|
--- |
|
base_model: monologg/distilkobert |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: distilkobert-KEmoFact-EFE-0927 |
|
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. --> |
|
|
|
# distilkobert-KEmoFact-EFE-0927 |
|
|
|
This model is a fine-tuned version of [monologg/distilkobert](https://huggingface.co/monologg/distilkobert) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6353 |
|
- Precision: 0.1922 |
|
- Recall: 0.1524 |
|
- F1: 0.17 |
|
- Ov Accuracy: 0.7154 |
|
- Jaccard: 0.4371 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- 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 | Precision | Recall | F1 | Ov Accuracy | Jaccard | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:-----------:|:-------:| |
|
| No log | 1.0 | 414 | 0.6729 | 0.1195 | 0.0967 | 0.1069 | 0.6943 | 0.3858 | |
|
| 0.7003 | 2.0 | 828 | 0.6687 | 0.1438 | 0.1261 | 0.1344 | 0.6932 | 0.4298 | |
|
| 0.6537 | 3.0 | 1242 | 0.6563 | 0.1463 | 0.1052 | 0.1224 | 0.7017 | 0.3558 | |
|
| 0.64 | 4.0 | 1656 | 0.6613 | 0.1484 | 0.1160 | 0.1302 | 0.7019 | 0.3975 | |
|
| 0.6323 | 5.0 | 2070 | 0.6563 | 0.1467 | 0.1160 | 0.1295 | 0.7028 | 0.3960 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
