This model is a fine-tuned version of google/bert_uncased_L-2_H-256_A-4 on the GLUE RTE dataset. It achieves the following results on the evaluation set:

Loss: 0.6523
Accuracy: 0.6029

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
0.6981	1.0	10	0.6832	0.5740
0.6877	2.0	20	0.6789	0.5740
0.6794	3.0	30	0.6746	0.5812
0.6685	4.0	40	0.6703	0.5740
0.6592	5.0	50	0.6674	0.5848
0.6447	6.0	60	0.6637	0.6029
0.6238	7.0	70	0.6565	0.5957
0.6077	8.0	80	0.6523	0.6029
0.5805	9.0	90	0.6558	0.5884
0.5502	10.0	100	0.6610	0.5848
0.5119	11.0	110	0.6632	0.6065
0.4778	12.0	120	0.6787	0.6029
0.4415	13.0	130	0.7027	0.5957

Framework versions

Transformers 4.46.3
Pytorch 2.2.1+cu118
Datasets 2.17.0
Tokenizers 0.20.3

gokulsrinivasagan/bert_uncased_L-2_H-256_A-4_rte

bert_uncased_L-2_H-256_A-4_rte

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

gokulsrinivasagan/
bert_uncased_L-2_H-256_A-4_rte