metadata
license: apache-2.0
base_model: ViktorDo/EcoBERT-Pretrained
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: EcoBERT-finetuned-ner-copious
results: []
EcoBERT-finetuned-ner-copious
This model is a fine-tuned version of ViktorDo/EcoBERT-Pretrained on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0764
- Precision: 0.6144
- Recall: 0.6696
- F1: 0.6408
- Accuracy: 0.9747
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 63 | 0.1328 | 0.2586 | 0.3043 | 0.2796 | 0.9522 |
| No log | 2.0 | 126 | 0.0885 | 0.4876 | 0.5681 | 0.5248 | 0.9688 |
| No log | 3.0 | 189 | 0.0816 | 0.5514 | 0.5913 | 0.5706 | 0.9720 |
| No log | 4.0 | 252 | 0.0764 | 0.6086 | 0.6536 | 0.6303 | 0.9748 |
| No log | 5.0 | 315 | 0.0764 | 0.6144 | 0.6696 | 0.6408 | 0.9747 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3