0c6b48b0be1d072ace628ecf9b322cdc

This model is a fine-tuned version of google-bert/bert-base-chinese on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 0.6830
• Data Size: 1.0
• Epoch Runtime: 16.0583
• Accuracy: 0.6213
• F1 Macro: 0.3832
• Rouge1: 0.6213
• Rouge2: 0.0
• Rougel: 0.6207
• Rougelsum: 0.6210

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	0.6912	0	1.9915	0.5322	0.5027	0.5319	0.0	0.5322	0.5325
No log	1	294	0.6785	0.0078	2.5234	0.5879	0.4535	0.5876	0.0	0.5882	0.5882
No log	2	588	0.6680	0.0156	2.3196	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
No log	3	882	0.6640	0.0312	2.6140	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0277	4	1176	0.6633	0.0625	3.0651	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0562	5	1470	0.6783	0.125	4.1088	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.098	6	1764	0.6831	0.25	5.7546	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6706	7	2058	0.6634	0.5	9.2526	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6701	8.0	2352	0.6632	1.0	15.9133	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6907	9.0	2646	0.6634	1.0	15.7746	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.682	10.0	2940	0.6647	1.0	16.4924	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6816	11.0	3234	0.6654	1.0	15.4475	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6726	12.0	3528	0.6627	1.0	15.5203	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6807	13.0	3822	0.6633	1.0	16.2722	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.682	14.0	4116	0.6678	1.0	15.6432	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6798	15.0	4410	0.6669	1.0	15.9516	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6746	16.0	4704	0.6830	1.0	16.0583	0.6213	0.3832	0.6213	0.0	0.6207	0.6210

Framework versions

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