vibert-base-cased-ed

This model is a fine-tuned version of FPTAI/vibert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0617
• F1 Micro: 0.7029
• F1 Macro: 0.0254
• Accuracy: 0.6459
• Recall Micro: 0.6169
• Precision Micro: 0.8169
• Recall Macro: 0.0269
• Precision Macro: 0.0240
• F1: 0.5817

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro	Accuracy	Recall Micro	Precision Micro	Recall Macro	Precision Macro	F1
0.0696	1.0	1526	0.0711	0.6892	0.0243	0.7054	0.6737	0.7054	0.0294	0.0207	0.5573
0.0577	2.0	3052	0.0640	0.6943	0.0251	0.6398	0.6111	0.8038	0.0267	0.0236	0.5742
0.0674	3.0	4578	0.0613	0.6949	0.0252	0.6257	0.5976	0.8300	0.0261	0.0244	0.5778
0.0576	4.0	6104	0.0610	0.7006	0.0254	0.6358	0.6073	0.8278	0.0265	0.0243	0.5814
0.0387	5.0	7630	0.0617	0.7029	0.0254	0.6459	0.6169	0.8169	0.0269	0.0240	0.5817

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1