metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Bert-Multilingual-Balanced-trimmed-10epoch
results: []
Bert-Multilingual-Balanced-trimmed-10epoch
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5212
- Accuracy: 0.48
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 4 | 1.1339 | 0.32 |
| No log | 2.0 | 8 | 1.0996 | 0.48 |
| No log | 3.0 | 12 | 1.1665 | 0.36 |
| No log | 4.0 | 16 | 1.1651 | 0.44 |
| No log | 5.0 | 20 | 1.1689 | 0.4 |
| No log | 6.0 | 24 | 1.2189 | 0.32 |
| No log | 7.0 | 28 | 1.1908 | 0.44 |
| No log | 8.0 | 32 | 1.1355 | 0.52 |
| No log | 9.0 | 36 | 1.2280 | 0.4 |
| No log | 10.0 | 40 | 1.3308 | 0.4 |
| No log | 11.0 | 44 | 1.3048 | 0.48 |
| No log | 12.0 | 48 | 1.3897 | 0.44 |
| No log | 13.0 | 52 | 1.3561 | 0.44 |
| No log | 14.0 | 56 | 1.3551 | 0.52 |
| No log | 15.0 | 60 | 1.5895 | 0.4 |
| No log | 16.0 | 64 | 1.7362 | 0.36 |
| No log | 17.0 | 68 | 1.6214 | 0.4 |
| No log | 18.0 | 72 | 1.5556 | 0.4 |
| No log | 19.0 | 76 | 1.5258 | 0.48 |
| No log | 20.0 | 80 | 1.5212 | 0.48 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 1.13.1
- Datasets 2.14.5
- Tokenizers 0.14.1