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-S800
results: []
EcoBERT-finetuned-ner-S800
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: 0.0830
- Precision: 0.5278
- Recall: 0.6129
- F1: 0.5672
- Accuracy: 0.9698
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 | 55 | 0.1278 | 0.3136 | 0.3871 | 0.3465 | 0.9466 |
| No log | 2.0 | 110 | 0.0904 | 0.4455 | 0.5442 | 0.4899 | 0.9657 |
| No log | 3.0 | 165 | 0.0825 | 0.5096 | 0.6339 | 0.5650 | 0.9691 |
| No log | 4.0 | 220 | 0.0795 | 0.5083 | 0.6003 | 0.5505 | 0.9699 |
| No log | 5.0 | 275 | 0.0830 | 0.5278 | 0.6129 | 0.5672 | 0.9698 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3