bert-large-cased-binary-classification

This model is a fine-tuned version of bert-large-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1857
• Accuracy: 0.7548
• F1 Macro: 0.7312
• Precision Macro: 0.7580
• Recall Macro: 0.7246
• Auc: 0.7883

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 Macro	Precision Macro	Recall Macro	Auc
No log	1.0	79	0.6805	0.5987	0.3818	0.7987	0.5039	0.6079
No log	2.0	158	0.6254	0.6497	0.6490	0.6611	0.6655	0.7395
No log	3.0	237	0.6803	0.7166	0.6941	0.7087	0.6900	0.7563
No log	4.0	316	0.7502	0.7166	0.7106	0.7093	0.7153	0.7784
No log	5.0	395	1.1857	0.7548	0.7312	0.7580	0.7246	0.7883
No log	6.0	474	1.4866	0.7548	0.7312	0.7580	0.7246	0.7798
0.3165	7.0	553	1.5617	0.7420	0.7319	0.7322	0.7316	0.7829
0.3165	8.0	632	1.6626	0.7452	0.7311	0.7366	0.7280	0.7762
0.3165	9.0	711	1.7303	0.7611	0.7423	0.7595	0.7363	0.7768
0.3165	10.0	790	1.7471	0.7452	0.7294	0.7376	0.7255	0.7765

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1