outputs_test

This model is a fine-tuned version of microsoft/deberta-v3-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9518
• Accuracy: 0.7386

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: 8e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	12	0.7810	0.5943
No log	2.0	24	0.5357	0.6629
No log	3.0	36	0.4338	0.7129
No log	4.0	48	0.5672	0.6886
No log	5.0	60	0.7802	0.7114
No log	6.0	72	0.7019	0.73
No log	7.0	84	0.7304	0.7514
No log	8.0	96	1.0413	0.72
No log	9.0	108	0.8902	0.7314
No log	10.0	120	0.8441	0.7514
No log	11.0	132	0.7846	0.7643
No log	12.0	144	0.8730	0.7586
No log	13.0	156	0.9532	0.7386
No log	14.0	168	0.9541	0.74
No log	15.0	180	0.9518	0.7386

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3