small-mlm-glue-cola-target-glue-stsb

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

• Loss: 0.5924
• Pearson: 0.8702
• Spearmanr: 0.8670

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
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Pearson	Spearmanr
0.8465	2.78	500	0.6385	0.8629	0.8640
0.3057	5.56	1000	0.6068	0.8672	0.8660
0.1832	8.33	1500	0.6459	0.8605	0.8577
0.1291	11.11	2000	0.6158	0.8675	0.8646
0.1023	13.89	2500	0.6053	0.8692	0.8664
0.0842	16.67	3000	0.6038	0.8703	0.8667
0.0715	19.44	3500	0.5854	0.8718	0.8686
0.0631	22.22	4000	0.5695	0.8729	0.8692
0.0575	25.0	4500	0.5868	0.8716	0.8685
0.0525	27.78	5000	0.5924	0.8702	0.8670

Framework versions

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