opt-125m-finetuned-rte

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: 1.0060
• Accuracy: 0.4729

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	0.9768	0.4765
No log	2.0	2	0.9663	0.4729
No log	3.0	3	0.9564	0.4729
No log	4.0	4	0.9482	0.4729
No log	5.0	5	0.9415	0.4693
No log	6.0	6	0.9357	0.4693
No log	7.0	7	0.9311	0.4693
No log	8.0	8	0.9275	0.4693
No log	9.0	9	0.9251	0.4693
No log	10.0	10	0.9239	0.4693

Framework versions

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