bert-base-uncased-finetuned-rte-run_3

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: 0.6883
• Accuracy: 0.6462

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: 9.796937080527387e-06
• train_batch_size: 64
• eval_batch_size: 32
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	39	0.6887	0.5307
No log	2.0	78	0.6797	0.5596
No log	3.0	117	0.6805	0.5523
No log	4.0	156	0.6554	0.6354
No log	5.0	195	0.6759	0.6245
No log	6.0	234	0.6883	0.6462
No log	7.0	273	0.7252	0.6137
No log	8.0	312	0.7378	0.6318
No log	9.0	351	0.7529	0.6282
No log	10.0	390	0.7541	0.6318

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1