mobilebert_add_GLUE_Experiment_logit_kd_pretrain_sst2

This model is a fine-tuned version of gokuls/mobilebert_add_pre-training-complete on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Accuracy: 0.4908

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	527	nan	0.4908
0.0	2.0	1054	nan	0.4908
0.0	3.0	1581	nan	0.4908
0.0	4.0	2108	nan	0.4908
0.0	5.0	2635	nan	0.4908
0.0	6.0	3162	nan	0.4908

Framework versions

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