defect-classification-llama-baseline-25-epochs

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

• Loss: 0.1655
• Accuracy: 0.9421

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: 2e-05
• train_batch_size: 512
• eval_batch_size: 512
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7994	1.0	1062	0.7879	0.8243
0.5403	2.0	2124	0.5089	0.8545
0.4235	3.0	3186	0.3855	0.8819
0.3556	4.0	4248	0.4072	0.8656
0.3133	5.0	5310	0.3077	0.8999
0.2998	6.0	6372	0.3031	0.9025
0.2842	7.0	7434	0.2610	0.9100
0.2773	8.0	8496	0.2443	0.9157
0.2413	9.0	9558	0.2339	0.9204
0.2394	10.0	10620	0.2241	0.9223
0.2305	11.0	11682	0.2230	0.9195
0.2119	12.0	12744	0.2129	0.9273
0.2106	13.0	13806	0.2186	0.9228
0.1973	14.0	14868	0.1961	0.9319
0.1993	15.0	15930	0.1903	0.9337
0.1863	16.0	16992	0.1888	0.9322
0.1883	17.0	18054	0.1966	0.9288
0.1879	18.0	19116	0.1794	0.9380
0.1856	19.0	20178	0.1786	0.9366
0.1808	20.0	21240	0.1838	0.9344
0.1711	21.0	22302	0.1749	0.9383
0.1689	22.0	23364	0.1694	0.9405
0.17	23.0	24426	0.1687	0.9411
0.1648	24.0	25488	0.1684	0.9403
0.1665	25.0	26550	0.1655	0.9421

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0