metadata
license: apache-2.0
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: []
distilbert-gest-pred-seqeval-partialmatch
This model is a fine-tuned version of 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