gte-multilingual-base-edu-scorer-lr3e4-bs32

This model is a fine-tuned version of Alibaba-NLP/gte-multilingual-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.7228
• Precision: 0.0303
• Recall: 0.1667
• F1 Macro: 0.0513
• Accuracy: 0.1818

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1 Macro	Accuracy
No log	0	0	4.1207	0.0587	0.1667	0.0869	0.3524
1.5193	0.3368	1000	1.5949	0.0516	0.1667	0.0788	0.3094
1.5961	0.6736	2000	1.5989	0.0516	0.1667	0.0788	0.3094
1.5912	1.0104	3000	1.5921	0.0516	0.1667	0.0788	0.3094
1.6099	1.3473	4000	1.5961	0.0516	0.1667	0.0788	0.3094
1.5681	1.6841	5000	1.5900	0.0516	0.1667	0.0788	0.3094

Framework versions

• Transformers 4.53.2
• Pytorch 2.7.1+cu126
• Datasets 4.0.0
• Tokenizers 0.21.2