0c4b852bd4b5215dce3c285f32ad7f8b

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

• Loss: 0.6438
• Data Size: 1.0
• Epoch Runtime: 14.6836
• Accuracy: 0.6651
• F1 Macro: 0.3994
• Rouge1: 0.6657
• Rouge2: 0.0
• Rougel: 0.6645
• Rougelsum: 0.6651

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	0.7208	0	1.9003	0.4935	0.4380	0.4935	0.0	0.4935	0.4941
No log	1	114	0.6822	0.0078	3.2793	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
No log	2	228	0.6355	0.0156	2.6180	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
No log	3	342	0.6397	0.0312	3.2506	0.6692	0.4158	0.6698	0.0	0.6692	0.6692
0.0214	4	456	0.6234	0.0625	4.2255	0.6857	0.4811	0.6857	0.0	0.6857	0.6857
0.0214	5	570	0.6549	0.125	5.2374	0.6686	0.4219	0.6692	0.0	0.6683	0.6686
0.0214	6	684	0.6680	0.25	6.1767	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.1567	7	798	0.6387	0.5	8.7699	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.6544	8.0	912	0.6438	1.0	14.6836	0.6651	0.3994	0.6657	0.0	0.6645	0.6651

Framework versions

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