defect-classification-t5-baseline-20-epochs

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4748
• Accuracy: 0.7776

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: 0.0001
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5451	1.0	1062	0.8419	0.6840
0.4981	2.0	2124	0.6668	0.6973
0.4465	3.0	3186	0.5410	0.7736
0.4091	4.0	4248	0.4561	0.8153
0.3967	5.0	5310	0.4574	0.8106
0.4033	6.0	6372	0.4654	0.8002
0.3887	7.0	7434	0.4576	0.7978
0.4674	8.0	8496	0.4824	0.7910
0.3977	9.0	9558	0.4450	0.8007
0.4191	10.0	10620	0.4415	0.7992
0.3749	11.0	11682	0.4439	0.7946
0.3741	12.0	12744	0.4987	0.7725
0.3772	13.0	13806	0.4445	0.8008
0.398	14.0	14868	0.4641	0.7800
0.3939	15.0	15930	0.4601	0.7856
0.3777	16.0	16992	0.4587	0.7869
0.3705	17.0	18054	0.4627	0.7835
0.3856	18.0	19116	0.4707	0.7791
0.3982	19.0	20178	0.4829	0.7758
0.3811	20.0	21240	0.4748	0.7776

Framework versions

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