6b35e6ac34710df5171ac11349bb7612

This model is a fine-tuned version of facebook/opt-350m on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 0.6671
• Data Size: 1.0
• Epoch Runtime: 46.0515
• 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	1.0675	0	5.4791	0.4887	0.4871	0.4887	0.0	0.4890	0.4885
No log	1	294	3.7971	0.0078	6.2825	0.3796	0.2794	0.3799	0.0	0.3799	0.3796
No log	2	588	0.8807	0.0156	6.2088	0.6103	0.3961	0.6106	0.0	0.6100	0.6100
No log	3	882	0.8784	0.0312	7.5796	0.3854	0.2930	0.3854	0.0	0.3860	0.3857
0.0424	4	1176	0.7252	0.0625	8.7711	0.6213	0.3847	0.6216	0.0	0.6210	0.6212
0.0563	5	1470	0.6955	0.125	12.1851	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0948	6	1764	0.7569	0.25	16.9797	0.3784	0.2745	0.3784	0.0	0.3787	0.3784
0.6702	7	2058	0.6799	0.5	26.0937	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6661	8.0	2352	0.6681	1.0	46.4669	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6839	9.0	2646	0.7078	1.0	46.0776	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.676	10.0	2940	0.6702	1.0	45.8669	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6752	11.0	3234	0.6633	1.0	47.0501	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.67	12.0	3528	0.6635	1.0	45.9442	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6738	13.0	3822	0.6636	1.0	46.0966	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6671	14.0	4116	0.6639	1.0	47.0798	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.6745	15.0	4410	0.6671	1.0	46.0515	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