metadata
license: mit
base_model: intfloat/multilingual-e5-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: multilingual-e5-large-finetuned-autext24
results: []
multilingual-e5-large-finetuned-autext24
This model is a fine-tuned version of intfloat/multilingual-e5-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2096
- Accuracy: 0.9673
- F1: 0.9673
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: 16
- eval_batch_size: 16
- 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 4798 | 0.1903 | 0.9527 | 0.9526 |
| 0.1396 | 2.0 | 9596 | 0.1751 | 0.9672 | 0.9672 |
| 0.1396 | 3.0 | 14394 | 0.2093 | 0.9647 | 0.9646 |
| 0.0391 | 4.0 | 19192 | 0.1954 | 0.9690 | 0.9690 |
| 0.0391 | 5.0 | 23990 | 0.2096 | 0.9673 | 0.9673 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1