This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the augmented_glue_sst2 dataset. It achieves the following results on the evaluation set:

Loss: 0.2643
Accuracy: 0.9128

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: 6e-05
train_batch_size: 128
eval_batch_size: 128
seed: 33
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 7
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.602	1.0	6227	0.3389	0.9186
0.4195	2.0	12454	0.2989	0.9151
0.3644	3.0	18681	0.2794	0.9117
0.3304	4.0	24908	0.2793	0.9106
0.3066	5.0	31135	0.2659	0.9186
0.2881	6.0	37362	0.2668	0.9140
0.2754	7.0	43589	0.2643	0.9128

Framework versions

Transformers 4.16.2
Pytorch 1.10.0+cu111
Datasets 1.18.3
Tokenizers 0.11.0

moshew/miny-bert-aug-sst2-distilled

miny-bert-aug-sst2-distilled

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

moshew/
miny-bert-aug-sst2-distilled