Shijia's picture
End of training
857cce4 verified
|
raw
history blame
1.98 kB
---
base_model: yihongLiu/furina
tags:
- generated_from_trainer
model-index:
- name: furina_afr_loss_0.0001
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. -->
# furina_afr_loss_0.0001
This model is a fine-tuned version of [yihongLiu/furina](https://huggingface.co/yihongLiu/furina) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0463
- Spearman Corr: nan
## 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: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Spearman Corr |
|:-------------:|:-----:|:----:|:---------------:|:-------------:|
| No log | 0.85 | 200 | 0.0462 | nan |
| No log | 1.69 | 400 | 0.0463 | nan |
| 0.0501 | 2.54 | 600 | 0.0485 | nan |
| 0.0501 | 3.38 | 800 | 0.0469 | 0.0358 |
| 0.0495 | 4.23 | 1000 | 0.0474 | nan |
| 0.0495 | 5.07 | 1200 | 0.0481 | nan |
| 0.0495 | 5.92 | 1400 | 0.0472 | nan |
| 0.0494 | 6.77 | 1600 | 0.0469 | nan |
| 0.0494 | 7.61 | 1800 | 0.0463 | nan |
### Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2