hBERTv1_new_pretrain_w_init_48_ver2_sst2

This model is a fine-tuned version of gokuls/bert_12_layer_model_v1_complete_training_new_wt_init_48 on the GLUE SST2 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6941
• Accuracy: 0.5092

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: 4e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 10
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6948	1.0	1053	0.6948	0.5092
0.6927	2.0	2106	0.6941	0.5092
0.6879	3.0	3159	0.7005	0.5092
0.6873	4.0	4212	0.7004	0.5092
0.6887	5.0	5265	0.7151	0.5092
0.6871	6.0	6318	0.6975	0.5092
0.6859	7.0	7371	0.7068	0.5092

Framework versions

• Transformers 4.34.0
• Pytorch 1.14.0a0+410ce96
• Datasets 2.14.5
• Tokenizers 0.14.1