metadata
license: apache-2.0
base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: para-multi-finetuning
results: []
para-multi-finetuning
This model is a fine-tuned version of sentence-transformers/paraphrase-multilingual-mpnet-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7937
- Accuracy: 0.8072
- F1: 0.8054
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: 5e-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
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.0969 | 1.0 | 65741 | 0.9992 | 0.7559 | 0.7478 |
| 0.7092 | 2.0 | 131482 | 0.8674 | 0.7820 | 0.7787 |
| 0.4966 | 3.0 | 197223 | 0.8120 | 0.7975 | 0.7927 |
| 0.739 | 4.0 | 262964 | 0.7937 | 0.8072 | 0.8054 |
| 0.4707 | 5.0 | 328705 | 0.8312 | 0.8109 | 0.8089 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1