4036feb458456f0f866194cccd0fa92a

This model is a fine-tuned version of facebook/opt-125m on the contemmcm/amazon_reviews_2013 [cell-phone] dataset. It achieves the following results on the evaluation set:

• Loss: 1.2041
• Data Size: 1.0
• Epoch Runtime: 150.9189
• Accuracy: 0.6651
• F1 Macro: 0.5909

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	1.8512	0	12.5388	0.1432	0.1321
No log	1	1973	1.2755	0.0078	13.7722	0.4698	0.3184
0.0266	2	3946	0.9072	0.0156	14.7337	0.6216	0.5362
0.9275	3	5919	0.9740	0.0312	16.8026	0.5971	0.5001
0.8562	4	7892	0.8652	0.0625	21.2712	0.6425	0.5705
0.8258	5	9865	0.8531	0.125	29.5289	0.6488	0.5225
0.7637	6	11838	0.7876	0.25	47.0536	0.6697	0.5662
0.7884	7	13811	0.7574	0.5	80.0012	0.6848	0.6130
0.706	8.0	15784	0.7417	1.0	149.7164	0.6889	0.6259
0.5859	9.0	17757	0.7810	1.0	150.1929	0.6938	0.6130
0.4151	10.0	19730	0.9515	1.0	148.7351	0.6469	0.6042
0.344	11.0	21703	1.1042	1.0	150.7246	0.6741	0.6083
0.2612	12.0	23676	1.2041	1.0	150.9189	0.6651	0.5909

Framework versions

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