metadata
license: apache-2.0
base_model: distilbert/distilbert-base-multilingual-cased
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-multilingual-cased_regression_finetuned_mobile01_all
results: []
distilbert-base-multilingual-cased_regression_finetuned_mobile01_all
This model is a fine-tuned version of distilbert/distilbert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
- Mse: 0.0001
- Mae: 0.0078
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae |
|---|---|---|---|---|---|
| No log | 1.0 | 5 | 0.1000 | 0.1000 | 0.3073 |
| No log | 2.0 | 10 | 0.0123 | 0.0123 | 0.1057 |
| No log | 3.0 | 15 | 0.0076 | 0.0076 | 0.0854 |
| No log | 4.0 | 20 | 0.0042 | 0.0042 | 0.0632 |
| No log | 5.0 | 25 | 0.0028 | 0.0028 | 0.0516 |
| No log | 6.0 | 30 | 0.0001 | 0.0001 | 0.0088 |
| No log | 7.0 | 35 | 0.0012 | 0.0012 | 0.0337 |
| No log | 8.0 | 40 | 0.0001 | 0.0001 | 0.0078 |
| No log | 9.0 | 45 | 0.0004 | 0.0004 | 0.0174 |
| 0.0746 | 10.0 | 50 | 0.0004 | 0.0004 | 0.0183 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2