61391e0950ec98a1b443bcf9ff78261d

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

• Loss: 0.6940
• Data Size: 1.0
• Epoch Runtime: 305.0386
• Accuracy: 0.4943
• F1 Macro: 0.3308
• Rouge1: 0.4947
• Rouge2: 0.0
• Rougel: 0.4943
• Rougelsum: 0.4944

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	0.7108	0	4.6593	0.5256	0.4696	0.5256	0.0	0.5254	0.5254
No log	1	3273	0.6937	0.0078	7.3225	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.0116	2	6546	0.7210	0.0156	10.6195	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.716	3	9819	0.6947	0.0312	14.6452	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.7059	4	13092	0.6925	0.0625	24.8280	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.7018	5	16365	0.6936	0.125	43.4456	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.7079	6	19638	0.6965	0.25	80.4857	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6987	7	22911	0.7070	0.5	154.0918	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6965	8.0	26184	0.6940	1.0	305.0386	0.4943	0.3308	0.4947	0.0	0.4943	0.4944

Framework versions

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