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

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

• Loss: 1.0963
• Accuracy: 0.7034
• F1: 0.7738

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
0.5884	4.35	500	0.5523	0.7059	0.8046
0.4494	8.7	1000	0.5547	0.7574	0.8358
0.304	13.04	1500	0.6339	0.7525	0.8256
0.1927	17.39	2000	0.7843	0.7230	0.8000
0.1179	21.74	2500	1.0963	0.7034	0.7738

Framework versions

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