a9df448ebd798e4ac1ba00288d5da42d

This model is a fine-tuned version of studio-ousia/mluke-large on the nyu-mll/glue [mnli] dataset. It achieves the following results on the evaluation set:

• Loss: 1.1005
• Data Size: 1.0
• Epoch Runtime: 2103.3780
• Accuracy: 0.3545
• F1 Macro: 0.1745
• Rouge1: 0.3544
• Rouge2: 0.0
• Rougel: 0.3545
• Rougelsum: 0.3543

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	1.1022	0	15.1394	0.3297	0.2701	0.3297	0.0	0.3296	0.3297
1.1151	1	12271	1.0998	0.0078	31.1871	0.3182	0.1609	0.3184	0.0	0.3182	0.3183
1.1043	2	24542	1.1010	0.0156	49.5219	0.3273	0.1644	0.3273	0.0	0.3275	0.3277
1.1008	3	36813	1.0985	0.0312	79.9591	0.3273	0.1644	0.3273	0.0	0.3275	0.3277
1.0998	4	49084	1.0989	0.0625	143.9952	0.3182	0.1609	0.3184	0.0	0.3182	0.3183
1.1009	5	61355	1.0978	0.125	270.0645	0.3273	0.1644	0.3273	0.0	0.3275	0.3277
1.1056	6	73626	1.1053	0.25	525.0743	0.3182	0.1609	0.3184	0.0	0.3182	0.3183
1.1009	7	85897	1.0962	0.5	1041.8637	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.0989	8.0	98168	1.0978	1.0	2061.0580	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.0989	9.0	110439	1.1013	1.0	2060.9194	0.3273	0.1644	0.3273	0.0	0.3275	0.3277
1.1006	10.0	122710	1.0997	1.0	2069.1465	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.1	11.0	134981	1.1005	1.0	2103.3780	0.3545	0.1745	0.3544	0.0	0.3545	0.3543

Framework versions

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