learning_curve_overfit

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: 0.4524
• Accuracy: 0.8168
• F1: 0.8688

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use 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	F1
0.6101	0.2174	50	0.6364	0.7279	0.8177
0.5008	0.4348	100	0.5460	0.7525	0.8439
0.4883	0.6522	150	0.4691	0.7966	0.8642
0.4098	0.8696	200	0.4353	0.8137	0.8707
0.2658	1.0870	250	0.4194	0.8333	0.8736
0.3686	1.3043	300	0.4500	0.8113	0.8723
0.3576	1.5217	350	0.3881	0.8505	0.8950
0.2184	1.7391	400	0.5283	0.8113	0.8752
0.3837	1.9565	450	0.3702	0.8431	0.8832
0.1495	2.1739	500	0.6471	0.8480	0.8970
0.2161	2.3913	550	0.5114	0.8358	0.8757

Framework versions

• Transformers 4.53.2
• Pytorch 2.7.1+cu128
• Datasets 4.0.0
• Tokenizers 0.21.2