83c20a06d5fec7d21887569c1f2eacd3

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the nyu-mll/glue [sst2] dataset. It achieves the following results on the evaluation set:

• Loss: 0.4087
• Data Size: 1.0
• Epoch Runtime: 54.9262
• Accuracy: 0.8889
• F1 Macro: 0.8888
• Rouge1: 0.8889
• Rouge2: 0.0
• Rougel: 0.8889
• Rougelsum: 0.8889

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	0.6973	0	0.8355	0.4306	0.3605	0.4306	0.0	0.4306	0.4306
No log	1	2104	0.5524	0.0078	1.4001	0.8032	0.8030	0.8032	0.0	0.8032	0.8032
No log	2	4208	0.4644	0.0156	1.7952	0.7998	0.7951	0.7998	0.0	0.8003	0.7998
0.0092	3	6312	0.3848	0.0312	2.9598	0.8403	0.8384	0.8403	0.0	0.8403	0.8403
0.3308	4	8416	0.2790	0.0625	4.3496	0.8796	0.8796	0.8796	0.0	0.8796	0.8796
0.2593	5	10520	0.2675	0.125	7.8111	0.8877	0.8877	0.8877	0.0	0.8877	0.8877
0.1825	6	12624	0.2665	0.25	14.5150	0.8889	0.8888	0.8889	0.0	0.8889	0.8900
0.1898	7	14728	0.2858	0.5	28.0384	0.8958	0.8955	0.8958	0.0	0.8958	0.8970
0.142	8.0	16832	0.2887	1.0	55.0314	0.8958	0.8958	0.8958	0.0	0.8958	0.8958
0.0973	9.0	18936	0.3160	1.0	55.0581	0.8958	0.8958	0.8958	0.0	0.8958	0.8970
0.0925	10.0	21040	0.4087	1.0	54.9262	0.8889	0.8888	0.8889	0.0	0.8889	0.8889

Framework versions

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