Llama-2-7b-hf-finetuned-mrpc-v5

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the glue dataset. It achieves the following results on the evaluation set:

• Accuracy: 0.8578
• F1: 0.8986
• Loss: 0.6758

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Accuracy	F1	Validation Loss
0.733	1.0	917	0.6912	0.7974	0.6016
0.6103	2.0	1834	0.7402	0.8339	0.5650
0.508	3.0	2751	0.7525	0.8358	0.5246
0.5354	4.0	3668	0.7794	0.8529	0.5318
0.4246	5.0	4585	0.7843	0.8508	0.5279
0.4295	6.0	5502	0.7966	0.8591	0.5248
0.4473	7.0	6419	0.8162	0.8696	0.5169
0.419	8.0	7336	0.8260	0.8778	0.5552
0.3876	9.0	8253	0.8284	0.8776	0.5514
0.42	10.0	9170	0.8407	0.8862	0.5576
0.3678	11.0	10087	0.8480	0.8927	0.6212
0.3453	12.0	11004	0.8480	0.8916	0.6070
0.353	13.0	11921	0.8529	0.8958	0.6705
0.3257	14.0	12838	0.8407	0.8845	0.6579
0.3047	15.0	13755	0.8578	0.8986	0.6758

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3