yigitkucuk/bert-base-uncased-finetuned-rte-run_3-2025-04-01_00-04

bert-base-uncased-finetuned-rte-run_1-2025-04-01_00-49

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: 1.7147
• Accuracy: 0.6643

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: 4.7844656226353705e-05
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.18588223157500006
• lr_scheduler_warmup_steps: 500
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	78	0.6996	0.4693
No log	2.0	156	0.6848	0.5523
No log	3.0	234	0.6481	0.6390
No log	4.0	312	0.7540	0.6390
No log	5.0	390	1.1176	0.6209
No log	6.0	468	1.5226	0.6390
0.4745	7.0	546	1.7403	0.6282
0.4745	8.0	624	1.7147	0.6643

Framework versions

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