en-tel-v3

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: 0.1658

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: 50
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.1951	8	0.3454
0.3684	0.3902	16	0.3086
0.3289	0.5854	24	0.2739
0.2734	0.7805	32	0.2460
0.2494	0.9756	40	0.2194
0.2494	1.1707	48	0.2002
0.2025	1.3659	56	0.1832
0.1898	1.5610	64	0.1723
0.1733	1.7561	72	0.1674
0.1753	1.9512	80	0.1658

Framework versions

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