opt-350m-lora-1.57M-snli-model3

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: 0.8582
• Accuracy: 0.686

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: 75
• 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
0.5032	1.0	2146	0.4190	0.8378
0.4594	2.0	4292	0.3869	0.8562
0.4445	3.0	6438	0.3771	0.8623

Framework versions

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