bert-finetuned-ner / README.md
coyotte508's picture
coyotte508 HF staff
Add verifyToken field to verify evaluation results are produced by Hugging Face's automatic model evaluator (#4)
eeb2784
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: test-bert-finetuned-ner
results:
- task:
type: token-classification
name: Token Classification
dataset:
name: conll2003
type: conll2003
args: conll2003
metrics:
- type: precision
value: 0.9354625186165811
name: Precision
- type: recall
value: 0.9513631773813531
name: Recall
- type: f1
value: 0.943345848977889
name: F1
- type: accuracy
value: 0.9867545770294931
name: Accuracy
- task:
type: token-classification
name: Token Classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: test
metrics:
- type: accuracy
value: 0.9003797607979704
name: Accuracy
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGVlNjEyMTJmOTBhMmE1NjY1ODA3MTE0ZjM1YjU5Mzk2ZTY1NWE2MTZiMGMxZTRiNDNjNzNiYzI2NzZiMzAxMiIsInZlcnNpb24iOjF9.ScTPJWA72u8-LTp78w7U8teH-TXdyWnoz4vnK-1TefERahcKQ51eekHI_2xjOPe-1uQmw5z8rKTZfh3MOv-HCw
- type: precision
value: 0.9286807108391197
name: Precision
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYjc0OGM4MTQ0OGM3NzA1ZTJmODg4YmJiZTZjOTVkZWYzZGYxZGYzZThhYzRkMzAxOWNhZmQ0NmJhNTMxZGI4MCIsInZlcnNpb24iOjF9.vloc_Hl4_UmVHUMTN2utIKJ2gYntSlZVuVJNkeGn-fR9SeRbKzmkBds4GQNjsV0JiVmnX0POB1hUqRGP4UjdAg
- type: recall
value: 0.9158238551580065
name: Recall
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYzE2ZGIwNTAzNDhkMDc0MmU2NTQ2MjIyNjA0NzI0N2JiNDM3NjgxNTU3YmNiNWIwOTRmYzNkMTE0MmUyOTNhNiIsInZlcnNpb24iOjF9.-mi3lImJs1-993tdLiTL7KGFEb-jZJVrviqUlFaVY0rgkojDvRyhbUBnJoD4dadh728kRDTH5NW-ZKb9B9FTDg
- type: f1
value: 0.9222074745602832
name: F1
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGE1ODE0MGUzZmFhZTNhOWMwMzk3NzQ5MTQwOWIyNjAxZWUwMDgzNDBlNGIyNmY4YmQ4ZDRmOTljZmYyNGYzOCIsInZlcnNpb24iOjF9.PjQJinFobofJhCpsTLEuMSjsskLfbOmAPPQVGWBGk7jYOi3lvd9CUn9i_g1GlbbxuxmO1L9sMAj-pANn-aQiAA
- type: loss
value: 0.8705922365188599
name: loss
verified: true
verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOGI2YTU4ZmExYmZmMjBmMjM3ZWJhNDA0OGMwZjM4YWE4MjU1YmFjMTQxMjQ5MDlhNzYzYTBmYTc3YzRkN2UwOCIsInZlcnNpb24iOjF9.iyuIRW9M-yknXWi2Whboo-rjzicgxSGaeCpypgiQVYexjenzA5itKt_CDx52t7508zYshp-1ERnEHuEwBic9Aw
---
<!-- 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. -->
# test-bert-finetuned-ner
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0600
- Precision: 0.9355
- Recall: 0.9514
- F1: 0.9433
- Accuracy: 0.9868
## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0849 | 1.0 | 1756 | 0.0713 | 0.9144 | 0.9366 | 0.9253 | 0.9817 |
| 0.0359 | 2.0 | 3512 | 0.0658 | 0.9346 | 0.9500 | 0.9422 | 0.9860 |
| 0.0206 | 3.0 | 5268 | 0.0600 | 0.9355 | 0.9514 | 0.9433 | 0.9868 |
### Framework versions
- Transformers 4.11.0.dev0
- Pytorch 1.8.1+cu111
- Datasets 1.12.1.dev0
- Tokenizers 0.10.3