tiny-mlm-glue-stsb-target-glue-mrpc

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

• Loss: 1.2364
• Accuracy: 0.7132
• F1: 0.8047

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	Accuracy	F1
0.5901	4.35	500	0.5567	0.7108	0.8072
0.4581	8.7	1000	0.5798	0.7377	0.8283
0.3115	13.04	1500	0.6576	0.7426	0.8247
0.197	17.39	2000	0.7977	0.7255	0.8152
0.1153	21.74	2500	1.0637	0.7059	0.7973
0.0843	26.09	3000	1.2364	0.7132	0.8047

Framework versions

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