distilbert_sa_GLUE_Experiment_cola

This model is a fine-tuned version of distilbert-base-uncased on the GLUE COLA dataset. It achieves the following results on the evaluation set:

• Loss: 0.6150
• Matthews Correlation: -0.0293

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: 256
• eval_batch_size: 256
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Matthews Correlation
0.6207	1.0	34	0.6165	0.0
0.6034	2.0	68	0.6150	-0.0293
0.5759	3.0	102	0.6505	-0.0293
0.5443	4.0	136	0.6320	0.0549
0.4957	5.0	170	0.6662	0.1327
0.4623	6.0	204	0.7247	0.0675
0.4249	7.0	238	0.7533	0.0972

Framework versions

• Transformers 4.26.0
• Pytorch 1.14.0a0+410ce96
• Datasets 2.8.0
• Tokenizers 0.13.2