75ba58b67e17a6cd07aec07b9db1310e

This model is a fine-tuned version of albert/albert-base-v2 on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 0.6633
• Data Size: 1.0
• Epoch Runtime: 12.6546
• 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	0.7087	0	1.8618	0.4589	0.4490	0.4586	0.0	0.4589	0.4586
No log	1	294	0.6777	0.0078	2.4637	0.6170	0.3955	0.6167	0.0	0.6164	0.6170
No log	2	588	0.6773	0.0156	2.0513	0.5744	0.5065	0.5744	0.0	0.5748	0.5741
No log	3	882	0.6634	0.0312	2.2265	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0272	4	1176	0.6662	0.0625	2.5949	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0552	5	1470	0.6660	0.125	3.2348	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0958	6	1764	0.6686	0.25	4.5856	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.664	7	2058	0.6633	0.5	7.1682	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6622	8.0	2352	0.6647	1.0	12.9353	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6708	9.0	2646	0.6632	1.0	12.6634	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6646	10.0	2940	0.6667	1.0	12.6537	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6762	11.0	3234	0.6633	1.0	12.6628	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.665	12.0	3528	0.6636	1.0	12.6599	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6679	13.0	3822	0.6633	1.0	12.6546	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