en-tel

This model is a fine-tuned version of unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:

• Loss: 20.6121

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• 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
• lr_scheduler_warmup_steps: 100
• num_epochs: 7
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
9.7358	1.2195	50	10.6668
6.2205	2.4390	100	24.3387
5.3569	3.6585	150	22.8831
5.1264	4.8780	200	21.4727
5.0125	6.0976	250	20.6121

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0