This model is a fine-tuned version of google/bert_uncased_L-4_H-256_A-4 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

Loss: 0.3628
Accuracy: 0.8429

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
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4143	1.0	264	0.4119	0.8131
0.2672	2.0	528	0.3628	0.8429
0.2117	3.0	792	0.3785	0.8498
0.1736	4.0	1056	0.4139	0.8475
0.1493	5.0	1320	0.4231	0.8532
0.1294	6.0	1584	0.4411	0.8544
0.1159	7.0	1848	0.4575	0.8589

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3

gokulsrinivasagan/bert_uncased_L-4_H-256_A-4_sst2

bert_uncased_L-4_H-256_A-4_sst2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

gokulsrinivasagan/
bert_uncased_L-4_H-256_A-4_sst2