mobilebert_add_GLUE_Experiment_logit_kd_pretrain_qqp

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

• Loss: nan
• Accuracy: 0.6318
• F1: 0.0
• Combined Score: 0.3159

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	F1	Combined Score
0.0	1.0	2843	nan	0.6318	0.0	0.3159
0.0	2.0	5686	nan	0.6318	0.0	0.3159
0.0	3.0	8529	nan	0.6318	0.0	0.3159
0.0	4.0	11372	nan	0.6318	0.0	0.3159
0.0	5.0	14215	nan	0.6318	0.0	0.3159
0.0	6.0	17058	nan	0.6318	0.0	0.3159

Framework versions

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