nhankins/yo_euph_distilbert_lora_final

distilbert-base-multilingual-cased-lora-text-classification

This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6074
• Precision: 0.7192
• Recall: 0.912
• F1 and accuracy: {'accuracy': 0.7146529562982005, 'f1': 0.8042328042328042}

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1 and accuracy
No log	1.0	388	0.6278	0.6723	0.96	{'accuracy': 0.6735218508997429, 'f1': 0.7907742998352554}
0.5998	2.0	776	0.6380	0.6713	0.956	{'accuracy': 0.6709511568123393, 'f1': 0.7887788778877888}
0.5865	3.0	1164	0.6196	0.6988	0.9	{'accuracy': 0.6863753213367609, 'f1': 0.7867132867132868}
0.5681	4.0	1552	0.6284	0.7018	0.932	{'accuracy': 0.7017994858611826, 'f1': 0.8006872852233677}
0.5681	5.0	1940	0.6072	0.7143	0.88	{'accuracy': 0.6966580976863753, 'f1': 0.7885304659498208}
0.5641	6.0	2328	0.6122	0.7031	0.9	{'accuracy': 0.6915167095115681, 'f1': 0.7894736842105263}
0.5356	7.0	2716	0.6074	0.7125	0.912	{'accuracy': 0.7069408740359897, 'f1': 0.8}
0.5407	8.0	3104	0.6016	0.7320	0.896	{'accuracy': 0.7223650385604113, 'f1': 0.8057553956834531}
0.5407	9.0	3492	0.6079	0.7192	0.912	{'accuracy': 0.7146529562982005, 'f1': 0.8042328042328042}
0.535	10.0	3880	0.6074	0.7192	0.912	{'accuracy': 0.7146529562982005, 'f1': 0.8042328042328042}

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2