9dd352624e99ac85475c7981d940ac85

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

• Loss: 0.6636
• Data Size: 1.0
• Epoch Runtime: 31.5156
• 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	1.0209	0	3.3662	0.3787	0.2747	0.3787	0.0	0.3793	0.3790
No log	1	294	0.7434	0.0078	4.1629	0.3787	0.2747	0.3787	0.0	0.3793	0.3790
No log	2	588	0.6738	0.0156	4.1549	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
No log	3	882	0.6516	0.0312	5.3953	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0277	4	1176	0.6394	0.0625	6.2871	0.6216	0.3849	0.6216	0.0	0.6210	0.6213
0.0542	5	1470	0.6428	0.125	7.8398	0.6562	0.6019	0.6562	0.0	0.6562	0.6566
0.0883	6	1764	0.6936	0.25	11.6418	0.5904	0.5891	0.5901	0.0	0.5901	0.5904
0.5484	7	2058	0.5936	0.5	17.9271	0.6599	0.6598	0.6598	0.0	0.6596	0.6599
0.51	8.0	2352	0.5727	1.0	33.1113	0.7163	0.6475	0.7163	0.0	0.7166	0.7166
0.4658	9.0	2646	0.5971	1.0	31.7870	0.7540	0.7316	0.7541	0.0	0.7537	0.7537
0.6861	10.0	2940	0.6659	1.0	31.8436	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6839	11.0	3234	0.6661	1.0	32.2225	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6805	12.0	3528	0.6636	1.0	31.5156	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