distilbert_sa_GLUE_Experiment_logit_kd_pretrain_wnli

This model is a fine-tuned version of gokuls/distilbert_sa_pre-training-complete on the GLUE WNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.3499
• Accuracy: 0.5493

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
0.3552	1.0	3	0.3512	0.4085
0.3495	2.0	6	0.3540	0.2817
0.3471	3.0	9	0.3499	0.5493
0.3473	4.0	12	0.3514	0.5634
0.3476	5.0	15	0.3536	0.5070
0.3465	6.0	18	0.3576	0.1831
0.3463	7.0	21	0.3589	0.2113
0.3449	8.0	24	0.3598	0.2958

Framework versions

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