classify

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

• Loss: 0.5723
• Precision: 0.0
• Recall: 0.0
• F1 Binary: 0.0
• Accuracy: 0.7429

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: 0.0003
• train_batch_size: 4
• eval_batch_size: 4
• seed: 0
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1 Binary	Accuracy
No log	0	0	0.7028	0.2437	0.7160	0.3636	0.3556
0.6	2.8181	1000	0.5779	0.0	0.0	0.0	0.7429
0.5522	5.6347	2000	0.5709	0.0	0.0	0.0	0.7429
0.5582	8.4513	3000	0.5709	0.0	0.0	0.0	0.7429
0.5791	11.2680	4000	0.5703	0.0	0.0	0.0	0.7429
0.5895	14.0846	5000	0.5701	0.0	0.0	0.0	0.7429
0.5629	16.9027	6000	0.5730	0.0	0.0	0.0	0.7429
0.5841	19.7193	7000	0.5723	0.0	0.0	0.0	0.7429

Framework versions

• Transformers 4.48.1
• Pytorch 2.3.0
• Datasets 3.2.0
• Tokenizers 0.21.0