|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: kaelte |
|
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. --> |
|
|
|
# kaelte |
|
|
|
This model is a fine-tuned version of [svalabs/gbert-large-zeroshot-nli](https://huggingface.co/svalabs/gbert-large-zeroshot-nli) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0022 |
|
- F1: 1.0 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| No log | 0.94 | 11 | 0.6783 | 0.7786 | |
|
| No log | 1.94 | 22 | 0.1718 | 0.9272 | |
|
| No log | 2.94 | 33 | 0.0769 | 0.9887 | |
|
| No log | 3.94 | 44 | 0.0686 | 0.9887 | |
|
| No log | 4.94 | 55 | 0.0227 | 0.9887 | |
|
| No log | 5.94 | 66 | 0.0075 | 1.0 | |
|
| No log | 6.94 | 77 | 0.0099 | 1.0 | |
|
| No log | 7.94 | 88 | 0.0025 | 1.0 | |
|
| No log | 8.94 | 99 | 0.0023 | 1.0 | |
|
| No log | 9.94 | 110 | 0.0022 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.22.2 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.5.1 |
|
- Tokenizers 0.12.1 |
|
|
