peft-my_model

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

• Loss: 1.3404

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 8
• seed: 1234
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
1.5275	0.2665	50	1.4034
1.3807	0.5330	100	1.3815
1.3537	0.7995	150	1.3723
1.3702	1.0640	200	1.3674
1.3621	1.3304	250	1.3645
1.338	1.5969	300	1.3618
1.3472	1.8634	350	1.3605
1.3353	2.1279	400	1.3595
1.3261	2.3944	450	1.3588
1.3333	2.6609	500	1.3584
1.3434	2.9274	550	1.3579

Framework versions

• PEFT 0.17.1
• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 3.6.0
• Tokenizers 0.22.1