opt-350m-finetuned-mnli-mm

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: 3.0148
• Accuracy: 0.5163

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	3.0148	0.5163
No log	2.0	2	1.7303	0.5153
No log	3.0	3	0.9062	0.4932
No log	4.0	4	1.1445	0.4908
No log	5.0	5	1.3091	0.4863
No log	6.0	6	1.2249	0.4901
No log	7.0	7	1.0692	0.4935
No log	8.0	8	0.9502	0.5031
No log	9.0	9	0.9018	0.5054
No log	10.0	10	0.8909	0.5089

Framework versions

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