lora-llama-3.2b-instruct

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0351

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: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.119	0.3125	50	0.1116
0.0695	0.625	100	0.0709
0.049	0.9375	150	0.0506
0.05	1.25	200	0.0436
0.0367	1.5625	250	0.0398
0.033	1.875	300	0.0376
0.03	2.1875	350	0.0362
0.0312	2.5	400	0.0355
0.0299	2.8125	450	0.0351

Framework versions

• PEFT 0.14.0
• Transformers 4.51.1
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.0