metadata
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: deberta-v3-base-finetuned-ner
results: []
deberta-v3-base-finetuned-ner
This model is a fine-tuned version of microsoft/deberta-v3-base on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.9895
- Overall Precision: 0.5201
- Overall Recall: 0.3319
- Overall F1: 0.4052
- Overall Accuracy: 0.9326
- Datasetname F1: 0.4952
- Hyperparametername F1: 0.48
- Hyperparametervalue F1: 0.5
- Methodname F1: 0.3933
- Metricname F1: 0.2488
- Metricvalue F1: 0.2456
- Taskname F1: 0.6393
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Datasetname F1 | Hyperparametername F1 | Hyperparametervalue F1 | Methodname F1 | Metricname F1 | Metricvalue F1 | Taskname F1 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 141 | 1.2556 | 0.2784 | 0.1520 | 0.1967 | 0.9212 | 0.0 | 0.3478 | 0.2581 | 0.3750 | 0.0 | 0.0 | 0.0556 |
| No log | 2.0 | 282 | 0.8945 | 0.3020 | 0.5096 | 0.3793 | 0.9088 | 0.5 | 0.1538 | 0.2778 | 0.3540 | 0.4566 | 0.0896 | 0.3756 |
| No log | 3.0 | 423 | 1.0233 | 0.3702 | 0.4518 | 0.4069 | 0.9268 | 0.4211 | 0.2647 | 0.3333 | 0.3529 | 0.4658 | 0.1613 | 0.5270 |
| 0.6352 | 4.0 | 564 | 1.1734 | 0.4316 | 0.4390 | 0.4352 | 0.9310 | 0.4854 | 0.3462 | 0.3415 | 0.4352 | 0.4269 | 0.2295 | 0.5827 |
| 0.6352 | 5.0 | 705 | 1.3147 | 0.4840 | 0.4540 | 0.4685 | 0.9390 | 0.5143 | 0.5 | 0.625 | 0.5739 | 0.3495 | 0.2333 | 0.5865 |
| 0.6352 | 6.0 | 846 | 2.1441 | 0.5618 | 0.3405 | 0.4240 | 0.9373 | 0.5185 | 0.5581 | 0.6061 | 0.4898 | 0.2365 | 0.1071 | 0.6126 |
| 0.6352 | 7.0 | 987 | 1.9895 | 0.5201 | 0.3319 | 0.4052 | 0.9326 | 0.4952 | 0.48 | 0.5 | 0.3933 | 0.2488 | 0.2456 | 0.6393 |
Framework versions
- Transformers 4.23.1
- Pytorch 1.12.1+cu102
- Datasets 2.6.1
- Tokenizers 0.13.1