fa581602ac347fd04894cdf45dfa1041

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

• Loss: 1.0977
• Data Size: 1.0
• Epoch Runtime: 1125.1428
• 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	1.1676	0	7.9672	0.3354	0.2047	0.3354	0.0	0.3357	0.3353
1.1317	1	12271	1.1005	0.0078	18.0915	0.3182	0.1609	0.3184	0.0	0.3182	0.3183
1.1193	2	24542	1.0977	0.0156	26.7213	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.1241	3	36813	1.0957	0.0312	44.1442	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.1214	4	49084	1.0950	0.0625	79.1851	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.1104	5	61355	1.0975	0.125	148.0363	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.105	6	73626	1.1091	0.25	285.2391	0.3182	0.1609	0.3184	0.0	0.3182	0.3183
1.1031	7	85897	1.0989	0.5	568.7817	0.3545	0.1745	0.3544	0.0	0.3545	0.3543
1.1003	8.0	98168	1.0977	1.0	1125.1428	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