399db4019217f37aa91f9ac055fdb8a5

This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 2.6898
• Data Size: 1.0
• Epoch Runtime: 128.4545
• 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	3.8357	0	12.0436	0.5990	0.4183	0.5993	0.0	0.5987	0.5987
No log	1	294	54.8148	0.0078	12.2489	0.3787	0.2747	0.3787	0.0	0.3793	0.3790
No log	2	588	2.6549	0.0156	16.8681	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
No log	3	882	2.6569	0.0312	21.3233	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.3104	4	1176	2.6704	0.0625	28.6613	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.2261	5	1470	2.6547	0.125	32.9374	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.3905	6	1764	2.6726	0.25	49.8449	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
7.3579	7	2058	45.1944	0.5	73.3825	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
2.6565	8.0	2352	2.6757	1.0	135.0485	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
2.7641	9.0	2646	2.6898	1.0	128.4545	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