bert-large-cased-snli-model1

This model is a fine-tuned version of bert-large-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2434
• Accuracy: 0.9188

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: 512
• eval_batch_size: 512
• seed: 43
• 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
0.3253	1.0	1073	0.2511	0.9069
0.2555	2.0	2146	0.2410	0.9159
0.2094	3.0	3219	0.2434	0.9188

Framework versions

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