Meta-Llama-2-13B-009-3000

This model is a fine-tuned version of meta-llama/Llama-2-13b-chat-hf on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2396

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6145	0.9927	102	0.6419
0.4791	1.9927	204	0.5388
0.4922	2.9927	306	0.4697
0.4222	3.9927	408	0.4105
0.3414	4.9927	510	0.3564
0.2968	5.9927	612	0.3099
0.2606	6.9927	714	0.2755
0.2241	7.9927	816	0.2545
0.2028	8.9927	918	0.2432
0.1867	9.9927	1020	0.2396

Framework versions

• PEFT 0.15.2
• Transformers 4.51.3
• Pytorch 2.7.0+cu126
• Datasets 3.5.1
• Tokenizers 0.21.1