896ca2d686134cd518f700a5b54da6d7

This model is a fine-tuned version of albert/albert-xlarge-v1 on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 0.6850
• Data Size: 0.5
• Epoch Runtime: 23.6812
• 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	0.7318	0	4.4223	0.5061	0.4975	0.5058	0.0	0.5064	0.5058
No log	1	294	0.6988	0.0078	4.9902	0.5913	0.4290	0.5919	0.0	0.5904	0.5916
No log	2	588	0.6868	0.0156	5.1220	0.5270	0.5123	0.5270	0.0	0.5267	0.5267
No log	3	882	0.6748	0.0312	5.8715	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0295	4	1176	0.6955	0.0625	7.0545	0.3787	0.2747	0.3787	0.0	0.3793	0.3790
0.0567	5	1470	0.6790	0.125	9.3494	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0969	6	1764	0.7311	0.25	14.1797	0.3891	0.3022	0.3888	0.0	0.3894	0.3894
0.6889	7	2058	0.6850	0.5	23.6812	0.6213	0.3832	0.6213	0.0	0.6207	0.6210

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.1