opt-350m-finetuned-mnli

This model is a fine-tuned version of facebook/opt-350m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2789
• Accuracy: 0.5235

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	1.4105	0.4852
No log	2.0	2	1.1544	0.5132
No log	3.0	3	1.2071	0.5163
No log	4.0	4	1.0910	0.5094
No log	5.0	5	1.1394	0.5154
No log	6.0	6	1.1741	0.5185
No log	7.0	7	1.2318	0.5199
No log	8.0	8	1.2789	0.5235
No log	9.0	9	1.3077	0.5211
No log	10.0	10	1.3205	0.5202

Framework versions

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