gpt2-large-snli-model3

This model is a fine-tuned version of openai-community/gpt2-large on the snli dataset. It achieves the following results on the evaluation set:

• Loss: 0.2891
• Accuracy: 0.9145

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: 2e-05
• train_batch_size: 128
• eval_batch_size: 128
• seed: 87
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3125	1.0	4292	0.2509	0.9126
0.2233	2.0	8584	0.2487	0.9143
0.1424	3.0	12876	0.2891	0.9145

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0