|
|
--- |
|
|
license: mit |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
- f1 |
|
|
model-index: |
|
|
- name: rubert-tiny2_finetuned_emotion_experiment |
|
|
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. --> |
|
|
|
|
|
# rubert-tiny2_finetuned_emotion_experiment |
|
|
|
|
|
This model is a fine-tuned version of [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3947 |
|
|
- Accuracy: 0.8616 |
|
|
- F1: 0.8577 |
|
|
|
|
|
## 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: 15 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
|
| 0.651 | 1.0 | 54 | 0.5689 | 0.8172 | 0.8008 | |
|
|
| 0.5355 | 2.0 | 108 | 0.4842 | 0.8486 | 0.8349 | |
|
|
| 0.4561 | 3.0 | 162 | 0.4436 | 0.8590 | 0.8509 | |
|
|
| 0.4133 | 4.0 | 216 | 0.4203 | 0.8590 | 0.8528 | |
|
|
| 0.3709 | 5.0 | 270 | 0.4071 | 0.8564 | 0.8515 | |
|
|
| 0.3346 | 6.0 | 324 | 0.3980 | 0.8564 | 0.8529 | |
|
|
| 0.3153 | 7.0 | 378 | 0.3985 | 0.8590 | 0.8565 | |
|
|
| 0.302 | 8.0 | 432 | 0.3967 | 0.8642 | 0.8619 | |
|
|
| 0.2774 | 9.0 | 486 | 0.3958 | 0.8616 | 0.8575 | |
|
|
| 0.2728 | 10.0 | 540 | 0.3959 | 0.8668 | 0.8644 | |
|
|
| 0.2427 | 11.0 | 594 | 0.3962 | 0.8590 | 0.8550 | |
|
|
| 0.2425 | 12.0 | 648 | 0.3959 | 0.8642 | 0.8611 | |
|
|
| 0.2414 | 13.0 | 702 | 0.3959 | 0.8642 | 0.8611 | |
|
|
| 0.2249 | 14.0 | 756 | 0.3949 | 0.8616 | 0.8582 | |
|
|
| 0.2391 | 15.0 | 810 | 0.3947 | 0.8616 | 0.8577 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.19.2 |
|
|
- Pytorch 1.11.0+cu113 |
|
|
- Datasets 2.2.1 |
|
|
- Tokenizers 0.12.1 |
|
|
|
