results

This model is a fine-tuned version of unsloth/llama-3.2-1b-unsloth-bnb-4bit on the None dataset. It achieves the following results on the evaluation set:

• Loss: 7.2083

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: 4
• eval_batch_size: 4
• seed: 42
• 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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
13.3929	1.0	43	7.2656
11.4271	2.0	86	7.2669
11.0609	3.0	129	7.3441
10.097	4.0	172	7.6927
8.2179	5.0	215	7.7197
7.1093	6.0	258	7.6223
6.3082	7.0	301	7.5638
5.8958	8.0	344	7.4709
5.7789	9.0	387	7.3977
5.5157	10.0	430	7.3469
5.3691	11.0	473	7.3023
5.4559	12.0	516	7.2700
5.3126	13.0	559	7.2285
5.2435	14.0	602	7.2138
5.3684	15.0	645	7.2083

Framework versions

• PEFT 0.14.0
• Transformers 4.48.3
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0