opt-1.3b-lora-3.15M-snli-model2

This model is a fine-tuned version of facebook/opt-1.3b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6840
• Accuracy: 0.755

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: 25
• 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
0.3528	1.0	4292	0.2888	0.8930
0.3296	2.0	8584	0.2705	0.9012
0.3158	3.0	12876	0.2617	0.9040

Framework versions

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