|
--- |
|
base_model: xxxxxxxxx |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- AmazonScience/massive |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: massive_indo |
|
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. --> |
|
|
|
# massive_indo |
|
|
|
This model is a fine-tuned version of [xxxxxxxxx](https://huggingface.co/xxxxxxxxx) on the massive dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1219 |
|
- F1: 0.9750 |
|
|
|
## 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: 0.0001 |
|
- 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 3.1726 | 0.58 | 100 | 2.2176 | 0.6600 | |
|
| 1.7054 | 1.16 | 200 | 1.0444 | 0.8521 | |
|
| 0.7568 | 1.73 | 300 | 0.4974 | 0.9248 | |
|
| 0.3368 | 2.31 | 400 | 0.2992 | 0.9454 | |
|
| 0.165 | 2.89 | 500 | 0.2052 | 0.9606 | |
|
| 0.0739 | 3.47 | 600 | 0.1621 | 0.9665 | |
|
| 0.0438 | 4.05 | 700 | 0.1568 | 0.9656 | |
|
| 0.0228 | 4.62 | 800 | 0.1331 | 0.9711 | |
|
| 0.0183 | 5.2 | 900 | 0.1249 | 0.9734 | |
|
| 0.011 | 5.78 | 1000 | 0.1238 | 0.9733 | |
|
| 0.0091 | 6.36 | 1100 | 0.1221 | 0.9741 | |
|
| 0.0079 | 6.94 | 1200 | 0.1207 | 0.9756 | |
|
| 0.007 | 7.51 | 1300 | 0.1218 | 0.9750 | |
|
| 0.0064 | 8.09 | 1400 | 0.1216 | 0.9745 | |
|
| 0.006 | 8.67 | 1500 | 0.1218 | 0.9749 | |
|
| 0.0058 | 9.25 | 1600 | 0.1217 | 0.9750 | |
|
| 0.0056 | 9.83 | 1700 | 0.1219 | 0.9750 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Tokenizers 0.14.1 |
|
|
