add_BERT_24_mnli

This model is a fine-tuned version of gokuls/add_bert_12_layer_model_complete_training_new on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

• Loss: 1.0986
• Accuracy: 0.3295

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: 4e-05
• train_batch_size: 128
• eval_batch_size: 128
• 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

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1032	1.0	3068	1.0994	0.3182
1.0988	2.0	6136	1.0986	0.3182
1.0987	3.0	9204	1.0987	0.3274
1.0988	4.0	12272	1.0986	0.3274
1.0987	5.0	15340	1.0986	0.3274
1.0986	6.0	18408	1.0986	0.3182
1.0986	7.0	21476	1.0986	0.3182
1.0986	8.0	24544	1.0986	0.3182
1.0986	9.0	27612	1.0986	0.3274

Framework versions

• Transformers 4.30.2
• Pytorch 1.14.0a0+410ce96
• Datasets 2.13.0
• Tokenizers 0.13.3