1e35191cec57bd7ac1b9c9b782f1c785

This model is a fine-tuned version of facebook/opt-6.7b on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 0.9631
• Data Size: 1.0
• Epoch Runtime: 264.1938
• Accuracy: 0.6520
• F1 Macro: 0.6310
• Rouge1: 0.6517
• Rouge2: 0.0
• Rougel: 0.6520
• Rougelsum: 0.6520

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	0.7800	0	18.5073	0.5702	0.4781	0.5705	0.0	0.5699	0.5702
No log	1	294	1.4717	0.0078	21.3717	0.6183	0.4084	0.6183	0.0	0.6180	0.6183
No log	2	588	0.9150	0.0156	30.2984	0.3784	0.2749	0.3784	0.0	0.3790	0.3784
No log	3	882	0.6917	0.0312	43.5605	0.5389	0.5276	0.5395	0.0	0.5386	0.5389
0.0449	4	1176	0.6737	0.0625	61.6204	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0579	5	1470	0.6624	0.125	63.5431	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.0987	6	1764	0.7313	0.25	98.8177	0.4219	0.3758	0.4219	0.0	0.4225	0.4219
0.6469	7	2058	0.7070	0.5	160.6138	0.5423	0.5421	0.5420	0.0	0.5420	0.5424
0.5275	8.0	2352	0.6881	1.0	265.8528	0.6097	0.6082	0.6094	0.0	0.6100	0.6100
0.3606	9.0	2646	0.9631	1.0	264.1938	0.6520	0.6310	0.6517	0.0	0.6520	0.6520

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1