small-mlm-glue-mrpc-target-glue-rte

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

• Loss: 3.5597
• Accuracy: 0.6245

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	Accuracy
0.4061	6.41	500	1.4142	0.6282
0.0518	12.82	1000	2.5075	0.6101
0.0239	19.23	1500	2.7691	0.6209
0.0192	25.64	2000	3.0528	0.6354
0.0183	32.05	2500	3.3188	0.6137
0.0158	38.46	3000	3.3546	0.6137
0.0102	44.87	3500	3.5597	0.6245

Framework versions

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