|
--- |
|
license: mit |
|
base_model: microsoft/Multilingual-MiniLM-L12-H384 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: intent_trading |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# intent_trading |
|
|
|
This model is a fine-tuned version of [microsoft/Multilingual-MiniLM-L12-H384](https://huggingface.co/microsoft/Multilingual-MiniLM-L12-H384) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1788 |
|
- Accuracy: 0.9590 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 40 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 235 | 1.6327 | 0.6781 | |
|
| No log | 2.0 | 470 | 1.0073 | 0.8852 | |
|
| 1.7024 | 3.0 | 705 | 0.6035 | 0.9299 | |
|
| 1.7024 | 4.0 | 940 | 0.3965 | 0.9323 | |
|
| 0.5941 | 5.0 | 1175 | 0.2810 | 0.9534 | |
|
| 0.5941 | 6.0 | 1410 | 0.2259 | 0.9531 | |
|
| 0.2567 | 7.0 | 1645 | 0.1949 | 0.9531 | |
|
| 0.2567 | 8.0 | 1880 | 0.1723 | 0.9566 | |
|
| 0.1484 | 9.0 | 2115 | 0.1736 | 0.9558 | |
|
| 0.1484 | 10.0 | 2350 | 0.1545 | 0.9558 | |
|
| 0.1084 | 11.0 | 2585 | 0.1559 | 0.9568 | |
|
| 0.1084 | 12.0 | 2820 | 0.1562 | 0.9536 | |
|
| 0.0824 | 13.0 | 3055 | 0.1486 | 0.9560 | |
|
| 0.0824 | 14.0 | 3290 | 0.1450 | 0.9560 | |
|
| 0.0714 | 15.0 | 3525 | 0.1386 | 0.9568 | |
|
| 0.0714 | 16.0 | 3760 | 0.1412 | 0.9600 | |
|
| 0.0714 | 17.0 | 3995 | 0.1475 | 0.9563 | |
|
| 0.063 | 18.0 | 4230 | 0.1471 | 0.9558 | |
|
| 0.063 | 19.0 | 4465 | 0.1517 | 0.9574 | |
|
| 0.0529 | 20.0 | 4700 | 0.1535 | 0.9550 | |
|
| 0.0529 | 21.0 | 4935 | 0.1494 | 0.9598 | |
|
| 0.0504 | 22.0 | 5170 | 0.1661 | 0.9579 | |
|
| 0.0504 | 23.0 | 5405 | 0.1548 | 0.9592 | |
|
| 0.0453 | 24.0 | 5640 | 0.1584 | 0.9600 | |
|
| 0.0453 | 25.0 | 5875 | 0.1601 | 0.9558 | |
|
| 0.0395 | 26.0 | 6110 | 0.1511 | 0.9598 | |
|
| 0.0395 | 27.0 | 6345 | 0.1655 | 0.9584 | |
|
| 0.0375 | 28.0 | 6580 | 0.1614 | 0.9579 | |
|
| 0.0375 | 29.0 | 6815 | 0.1534 | 0.9595 | |
|
| 0.0332 | 30.0 | 7050 | 0.1757 | 0.9574 | |
|
| 0.0332 | 31.0 | 7285 | 0.1701 | 0.9576 | |
|
| 0.0324 | 32.0 | 7520 | 0.1635 | 0.9587 | |
|
| 0.0324 | 33.0 | 7755 | 0.1721 | 0.9587 | |
|
| 0.0324 | 34.0 | 7990 | 0.1742 | 0.9584 | |
|
| 0.0294 | 35.0 | 8225 | 0.1798 | 0.9582 | |
|
| 0.0294 | 36.0 | 8460 | 0.1812 | 0.9582 | |
|
| 0.029 | 37.0 | 8695 | 0.1759 | 0.9590 | |
|
| 0.029 | 38.0 | 8930 | 0.1777 | 0.9600 | |
|
| 0.028 | 39.0 | 9165 | 0.1782 | 0.9598 | |
|
| 0.028 | 40.0 | 9400 | 0.1788 | 0.9590 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.19.1 |
|
|
