bert_tiny_olda_book_10_v1_mnli

This model is a fine-tuned version of gokulsrinivasagan/bert_tiny_olda_book_10_v1 on the GLUE MNLI dataset. It achieves the following results on the evaluation set:

• Loss: 0.6019
• Accuracy: 0.7581

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 OptimizerNames.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
0.7814	1.0	1534	0.6793	0.7137
0.6299	2.0	3068	0.6363	0.7349
0.5472	3.0	4602	0.6204	0.7499
0.4774	4.0	6136	0.6359	0.7510
0.4143	5.0	7670	0.6501	0.7560
0.3584	6.0	9204	0.7101	0.7529
0.3097	7.0	10738	0.7401	0.7511
0.2648	8.0	12272	0.8199	0.7484

Framework versions

• Transformers 4.46.1
• Pytorch 2.2.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.1