tiny-mlm-glue-qnli-target-glue-stsb

This model is a fine-tuned version of muhtasham/tiny-mlm-glue-qnli on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8934
• Pearson: 0.8154
• Spearmanr: 0.8157

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: 3e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr
2.952	2.78	500	1.1581	0.7199	0.7571
0.9583	5.56	1000	1.1118	0.7743	0.7995
0.7459	8.33	1500	0.9843	0.8028	0.8182
0.6197	11.11	2000	0.8616	0.8165	0.8217
0.5182	13.89	2500	0.9113	0.8140	0.8169
0.4676	16.67	3000	0.9804	0.8144	0.8183
0.4128	19.44	3500	0.8934	0.8154	0.8157

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu116
• Datasets 2.8.1.dev0
• Tokenizers 0.13.2