6269e575b46336984c5cf00313ecaf59

This model is a fine-tuned version of distilbert/distilroberta-base on the contemmcm/amazon_reviews_2013 [cell-phone] dataset. It achieves the following results on the evaluation set:

• Loss: 0.9222
• Data Size: 1.0
• Epoch Runtime: 108.3090
• Accuracy: 0.6990
• F1 Macro: 0.6312

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	1.6195	0	10.9986	0.1857	0.0694
No log	1	1973	1.2618	0.0078	12.0127	0.5240	0.2679
0.0276	2	3946	1.0377	0.0156	12.8600	0.5638	0.3347
0.9435	3	5919	0.9777	0.0312	14.4464	0.5997	0.4247
0.89	4	7892	0.8614	0.0625	17.8899	0.6449	0.5632
0.8396	5	9865	0.7977	0.125	24.1189	0.6720	0.5851
0.77	6	11838	0.7629	0.25	37.3497	0.6866	0.5987
0.7886	7	13811	0.7437	0.5	62.9690	0.6864	0.6276
0.7216	8.0	15784	0.7383	1.0	114.9539	0.6978	0.6341
0.6122	9.0	17757	0.7680	1.0	115.6121	0.7007	0.6259
0.5309	10.0	19730	0.8616	1.0	111.2900	0.6628	0.6179
0.4582	11.0	21703	0.8959	1.0	109.8580	0.6909	0.6217
0.4109	12.0	23676	0.9222	1.0	108.3090	0.6990	0.6312

Framework versions

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