du33169/t5-base-finetuned-GLUE-RTE

RTE

This model is a fine-tuned version of google-t5/t5-base on the GLUE RTE dataset. It achieves the following results on the evaluation set:

• Loss: 0.7698
• Accuracy: 0.6931

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	78	0.6982	0.4946
No log	2.0	156	0.6822	0.5632
No log	3.0	234	0.6642	0.5921
No log	4.0	312	0.6545	0.6101
No log	5.0	390	0.6433	0.6390
No log	6.0	468	0.6844	0.6606
0.5942	7.0	546	0.7054	0.6462
0.5942	8.0	624	0.7449	0.6643
0.5942	9.0	702	0.7662	0.6715
0.5942	10.0	780	0.7698	0.6931

Framework versions

• Transformers 4.43.3
• Pytorch 1.11.0+cu113
• Datasets 2.20.0
• Tokenizers 0.19.1