e110950490e0357d7cdad96d4c704b90

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the contemmcm/amazon_reviews_2013 [cell-phone] dataset. It achieves the following results on the evaluation set:

• Loss: 5.6949
• Data Size: 1.0
• Epoch Runtime: 415.5165
• Accuracy: 0.6221
• F1 Macro: 0.5272

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro
No log	0	0	8.3784	0	27.9869	0.3768	0.1584
No log	1	1973	7.2604	0.0078	31.0134	0.3853	0.1112
0.2138	2	3946	5.9853	0.0156	34.3964	0.3853	0.1112
5.9565	3	5919	5.9152	0.0312	41.3593	0.3853	0.1112
13.0347	4	7892	6.1092	0.0625	54.2843	0.3269	0.1978
4.6922	5	9865	4.2377	0.125	78.5533	0.5837	0.4152
3.784	6	11838	3.6718	0.25	127.0097	0.6229	0.4521
3.6746	7	13811	3.4459	0.5	223.6140	0.6334	0.5609
3.1842	8.0	15784	3.4746	1.0	415.0937	0.6365	0.5611
2.5682	9.0	17757	3.7491	1.0	411.8911	0.6316	0.5459
1.9125	10.0	19730	4.2391	1.0	413.2380	0.5993	0.5463
1.4109	11.0	21703	5.6949	1.0	415.5165	0.6221	0.5272

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1