xlm-roberta-base_original_esp-kin-eng_train_spearman_corr
This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0297
- Spearman Corr: 0.7242
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 | 1.63 | 200 | 0.0309 | 0.6402 |
0.0362 | 3.27 | 400 | 0.0302 | 0.6935 |
0.0217 | 4.9 | 600 | 0.0271 | 0.6991 |
0.0164 | 6.53 | 800 | 0.0280 | 0.7128 |
0.0126 | 8.16 | 1000 | 0.0317 | 0.7174 |
0.0126 | 9.8 | 1200 | 0.0295 | 0.7118 |
0.0101 | 11.43 | 1400 | 0.0286 | 0.7256 |
0.0086 | 13.06 | 1600 | 0.0285 | 0.7179 |
0.0069 | 14.69 | 1800 | 0.0283 | 0.7091 |
0.0059 | 16.33 | 2000 | 0.0296 | 0.7225 |
0.0059 | 17.96 | 2200 | 0.0295 | 0.7201 |
0.0054 | 19.59 | 2400 | 0.0288 | 0.7188 |
0.0047 | 21.22 | 2600 | 0.0298 | 0.7236 |
0.0042 | 22.86 | 2800 | 0.0287 | 0.7233 |
0.0039 | 24.49 | 3000 | 0.0297 | 0.7242 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 5