copilot_wnut_model / README.md
bobbyw's picture
End of training
a7b28a1
---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- wnut_17
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: copilot_wnut_model
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wnut_17
type: wnut_17
config: wnut_17
split: test
args: wnut_17
metrics:
- name: Precision
type: precision
value: 0.5803921568627451
- name: Recall
type: recall
value: 0.4114921223354958
- name: F1
type: f1
value: 0.48156182212581344
- name: Accuracy
type: accuracy
value: 0.9483562053781369
---
<!-- 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. -->
# copilot_wnut_model
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the wnut_17 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3448
- Precision: 0.5804
- Recall: 0.4115
- F1: 0.4816
- Accuracy: 0.9484
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| No log | 1.0 | 213 | 0.2743 | 0.6364 | 0.2725 | 0.3816 | 0.9401 |
| No log | 2.0 | 426 | 0.2598 | 0.5977 | 0.3346 | 0.4290 | 0.9445 |
| 0.1759 | 3.0 | 639 | 0.3063 | 0.6741 | 0.3086 | 0.4234 | 0.9445 |
| 0.1759 | 4.0 | 852 | 0.3097 | 0.5930 | 0.3605 | 0.4484 | 0.9463 |
| 0.0477 | 5.0 | 1065 | 0.2962 | 0.5558 | 0.4106 | 0.4723 | 0.9474 |
| 0.0477 | 6.0 | 1278 | 0.3218 | 0.5792 | 0.3967 | 0.4708 | 0.9474 |
| 0.0477 | 7.0 | 1491 | 0.3199 | 0.5595 | 0.4096 | 0.4730 | 0.9477 |
| 0.022 | 8.0 | 1704 | 0.3385 | 0.5938 | 0.4106 | 0.4855 | 0.9481 |
| 0.022 | 9.0 | 1917 | 0.3311 | 0.5687 | 0.4217 | 0.4843 | 0.9478 |
| 0.0123 | 10.0 | 2130 | 0.3448 | 0.5804 | 0.4115 | 0.4816 | 0.9484 |
### Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1