distilbert_add_GLUE_Experiment_logit_kd_sst2_256

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: 1.0990
• Accuracy: 0.7741

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
1.6037	1.0	264	1.4539	0.5092
1.0469	2.0	528	1.4535	0.6961
0.6705	3.0	792	1.4747	0.7271
0.5309	4.0	1056	1.3223	0.75
0.4534	5.0	1320	1.1506	0.7718
0.4222	6.0	1584	1.1359	0.7661
0.3765	7.0	1848	1.0990	0.7741
0.3479	8.0	2112	1.1928	0.7672
0.323	9.0	2376	1.2111	0.7683
0.306	10.0	2640	1.2978	0.7672
0.2917	11.0	2904	1.2737	0.7649
0.2684	12.0	3168	1.1852	0.7729

Framework versions

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