|
--- |
|
license: other |
|
datasets: |
|
- Jsevisal/gesture_pred |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
widget: |
|
- text: I'm fine. Who is this? |
|
- text: You can't take anything seriously. |
|
- text: In the end he''s going to croak, isn''t he? |
|
pipeline_tag: token-classification |
|
base_model: elastic/distilbert-base-cased-finetuned-conll03-english |
|
model-index: |
|
- name: distilbert-gest-pred-seqeval-partialmatch |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# distilbert-gest-pred-seqeval-partialmatch |
|
|
|
This model is a fine-tuned version of [elastic/distilbert-base-cased-finetuned-conll03-english](https://huggingface.co/elastic/distilbert-base-cased-finetuned-conll03-english) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7300 |
|
- Precision: 0.8116 |
|
- Recall: 0.6988 |
|
- F1: 0.7337 |
|
- Accuracy: 0.8082 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 1.8684 | 1.0 | 147 | 1.1962 | 0.3713 | 0.4095 | 0.3845 | 0.7100 | |
|
| 0.9616 | 2.0 | 294 | 0.8900 | 0.6151 | 0.5556 | 0.5459 | 0.7594 | |
|
| 0.696 | 3.0 | 441 | 0.7715 | 0.5896 | 0.5636 | 0.5634 | 0.7848 | |
|
| 0.5283 | 4.0 | 588 | 0.7300 | 0.8116 | 0.6988 | 0.7337 | 0.8082 | |
|
| 0.4079 | 5.0 | 735 | 0.7423 | 0.7973 | 0.6971 | 0.7258 | 0.8134 | |
|
| 0.309 | 6.0 | 882 | 0.8589 | 0.8034 | 0.6935 | 0.7185 | 0.7965 | |
|
| 0.2629 | 7.0 | 1029 | 0.8160 | 0.8076 | 0.6955 | 0.7268 | 0.7958 | |
|
| 0.2059 | 8.0 | 1176 | 0.8178 | 0.8116 | 0.7130 | 0.7382 | 0.8127 | |
|
| 0.1701 | 9.0 | 1323 | 0.8471 | 0.7981 | 0.7214 | 0.7365 | 0.8101 | |
|
| 0.1574 | 10.0 | 1470 | 0.8515 | 0.7956 | 0.7216 | 0.7363 | 0.8088 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.2 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
|
|
|
### LICENSE |
|
Copyright (c) 2014, Universidad Carlos III de Madrid. Todos los derechos reservados. |
|
Este software es propiedad de la Universidad Carlos III de Madrid, grupo de investigaci贸n Robots Sociales. La Universidad Carlos III de Madrid es titular en exclusiva de los derechos de propiedad intelectual de este software. Queda prohibido cualquier uso indebido o no autorizado, entre estos, a t铆tulo enunciativo pero no limitativo, la reproducci贸n, fijaci贸n, distribuci贸n, comunicaci贸n p煤blica, ingenier铆a inversa y/o transformaci贸n sobre dicho software, ya sea total o parcialmente, siendo el responsable del uso indebido o no autorizado tambi茅n responsable de las consecuencias legales que pudieran derivarse de sus actos. |
