Llama-3.2-1B-Instruct-tuned

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: 2.2766

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: 0.01
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	12.3951
No log	0.2004	27	5.5223
No log	0.4007	54	3.8031
No log	0.6011	81	3.1578
No log	0.8015	108	2.8569
No log	1.0	135	2.6538
No log	1.2004	162	2.4921
No log	1.4007	189	2.3860
No log	1.6011	216	2.3240
No log	1.8015	243	2.2894
No log	2.0	270	2.2766

Framework versions

• PEFT 0.15.2
• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1