metadata
license: mit
base_model: Microsoft/Multilingual-MiniLM-L12-H384
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: my-model-MiniLM-Area
results: []
my-model-MiniLM-Area
This model is a fine-tuned version of Microsoft/Multilingual-MiniLM-L12-H384 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4662
- Accuracy: 0.4676
- F1: 0.3710
- Precision: 0.3276
- Recall: 0.4676
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: 3e-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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
1.8319 | 1.0 | 81 | 1.7972 | 0.2446 | 0.0961 | 0.0598 | 0.2446 |
1.7578 | 2.0 | 162 | 1.7665 | 0.2446 | 0.0961 | 0.0598 | 0.2446 |
1.7311 | 3.0 | 243 | 1.7140 | 0.3885 | 0.2579 | 0.1991 | 0.3885 |
1.6502 | 4.0 | 324 | 1.6061 | 0.4173 | 0.2789 | 0.2142 | 0.4173 |
1.551 | 5.0 | 405 | 1.5444 | 0.4029 | 0.2666 | 0.1999 | 0.4029 |
1.4605 | 6.0 | 486 | 1.5607 | 0.4532 | 0.3470 | 0.2842 | 0.4532 |
1.3818 | 7.0 | 567 | 1.5001 | 0.4604 | 0.3552 | 0.2913 | 0.4604 |
1.3256 | 8.0 | 648 | 1.5020 | 0.4820 | 0.3847 | 0.3341 | 0.4820 |
1.3104 | 9.0 | 729 | 1.4776 | 0.4604 | 0.3644 | 0.3218 | 0.4604 |
1.2741 | 10.0 | 810 | 1.4662 | 0.4676 | 0.3710 | 0.3276 | 0.4676 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1