classifier_3

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

• Loss: 0.6314
• Accuracy: 0.6600

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: 1e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 9

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	8	0.6471	0.6183
No log	2.0	16	0.6317	0.6541
No log	3.0	24	0.6263	0.6501
No log	4.0	32	0.6267	0.6501
No log	5.0	40	0.6260	0.6521
No log	6.0	48	0.6276	0.6481
No log	7.0	56	0.6297	0.6541
No log	8.0	64	0.6319	0.6461
No log	9.0	72	0.6314	0.6600

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0