15d366de1778a2f1ee1daf3765cc56f4

This model is a fine-tuned version of openai-community/gpt2 on the contemmcm/amazon_reviews_2013 [cell-phone] dataset. It achieves the following results on the evaluation set:

• Loss: 1.0339
• Data Size: 1.0
• Epoch Runtime: 149.1960
• Accuracy: 0.6877
• F1 Macro: 0.6175

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	5.8736	0	13.4380	0.3847	0.1131
No log	1	1973	1.4858	0.0078	15.1347	0.3860	0.1953
0.0376	2	3946	1.2614	0.0156	15.7584	0.5267	0.2982
1.0842	3	5919	1.1491	0.0312	18.0205	0.5544	0.3924
0.9091	4	7892	0.8382	0.0625	22.8577	0.6465	0.5485
0.8384	5	9865	0.8106	0.125	30.9092	0.6588	0.5433
0.7894	6	11838	0.7907	0.25	47.1153	0.6727	0.5656
0.7906	7	13811	0.7374	0.5	82.6121	0.6917	0.6146
0.725	8.0	15784	0.7290	1.0	149.7056	0.6928	0.6156
0.6145	9.0	17757	0.7366	1.0	149.5340	0.7023	0.6201
0.502	10.0	19730	0.7699	1.0	151.9729	0.6959	0.6293
0.455	11.0	21703	0.8716	1.0	156.7626	0.6923	0.6145
0.3554	12.0	23676	1.0339	1.0	149.1960	0.6877	0.6175

Framework versions

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