distilbert_sa_GLUE_Experiment_logit_kd_data_aug_mnli

This model is a fine-tuned version of distilbert-base-uncased on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.5076
• Accuracy: 0.6560

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
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4734	1.0	31440	0.5068	0.6496
0.3743	2.0	62880	0.5281	0.6379
0.3454	3.0	94320	0.5361	0.6354
0.3333	4.0	125760	0.5399	0.6350
0.3265	5.0	157200	0.5409	0.6379
0.3219	6.0	188640	0.5377	0.6413

Framework versions

• Transformers 4.26.0
• Pytorch 1.14.0a0+410ce96
• Datasets 2.9.0
• Tokenizers 0.13.2