llama3_1b_xsum_lora-finalmodel

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: 1.8001

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• 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: 1

Training results

Training Loss	Epoch	Step	Validation Loss
1.9495	0.0784	2000	1.9472
1.916	0.1568	4000	1.8971
1.8764	0.2352	6000	1.8705
1.888	0.3137	8000	1.8549
1.8387	0.3921	10000	1.8423
1.872	0.4705	12000	1.8342
1.8299	0.5489	14000	1.8244
1.8417	0.6273	16000	1.8188
1.8185	0.7057	18000	1.8116
1.8218	0.7841	20000	1.8073
1.8071	0.8626	22000	1.8029
1.8267	0.9410	24000	1.8001

Framework versions

• PEFT 0.17.1
• Transformers 4.57.1
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.22.1