metadata
library_name: transformers
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
model-index:
- name: bert-base-multilingual-cased-finetuned-yiddish-experiment-4
results: []
bert-base-multilingual-cased-finetuned-yiddish-experiment-4
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: 1.4127
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.5841 | 0.4728 | 100 | 2.6105 |
| 1.9725 | 0.9456 | 200 | 1.6720 |
| 1.535 | 1.4161 | 300 | 1.5957 |
| 1.4496 | 1.8889 | 400 | 1.5590 |
| 1.3806 | 2.3593 | 500 | 1.4973 |
| 1.3533 | 2.8322 | 600 | 1.4804 |
| 1.3 | 3.3026 | 700 | 1.4363 |
| 1.3135 | 3.7754 | 800 | 1.4593 |
| 1.2523 | 4.2459 | 900 | 1.4570 |
| 1.255 | 4.7187 | 1000 | 1.4659 |
| 1.2291 | 5.1891 | 1100 | 1.4127 |
| 1.2041 | 5.6619 | 1200 | 1.4866 |
| 1.1898 | 6.1324 | 1300 | 1.4525 |
| 1.1729 | 6.6052 | 1400 | 1.4438 |
| 1.1742 | 7.0757 | 1500 | 1.4242 |
| 1.1645 | 7.5485 | 1600 | 1.4479 |
| 1.1165 | 8.0189 | 1700 | 1.4881 |
| 1.1283 | 8.4917 | 1800 | 1.4369 |
| 1.1334 | 8.9645 | 1900 | 1.4631 |
| 1.1081 | 9.4350 | 2000 | 1.4551 |
| 1.1344 | 9.9078 | 2100 | 1.4553 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.21.0