This model is a fine-tuned version of google/bert_uncased_L-6_H-768_A-12 on the glue dataset. It achieves the following results on the evaluation set:

Loss: 0.2984
Accuracy: 0.9094

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: 7.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2453	1.0	527	0.2552	0.8979
0.1257	2.0	1054	0.2997	0.8933
0.0818	3.0	1581	0.2984	0.9094
0.057	4.0	2108	0.3181	0.9048
0.0403	5.0	2635	0.3299	0.9083
0.0274	6.0	3162	0.4222	0.9060
0.0192	7.0	3689	0.4797	0.9083

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0

jysh1023/bert_uncased_QAT

bert_uncased_qat

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jysh1023/
bert_uncased_QAT