tiny-mlm-glue-mrpc-from-scratch-custom-tokenizer-target-glue-wnli

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

• Loss: 1.5713
• Accuracy: 0.1127

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
0.6933	25.0	500	0.6928	0.5352
0.6841	50.0	1000	0.8358	0.2535
0.6609	75.0	1500	1.0305	0.1549
0.6149	100.0	2000	1.5713	0.1127

Framework versions

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