metadata
base_model: yihongLiu/furina
tags:
- generated_from_trainer
model-index:
- name: furina_seed42_eng_kin_amh_latin_2e-05
results: []
furina_seed42_eng_kin_amh_latin_2e-05
This model is a fine-tuned version of yihongLiu/furina on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0242
- Spearman Corr: 0.7470
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: 2e-05
- 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 | 1.75 | 200 | 0.0281 | 0.6376 |
| 0.0807 | 3.51 | 400 | 0.0246 | 0.7176 |
| 0.0216 | 5.26 | 600 | 0.0249 | 0.7301 |
| 0.0153 | 7.02 | 800 | 0.0226 | 0.7384 |
| 0.0119 | 8.77 | 1000 | 0.0236 | 0.7484 |
| 0.0096 | 10.53 | 1200 | 0.0247 | 0.7425 |
| 0.0079 | 12.28 | 1400 | 0.0226 | 0.7424 |
| 0.0068 | 14.04 | 1600 | 0.0236 | 0.7499 |
| 0.0068 | 15.79 | 1800 | 0.0235 | 0.7482 |
| 0.006 | 17.54 | 2000 | 0.0256 | 0.7489 |
| 0.0054 | 19.3 | 2200 | 0.0240 | 0.7489 |
| 0.005 | 21.05 | 2400 | 0.0242 | 0.7470 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2