4795e75624d0b09d640f07c2b61bdcbe

This model is a fine-tuned version of google-bert/bert-large-uncased-whole-word-masking-finetuned-squad on the nyu-mll/glue [qqp] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6585
• Data Size: 0.25
• Epoch Runtime: 291.4261
• Accuracy: 0.6320
• F1 Macro: 0.3872
• Rouge1: 0.6318
• Rouge2: 0.0
• Rougel: 0.6319
• Rougelsum: 0.6317

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	0.7416	0	31.5648	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.5709	1	11370	0.5047	0.0078	41.2103	0.7863	0.7520	0.7863	0.0	0.7864	0.7862
0.4432	2	22740	0.4137	0.0156	48.3811	0.8154	0.8080	0.8155	0.0	0.8154	0.8154
0.4486	3	34110	0.6769	0.0312	65.7942	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6769	4	45480	0.6609	0.0625	97.6886	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6671	5	56850	0.6578	0.125	161.6947	0.6320	0.3872	0.6318	0.0	0.6319	0.6317
0.6654	6	68220	0.6585	0.25	291.4261	0.6320	0.3872	0.6318	0.0	0.6319	0.6317

Framework versions

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