|
--- |
|
base_model: ElKulako/cryptobert |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: results |
|
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. --> |
|
|
|
# results |
|
|
|
This model is a fine-tuned version of [ElKulako/cryptobert](https://huggingface.co./ElKulako/cryptobert) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8983 |
|
- Accuracy: 0.6433 |
|
- Precision: 0.6614 |
|
- Recall: 0.6433 |
|
- F1: 0.6461 |
|
|
|
## 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: 3.5e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 69420 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.9586 | 0.19 | 100 | 0.8746 | 0.6033 | 0.5990 | 0.6033 | 0.5944 | |
|
| 0.7362 | 0.38 | 200 | 0.8187 | 0.63 | 0.6322 | 0.63 | 0.6232 | |
|
| 0.577 | 0.57 | 300 | 0.8065 | 0.6767 | 0.6821 | 0.6767 | 0.6761 | |
|
| 0.4632 | 0.76 | 400 | 0.8437 | 0.63 | 0.6411 | 0.63 | 0.6321 | |
|
| 0.3243 | 0.95 | 500 | 0.8983 | 0.6433 | 0.6614 | 0.6433 | 0.6461 | |
|
| 0.2257 | 1.14 | 600 | 1.3704 | 0.6033 | 0.6863 | 0.6033 | 0.6046 | |
|
| 0.1333 | 1.33 | 700 | 1.2951 | 0.6033 | 0.6201 | 0.6033 | 0.6052 | |
|
| 0.0574 | 1.52 | 800 | 1.5119 | 0.6333 | 0.6331 | 0.6333 | 0.6309 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Tokenizers 0.15.0 |
|
|
