mobilebert_add_GLUE_Experiment_logit_kd_pretrain_qnli

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

• Loss: nan
• Accuracy: 0.4946

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	819	nan	0.4946
0.0	2.0	1638	nan	0.4946
0.0	3.0	2457	nan	0.4946
0.0	4.0	3276	nan	0.4946
0.0	5.0	4095	nan	0.4946
0.0	6.0	4914	nan	0.4946

Framework versions

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