7e8c4dea5eae4f58d4fefc1bed80b2d7

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the google/boolq dataset. It achieves the following results on the evaluation set:

• Loss: 3.3769
• Data Size: 1.0
• Epoch Runtime: 887.1520
• 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	6.5299	0	22.7990	0.6127	0.4318	0.6131	0.0	0.6121	0.6129
No log	1	294	12.2836	0.0078	29.8525	0.3787	0.2747	0.3787	0.0	0.3793	0.3790
No log	2	588	25.6169	0.0156	41.7008	0.5101	0.5060	0.5097	0.0	0.5101	0.5098
No log	3	882	2.6657	0.0312	64.8662	0.6155	0.4175	0.6155	0.0	0.6150	0.6152
0.4445	4	1176	2.6835	0.0625	95.5641	0.6085	0.4046	0.6085	0.0	0.6078	0.6080
0.2643	5	1470	2.6560	0.125	143.6508	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
0.3869	6	1764	2.6943	0.25	253.5735	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
2.8583	7	2058	2.6631	0.5	470.1449	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
3.3626	8.0	2352	2.7717	1.0	902.3489	0.6213	0.3832	0.6213	0.0	0.6207	0.6210
3.4435	9.0	2646	3.3769	1.0	887.1520	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