Commit
•
53ac41f
1
Parent(s):
15785af
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- f1
|
| 6 |
+
model-index:
|
| 7 |
+
- name: mpnet-base-articles-ner
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# mpnet-base-articles-ner
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.8471
|
| 19 |
+
- F1: 0.7500
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 20
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 50 |
+
| 1.8042 | 1.0 | 5 | 1.6278 | 0.0 |
|
| 51 |
+
| 1.5353 | 2.0 | 10 | 1.5332 | 0.0 |
|
| 52 |
+
| 1.499 | 3.0 | 15 | 1.4356 | 0.1781 |
|
| 53 |
+
| 1.343 | 4.0 | 20 | 1.3254 | 0.3789 |
|
| 54 |
+
| 1.2306 | 5.0 | 25 | 1.2572 | 0.5075 |
|
| 55 |
+
| 1.1427 | 6.0 | 30 | 1.1572 | 0.5700 |
|
| 56 |
+
| 1.0715 | 7.0 | 35 | 1.0875 | 0.6305 |
|
| 57 |
+
| 0.9679 | 8.0 | 40 | 1.0261 | 0.6667 |
|
| 58 |
+
| 0.9169 | 9.0 | 45 | 0.9924 | 0.6512 |
|
| 59 |
+
| 0.8447 | 10.0 | 50 | 0.9457 | 0.7137 |
|
| 60 |
+
| 0.8253 | 11.0 | 55 | 0.9216 | 0.7094 |
|
| 61 |
+
| 0.7493 | 12.0 | 60 | 0.9068 | 0.7303 |
|
| 62 |
+
| 0.7378 | 13.0 | 65 | 0.8896 | 0.7404 |
|
| 63 |
+
| 0.7039 | 14.0 | 70 | 0.8827 | 0.7398 |
|
| 64 |
+
| 0.7277 | 15.0 | 75 | 0.8632 | 0.7635 |
|
| 65 |
+
| 0.6758 | 16.0 | 80 | 0.8517 | 0.775 |
|
| 66 |
+
| 0.6642 | 17.0 | 85 | 0.8618 | 0.7449 |
|
| 67 |
+
| 0.6327 | 18.0 | 90 | 0.8522 | 0.7490 |
|
| 68 |
+
| 0.6238 | 19.0 | 95 | 0.8477 | 0.7500 |
|
| 69 |
+
| 0.6101 | 20.0 | 100 | 0.8471 | 0.7500 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.24.0
|
| 75 |
+
- Pytorch 1.13.0+cu117
|
| 76 |
+
- Datasets 2.6.1
|
| 77 |
+
- Tokenizers 0.13.2
|