Classifier_with_external_sets_02

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

• Loss: 0.6968
• Accuracy: 0.5034

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: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.9983	289	0.6937	0.4966
0.6958	2.0	579	0.6958	0.4966
0.6958	2.9983	868	0.6972	0.4966
0.6845	4.0	1158	0.6931	0.5034
0.6845	4.9983	1447	0.7009	0.5034
0.6548	6.0	1737	0.7251	0.5034
0.6484	6.9983	2026	0.7186	0.5034
0.6484	8.0	2316	0.7049	0.5034
0.6453	8.9983	2605	0.6997	0.5034
0.6453	9.9827	2890	0.6968	0.5034

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1