7d89ba274ad8c57c19fc44dd42b35f96

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 2.6552
• Data Size: 0.5
• Epoch Runtime: 31.5298
• 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	11.2514	0	5.5727	0.3808	0.2831	0.3808	0.0	0.3811	0.3811
No log	1	294	21.3760	0.0078	5.8753	0.3909	0.3194	0.3915	0.0	0.3915	0.3912
No log	2	588	6.8944	0.0156	6.9392	0.3787	0.2747	0.3787	0.0	0.3793	0.3790
No log	3	882	2.6485	0.0312	8.7283	0.6219	0.3850	0.6219	0.0	0.6215	0.6219
0.2746	4	1176	2.6519	0.0625	10.2106	0.6192	0.4498	0.6192	0.0	0.6192	0.6189
0.2675	5	1470	2.7448	0.125	14.0979	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.4191	6	1764	2.8210	0.25	20.4202	0.4020	0.3329	0.4017	0.0	0.4029	0.4020
2.711	7	2058	2.6552	0.5	31.5298	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