b86d7339d34ce902479322e398be8b0f

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the nyu-mll/glue [wnli] dataset. It achieves the following results on the evaluation set:

• Loss: 7.6270
• Data Size: 1.0
• Epoch Runtime: 96.0946
• Accuracy: 0.4375
• F1 Macro: 0.3043
• Rouge1: 0.4375
• Rouge2: 0.0
• Rougel: 0.4375
• Rougelsum: 0.4375

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	11.9897	0	1.4471	0.4688	0.3637	0.4688	0.0	0.4688	0.4688
No log	1	19	113.3438	0.0078	2.0671	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	2	38	3.2453	0.0156	14.8986	0.5625	0.36	0.5625	0.0	0.5625	0.5625
No log	3	57	149.9844	0.0312	25.7324	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	4	76	28.9219	0.0625	35.2473	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
No log	5	95	3.2509	0.125	46.4101	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
2.924	6	114	2.8842	0.25	58.5537	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.924	7	133	2.7585	0.5	78.8896	0.5781	0.3981	0.5781	0.0	0.5781	0.5781
2.1454	8.0	152	2.7478	1.0	107.9464	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.1454	9.0	171	2.9122	1.0	105.3411	0.5625	0.36	0.5625	0.0	0.5625	0.5625
2.1454	10.0	190	44.6406	1.0	115.1407	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
16.7702	11.0	209	6.0126	1.0	134.0801	0.4375	0.3043	0.4375	0.0	0.4375	0.4375
16.7702	12.0	228	7.6270	1.0	96.0946	0.4375	0.3043	0.4375	0.0	0.4375	0.4375

Framework versions

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