update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: roberta-base-finetuned-ner-agglo-twitter
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# roberta-base-finetuned-ner-agglo-twitter
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [ArBert/roberta-base-finetuned-ner](https://huggingface.co/ArBert/roberta-base-finetuned-ner) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.6645
|
| 22 |
+
- Precision: 0.6885
|
| 23 |
+
- Recall: 0.7665
|
| 24 |
+
- F1: 0.7254
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 2e-05
|
| 44 |
+
- train_batch_size: 16
|
| 45 |
+
- eval_batch_size: 16
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 20
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
|
| 55 |
+
| No log | 1.0 | 245 | 0.2820 | 0.6027 | 0.7543 | 0.6700 |
|
| 56 |
+
| No log | 2.0 | 490 | 0.2744 | 0.6308 | 0.7864 | 0.7000 |
|
| 57 |
+
| 0.2301 | 3.0 | 735 | 0.2788 | 0.6433 | 0.7637 | 0.6984 |
|
| 58 |
+
| 0.2301 | 4.0 | 980 | 0.3255 | 0.6834 | 0.7221 | 0.7022 |
|
| 59 |
+
| 0.1153 | 5.0 | 1225 | 0.3453 | 0.6686 | 0.7439 | 0.7043 |
|
| 60 |
+
| 0.1153 | 6.0 | 1470 | 0.3988 | 0.6797 | 0.7420 | 0.7094 |
|
| 61 |
+
| 0.0617 | 7.0 | 1715 | 0.4711 | 0.6702 | 0.7259 | 0.6969 |
|
| 62 |
+
| 0.0617 | 8.0 | 1960 | 0.4904 | 0.6904 | 0.7505 | 0.7192 |
|
| 63 |
+
| 0.0328 | 9.0 | 2205 | 0.5088 | 0.6591 | 0.7713 | 0.7108 |
|
| 64 |
+
| 0.0328 | 10.0 | 2450 | 0.5709 | 0.6468 | 0.7788 | 0.7067 |
|
| 65 |
+
| 0.019 | 11.0 | 2695 | 0.5570 | 0.6642 | 0.7533 | 0.7059 |
|
| 66 |
+
| 0.019 | 12.0 | 2940 | 0.5574 | 0.6899 | 0.7656 | 0.7258 |
|
| 67 |
+
| 0.0131 | 13.0 | 3185 | 0.5858 | 0.6952 | 0.7609 | 0.7265 |
|
| 68 |
+
| 0.0131 | 14.0 | 3430 | 0.6239 | 0.6556 | 0.7826 | 0.7135 |
|
| 69 |
+
| 0.0074 | 15.0 | 3675 | 0.5931 | 0.6825 | 0.7599 | 0.7191 |
|
| 70 |
+
| 0.0074 | 16.0 | 3920 | 0.6364 | 0.6785 | 0.7580 | 0.7161 |
|
| 71 |
+
| 0.005 | 17.0 | 4165 | 0.6437 | 0.6855 | 0.7580 | 0.7199 |
|
| 72 |
+
| 0.005 | 18.0 | 4410 | 0.6610 | 0.6779 | 0.7599 | 0.7166 |
|
| 73 |
+
| 0.0029 | 19.0 | 4655 | 0.6625 | 0.6853 | 0.7656 | 0.7232 |
|
| 74 |
+
| 0.0029 | 20.0 | 4900 | 0.6645 | 0.6885 | 0.7665 | 0.7254 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.16.2
|
| 80 |
+
- Pytorch 1.10.0+cu111
|
| 81 |
+
- Datasets 1.18.3
|
| 82 |
+
- Tokenizers 0.11.0
|