f85fea88accc2e4b1983ba0004a5962c

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

• Loss: 0.6659
• Data Size: 1.0
• Epoch Runtime: 17.0290
• 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	0.6829	0	2.0073	0.5993	0.4286	0.5993	0.0	0.5990	0.5993
No log	1	294	0.6946	0.0078	2.3955	0.4743	0.4740	0.4741	0.0	0.4733	0.4740
No log	2	588	0.6677	0.0156	2.5218	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
No log	3	882	0.6976	0.0312	2.8379	0.5077	0.4880	0.5074	0.0	0.5070	0.5074
0.0271	4	1176	0.6640	0.0625	3.3485	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0551	5	1470	0.6754	0.125	4.4249	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0969	6	1764	0.6809	0.25	6.4441	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6639	7	2058	0.6636	0.5	10.2832	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6636	8.0	2352	0.6701	1.0	17.3765	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6732	9.0	2646	0.6641	1.0	16.9726	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6656	10.0	2940	0.6649	1.0	18.2063	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6756	11.0	3234	0.6630	1.0	16.9575	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6629	12.0	3528	0.6641	1.0	17.0325	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6683	13.0	3822	0.6637	1.0	17.9700	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6681	14.0	4116	0.6667	1.0	17.1390	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6714	15.0	4410	0.6659	1.0	17.0290	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