metadata
language:
- nl
license: apache-2.0
base_model: bert-base-uncased
tags:
- abc
- generated_from_trainer
datasets:
- stsb_multi_mt
model-index:
- name: bert-base-uncased-FinedTuned
results: []
bert-base-uncased-FinedTuned
This model is a fine-tuned version of bert-base-uncased on the stsb_multi_mt dataset. It achieves the following results on the evaluation set:
- Loss: 2.7197
- Pearson: 0.2346
- Mse: 2.7197
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 12000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Pearson | Mse |
|---|---|---|---|---|---|
| 0.051 | 5.5556 | 1000 | 2.8182 | 0.2432 | 2.8182 |
| 0.0623 | 11.1111 | 2000 | 2.8367 | 0.2164 | 2.8367 |
| 0.0471 | 16.6667 | 3000 | 2.7305 | 0.2126 | 2.7305 |
| 0.0357 | 22.2222 | 4000 | 2.6918 | 0.2324 | 2.6918 |
| 0.032 | 27.7778 | 5000 | 2.7902 | 0.2379 | 2.7902 |
| 0.0793 | 33.3333 | 6000 | 2.7368 | 0.2480 | 2.7368 |
| 0.0775 | 38.8889 | 7000 | 2.6499 | 0.2382 | 2.6499 |
| 0.0728 | 44.4444 | 8000 | 2.6974 | 0.2368 | 2.6974 |
| 0.0596 | 50.0 | 9000 | 2.7313 | 0.2302 | 2.7313 |
| 0.1012 | 55.5556 | 10000 | 2.7291 | 0.2332 | 2.7291 |
| 0.0644 | 61.1111 | 11000 | 2.7338 | 0.2315 | 2.7338 |
| 0.1595 | 66.6667 | 12000 | 2.7197 | 0.2346 | 2.7197 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1