b890082c567f9d454aa0709e7ee50afb

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

• Loss: 1.5555
• Data Size: 1.0
• Epoch Runtime: 563.4550
• Accuracy: 0.6819
• F1 Macro: 0.6179

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	1.8578	0	40.7235	0.1123	0.0933
No log	1	1973	0.9525	0.0078	45.2952	0.6073	0.5089
0.0238	2	3946	0.8428	0.0156	49.5352	0.6424	0.5546
0.8816	3	5919	0.8960	0.0312	60.0716	0.6184	0.4971
0.8347	4	7892	0.8353	0.0625	76.6967	0.6466	0.5765
0.7915	5	9865	0.7612	0.125	109.5614	0.6767	0.5513
0.7386	6	11838	0.7649	0.25	174.1360	0.6816	0.5650
0.7413	7	13811	0.7268	0.5	304.9475	0.6950	0.6375
0.6422	8.0	15784	0.7410	1.0	565.7611	0.6931	0.6220
0.4155	9.0	17757	0.8640	1.0	561.3008	0.6987	0.6148
0.2682	10.0	19730	1.1396	1.0	562.0894	0.6713	0.6217
0.157	11.0	21703	1.5555	1.0	563.4550	0.6819	0.6179

Framework versions

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