6092b68db85e70fdf09a4e82345627f1

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

• Loss: 0.6649
• Data Size: 1.0
• Epoch Runtime: 95.4464
• 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	0.7116	0	8.5900	0.5012	0.4998	0.5006	0.0	0.5012	0.5015
No log	1	294	0.7004	0.0078	9.2705	0.5450	0.4684	0.5453	0.0	0.5447	0.5447
No log	2	588	0.6827	0.0156	9.8441	0.6210	0.3854	0.6210	0.0	0.6207	0.6207
No log	3	882	0.6780	0.0312	11.1787	0.6088	0.4021	0.6086	0.0	0.6081	0.6088
0.0292	4	1176	0.6674	0.0625	13.4752	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0551	5	1470	0.6646	0.125	17.7182	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.1025	6	1764	0.6689	0.25	26.6261	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6826	7	2058	0.6676	0.5	44.2210	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6609	8.0	2352	0.6683	1.0	84.6792	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6732	9.0	2646	0.6649	1.0	95.4464	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