distilbert_add_GLUE_Experiment_logit_kd_sst2

This model is a fine-tuned version of distilbert-base-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.9411
• Accuracy: 0.7821

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
1.3582	1.0	264	1.0124	0.7546
0.8162	2.0	528	1.0190	0.7844
0.5596	3.0	792	0.9411	0.7821
0.4502	4.0	1056	0.9809	0.7798
0.4184	5.0	1320	1.0198	0.7741
0.3596	6.0	1584	1.0163	0.7718
0.3394	7.0	1848	1.0623	0.7752
0.3045	8.0	2112	1.1069	0.7626

Framework versions

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