c7869d92504d98a2f570e6b9c86836a7

This model is a fine-tuned version of facebook/opt-2.7b on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 0.6713
• Data Size: 1.0
• Epoch Runtime: 114.2150
• 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	0.7470	0	9.8304	0.5432	0.5264	0.5426	0.0	0.5432	0.5435
No log	1	294	2.1108	0.0078	10.8747	0.3928	0.3050	0.3928	0.0	0.3934	0.3928
No log	2	588	1.0130	0.0156	14.0843	0.4105	0.3478	0.4108	0.0	0.4108	0.4105
No log	3	882	0.7764	0.0312	19.7477	0.4712	0.4696	0.4712	0.0	0.4715	0.4712
0.0418	4	1176	0.7474	0.0625	25.6370	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0624	5	1470	0.6638	0.125	31.6751	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.1026	6	1764	0.8814	0.25	46.9062	0.3787	0.2747	0.3787	0.0	0.3793	0.3790
0.723	7	2058	0.7458	0.5	70.6913	0.3885	0.2990	0.3886	0.0	0.3888	0.3888
0.669	8.0	2352	0.7560	1.0	116.9018	0.3827	0.2967	0.3830	0.0	0.3830	0.3827
0.6902	9.0	2646	0.6713	1.0	114.2150	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