metadata
license: mit
base_model: FacebookAI/xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-base_hau_loss_5e-06
results: []
xlm-roberta-base_hau_loss_5e-06
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: 0.0248
- Spearman Corr: 0.7591
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-06
- 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 | 0.95 | 200 | 0.0249 | 0.7564 |
No log | 1.91 | 400 | 0.0258 | 0.7583 |
0.0014 | 2.86 | 600 | 0.0239 | 0.7618 |
0.0014 | 3.82 | 800 | 0.0246 | 0.7601 |
0.0013 | 4.77 | 1000 | 0.0242 | 0.7588 |
0.0013 | 5.73 | 1200 | 0.0241 | 0.7574 |
0.0013 | 6.68 | 1400 | 0.0248 | 0.7605 |
0.0013 | 7.64 | 1600 | 0.0255 | 0.7623 |
0.0014 | 8.59 | 1800 | 0.0247 | 0.7585 |
0.0014 | 9.55 | 2000 | 0.0252 | 0.7582 |
0.0014 | 10.5 | 2200 | 0.0248 | 0.7591 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2