distilbert_base_train_mnli

This model is a fine-tuned version of gokulsrinivasagan/distilbert_base_train on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.7366
• Accuracy: 0.6847

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: 5e-05
• train_batch_size: 256
• eval_batch_size: 256
• seed: 10
• optimizer: Use 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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9464	1.0	1534	0.8279	0.6259
0.7887	2.0	3068	0.7683	0.6624
0.6959	3.0	4602	0.7424	0.6854
0.6184	4.0	6136	0.7529	0.6899
0.5414	5.0	7670	0.7874	0.6879
0.4648	6.0	9204	0.8281	0.6882
0.3943	7.0	10738	0.9039	0.6865
0.3321	8.0	12272	1.0392	0.6811

Framework versions

• Transformers 4.46.3
• Pytorch 2.2.1+cu118
• Datasets 2.17.0
• Tokenizers 0.20.3