metadata
base_model: allenai/scibert_scivocab_cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: scibert-finetuned-ner
results: []
scibert-finetuned-ner
This model is a fine-tuned version of allenai/scibert_scivocab_cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4445
- Precision: 0.3974
- Recall: 0.3404
- F1: 0.3667
- Accuracy: 0.9140
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 121 | 0.5694 | 0.0808 | 0.0411 | 0.0545 | 0.8648 |
| No log | 2.0 | 242 | 0.4878 | 0.3169 | 0.1277 | 0.1820 | 0.9020 |
| No log | 3.0 | 363 | 0.4121 | 0.3422 | 0.2199 | 0.2677 | 0.9097 |
| No log | 4.0 | 484 | 0.4240 | 0.4273 | 0.2624 | 0.3251 | 0.9147 |
| 0.4235 | 5.0 | 605 | 0.3974 | 0.4187 | 0.2922 | 0.3442 | 0.9159 |
| 0.4235 | 6.0 | 726 | 0.4125 | 0.4146 | 0.3064 | 0.3524 | 0.9140 |
| 0.4235 | 7.0 | 847 | 0.4235 | 0.3713 | 0.3191 | 0.3432 | 0.9136 |
| 0.4235 | 8.0 | 968 | 0.4330 | 0.3794 | 0.3348 | 0.3557 | 0.9132 |
| 0.1633 | 9.0 | 1089 | 0.4481 | 0.3926 | 0.3319 | 0.3597 | 0.9133 |
| 0.1633 | 10.0 | 1210 | 0.4445 | 0.3974 | 0.3404 | 0.3667 | 0.9140 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1