metadata
base_model: yihongLiu/furina
tags:
- generated_from_trainer
model-index:
- name: furina_arq_loss_0.0001
results: []
furina_arq_loss_0.0001
This model is a fine-tuned version of yihongLiu/furina on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0482
- 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 | 0.92 | 200 | 0.0470 | nan |
| No log | 1.84 | 400 | 0.0473 | nan |
| 0.0502 | 2.76 | 600 | 0.0490 | nan |
| 0.0502 | 3.69 | 800 | 0.0480 | nan |
| 0.0498 | 4.61 | 1000 | 0.0484 | nan |
| 0.0498 | 5.53 | 1200 | 0.0478 | nan |
| 0.05 | 6.45 | 1400 | 0.0473 | nan |
| 0.05 | 7.37 | 1600 | 0.0491 | nan |
| 0.0501 | 8.29 | 1800 | 0.0482 | nan |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2