t2e-classifier-v7

This model is a fine-tuned version of st125338/t2e-classifier-v4 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6208
• Accuracy: 0.8497
• Micro F1: 0.8497
• Macro F1: 0.7468

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Micro F1	Macro F1
0.3291	1.0	5449	0.3378	0.8590	0.8590	0.7478
0.2761	2.0	10898	0.3480	0.85	0.85	0.7510
0.2221	3.0	16347	0.4159	0.8535	0.8535	0.7528
0.1793	4.0	21796	0.5131	0.8506	0.8506	0.7499
0.1476	4.9992	27240	0.6208	0.8497	0.8497	0.7468

Framework versions

• Transformers 4.51.1
• Pytorch 2.2.0+cu118
• Datasets 3.5.0
• Tokenizers 0.21.0