framework versions

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