opt-125m-finetuned-mnli

This model is a fine-tuned version of facebook/opt-125m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7805
• Accuracy: 0.5182

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	0.8038	0.5185
No log	2.0	2	0.8023	0.5182
No log	3.0	3	0.8011	0.5182
No log	4.0	4	0.8003	0.5184
No log	5.0	5	0.7993	0.5184
No log	6.0	6	0.7982	0.5184
No log	7.0	7	0.7974	0.5182
No log	8.0	8	0.7968	0.5182
No log	9.0	9	0.7962	0.5181
No log	10.0	10	0.7960	0.5182

Framework versions

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