opt-1.3b-finetuned-mnli

This model is a fine-tuned version of facebook/opt-1.3b on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7762
• Accuracy: 0.5027

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	1	0.7791	0.5057
No log	2.0	2	0.7755	0.5033
No log	3.0	3	0.7731	0.5001
No log	4.0	4	0.7716	0.4973
No log	5.0	5	0.7705	0.4963
No log	6.0	6	0.7698	0.4972
No log	7.0	7	0.7694	0.4963
No log	8.0	8	0.7691	0.4966
No log	9.0	9	0.7690	0.4961
No log	10.0	10	0.7690	0.4972

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1