Llama3.2-1B-SETBOX

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.7350

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.3077	10.0	10	3.5028
0.1409	20.0	20	3.2245
0.0007	30.0	30	3.3852
0.0001	40.0	40	3.9938
0.0	50.0	50	4.4237
0.0	60.0	60	4.6380
0.0	70.0	70	4.7116
0.0	80.0	80	4.7325
0.0	90.0	90	4.7363
0.0	100.0	100	4.7350

Framework versions

• PEFT 0.10.0
• Transformers 4.44.2
• Pytorch 2.5.1+cu124
• Datasets 2.14.4
• Tokenizers 0.19.1