e7858a945edb8bfe2175e1ac61eda800

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

• Loss: 1.1871
• Data Size: 1.0
• Epoch Runtime: 102.9865
• Accuracy: 0.6860
• F1 Macro: 0.6014

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	1.7126	0	7.4996	0.2257	0.0741
No log	1	1973	1.4152	0.0078	8.3311	0.3853	0.1112
0.028	2	3946	0.9820	0.0156	9.5258	0.5941	0.4098
0.9408	3	5919	1.0069	0.0312	10.8212	0.5965	0.4309
0.8456	4	7892	0.8304	0.0625	13.5053	0.6566	0.5601
0.831	5	9865	0.7916	0.125	19.5240	0.6712	0.5776
0.7491	6	11838	0.7707	0.25	31.6183	0.6814	0.5857
0.7654	7	13811	0.7548	0.5	55.3879	0.6820	0.6288
0.6792	8.0	15784	0.7310	1.0	103.7087	0.6980	0.6349
0.5445	9.0	17757	0.7809	1.0	102.4546	0.7011	0.6198
0.4374	10.0	19730	0.8354	1.0	104.5739	0.6833	0.6246
0.3303	11.0	21703	0.9831	1.0	103.9458	0.6859	0.6230
0.2541	12.0	23676	1.1871	1.0	102.9865	0.6860	0.6014

Framework versions

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