train_mrpc_123_1760637675

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the mrpc dataset. It achieves the following results on the evaluation set:

• Loss: 0.6401
• Num Input Tokens Seen: 6014864

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 123
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Input Tokens Seen
0.1366	2.0	1468	0.1702	601232
0.2231	4.0	2936	0.1508	1202944
0.1763	6.0	4404	0.1656	1805120
0.0984	8.0	5872	0.2230	2406704
0.0064	10.0	7340	0.3272	3008096
0.0177	12.0	8808	0.4660	3609744
0.0	14.0	10276	0.5128	4210656
0.0003	16.0	11744	0.6373	4812752
0.0	18.0	13212	0.6367	5414352
0.0	20.0	14680	0.6401	6014864

Framework versions

• PEFT 0.17.1
• Transformers 4.51.3
• Pytorch 2.9.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4