1ddadf358a43781f4f77a62ec93456a8

This model is a fine-tuned version of openai-community/gpt2-xl on the nyu-mll/glue [sst2] dataset. It achieves the following results on the evaluation set:

• Loss: 0.2855
• Data Size: 1.0
• Epoch Runtime: 565.6970
• Accuracy: 0.9074
• F1 Macro: 0.9074
• Rouge1: 0.9062
• Rouge2: 0.0
• Rougel: 0.9074
• Rougelsum: 0.9074

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	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	0.6573	0	3.1311	0.5822	0.5123	0.5822	0.0	0.5822	0.5822
No log	1	2104	0.7292	0.0078	8.8952	0.5671	0.4606	0.5671	0.0	0.5671	0.5671
No log	2	4208	0.2454	0.0156	14.8480	0.9062	0.9059	0.9062	0.0	0.9062	0.9062
0.0106	3	6312	0.3468	0.0312	26.5797	0.8646	0.8644	0.8634	0.0	0.8646	0.8634
0.2847	4	8416	0.2535	0.0625	46.0030	0.9016	0.9015	0.9016	0.0	0.9028	0.9016
0.2646	5	10520	0.2680	0.125	81.3585	0.8970	0.8969	0.8970	0.0	0.8970	0.8970
0.1822	6	12624	0.2434	0.25	146.5126	0.9155	0.9154	0.9155	0.0	0.9167	0.9155
0.1837	7	14728	0.2491	0.5	285.5312	0.9028	0.9027	0.9028	0.0	0.9028	0.9028
0.1591	8.0	16832	0.2484	1.0	564.9859	0.9005	0.9004	0.9005	0.0	0.9005	0.9016
0.1095	9.0	18936	0.2679	1.0	560.4997	0.9109	0.9108	0.9109	0.0	0.9109	0.9109
0.1014	10.0	21040	0.2855	1.0	565.6970	0.9074	0.9074	0.9062	0.0	0.9074	0.9074

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1