metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: 16class_combo_111123_vthout_pp_full_tweet
results: []
16class_combo_111123_vthout_pp_full_tweet
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: 0.1334
- Accuracy: 0.9505
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5839 | 1.0 | 694 | 0.6365 | 0.8174 |
| 0.7158 | 2.0 | 1388 | 0.4064 | 0.8861 |
| 0.4163 | 3.0 | 2082 | 0.2977 | 0.9100 |
| 0.3485 | 4.0 | 2776 | 0.2237 | 0.9295 |
| 0.2904 | 5.0 | 3470 | 0.1926 | 0.9357 |
| 0.223 | 6.0 | 4164 | 0.1550 | 0.9455 |
| 0.205 | 7.0 | 4858 | 0.1408 | 0.9483 |
| 0.1672 | 8.0 | 5552 | 0.1334 | 0.9505 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1