|
--- |
|
license: afl-3.0 |
|
base_model: masakhane/afroxlmr-large-ner-masakhaner-1.0_2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- precision |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: ewc_stabilised_no_date_lambda0.4 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# ewc_stabilised_no_date_lambda0.4 |
|
|
|
This model is a fine-tuned version of [masakhane/afroxlmr-large-ner-masakhaner-1.0_2.0](https://huggingface.co/masakhane/afroxlmr-large-ner-masakhaner-1.0_2.0) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1841 |
|
- F1: 0.8384 |
|
- Precision: 0.8348 |
|
- Recall: 0.8421 |
|
- Accuracy: 0.9649 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 3407 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:------:|:---------:|:------:|:--------:| |
|
| 0.3292 | 0.9993 | 701 | 0.1360 | 0.7966 | 0.7971 | 0.7961 | 0.9564 | |
|
| 0.1207 | 2.0 | 1403 | 0.1172 | 0.8235 | 0.8146 | 0.8326 | 0.9623 | |
|
| 0.0891 | 2.9993 | 2104 | 0.1133 | 0.8348 | 0.8307 | 0.8390 | 0.9640 | |
|
| 0.0684 | 4.0 | 2806 | 0.1172 | 0.8386 | 0.8411 | 0.8362 | 0.9650 | |
|
| 0.0527 | 4.9993 | 3507 | 0.1268 | 0.8371 | 0.8302 | 0.8441 | 0.9645 | |
|
| 0.0414 | 6.0 | 4209 | 0.1425 | 0.8390 | 0.8329 | 0.8453 | 0.9649 | |
|
| 0.0329 | 6.9993 | 4910 | 0.1532 | 0.8385 | 0.8374 | 0.8396 | 0.9647 | |
|
| 0.0263 | 8.0 | 5612 | 0.1650 | 0.8359 | 0.8287 | 0.8433 | 0.9645 | |
|
| 0.0222 | 8.9993 | 6313 | 0.1793 | 0.8396 | 0.8398 | 0.8395 | 0.9652 | |
|
| 0.019 | 9.9929 | 7010 | 0.1841 | 0.8384 | 0.8348 | 0.8421 | 0.9649 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.4 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
