metadata
license: mit
base_model: haryoaw/scenario-TCR-NER_data-univner_half
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: scenario-kd-scr-ner-full-xlmr-halfen_data-univner_en66
results: []
scenario-kd-scr-ner-full-xlmr-halfen_data-univner_en66
This model is a fine-tuned version of haryoaw/scenario-TCR-NER_data-univner_half on the None dataset. It achieves the following results on the evaluation set:
- Loss: 250.6721
- Precision: 0.4368
- Recall: 0.2754
- F1: 0.3378
- Accuracy: 0.9532
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 32
- seed: 66
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|---|---|---|
| 426.5331 | 1.28 | 500 | 343.1131 | 0.4717 | 0.0259 | 0.0491 | 0.9413 |
| 317.8317 | 2.55 | 1000 | 306.4857 | 0.3815 | 0.1066 | 0.1667 | 0.9449 |
| 288.4479 | 3.83 | 1500 | 285.8158 | 0.4429 | 0.1284 | 0.1990 | 0.9461 |
| 270.6268 | 5.1 | 2000 | 271.5317 | 0.3921 | 0.2050 | 0.2692 | 0.9494 |
| 257.3109 | 6.38 | 2500 | 260.7265 | 0.3853 | 0.2381 | 0.2943 | 0.9517 |
| 248.4864 | 7.65 | 3000 | 253.9278 | 0.3950 | 0.2940 | 0.3371 | 0.9527 |
| 242.8456 | 8.93 | 3500 | 250.6721 | 0.4368 | 0.2754 | 0.3378 | 0.9532 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.1.1+cu121
- Datasets 2.14.5
- Tokenizers 0.13.3