ConcPurcBERT-Katch
This model is a fine-tuned version of google-bert/bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6162
- Accuracy: 0.8402
- F1: 0.8402
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.3722 | 1.0 | 3073 | 0.4223 | 0.8222 | 0.8220 |
0.3481 | 2.0 | 6146 | 0.4450 | 0.8399 | 0.8397 |
0.3392 | 3.0 | 9219 | 0.6162 | 0.8402 | 0.8402 |
0.3006 | 4.0 | 12292 | 0.4926 | 0.8393 | 0.8393 |
0.2875 | 5.0 | 15365 | 0.6757 | 0.8361 | 0.8359 |
0.242 | 6.0 | 18438 | 0.6988 | 0.8377 | 0.8375 |
0.2082 | 7.0 | 21511 | 0.9105 | 0.8290 | 0.8284 |
0.1776 | 8.0 | 24584 | 0.9998 | 0.8317 | 0.8313 |
0.1362 | 9.0 | 27657 | 1.0866 | 0.8317 | 0.8315 |
0.0909 | 10.0 | 30730 | 1.1471 | 0.8340 | 0.8338 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.0.0
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 3
Model tree for MSParkDev/ConcPurcBERT-Katch
Base model
google-bert/bert-base-multilingual-cased
Finetuned
this model