opt-350m-snli-model1

This model is a fine-tuned version of facebook/opt-350m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0012
• Accuracy: 0.752

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: 256
• eval_batch_size: 256
• seed: 32
• 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
0.33	1.0	2146	0.2674	0.8998
0.2369	2.0	4292	0.2634	0.9070
0.1527	3.0	6438	0.3009	0.9087

Framework versions

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