mobilebert_add_GLUE_Experiment_logit_kd_pretrain_mnli

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

• Loss: nan
• Accuracy: 0.3522

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: 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
0.0	1.0	3068	nan	0.3545
0.0	2.0	6136	nan	0.3545
0.0	3.0	9204	nan	0.3545
0.0	4.0	12272	nan	0.3545
0.0	5.0	15340	nan	0.3545
0.0	6.0	18408	nan	0.3545

Framework versions

• Transformers 4.26.0
• Pytorch 1.14.0a0+410ce96
• Datasets 2.9.0
• Tokenizers 0.13.2