Commit
•
a480337
1
Parent(s):
5a18b60
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- conll2003
|
| 7 |
+
model-index:
|
| 8 |
+
- name: finetuned-test-1
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# finetuned-test-1
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the conll2003 dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.8192
|
| 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: 2e-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 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 2.8219 | 1.0 | 30 | 2.3343 |
|
| 52 |
+
| 2.4148 | 2.0 | 60 | 2.2010 |
|
| 53 |
+
| 2.3236 | 3.0 | 90 | 2.1442 |
|
| 54 |
+
| 2.2231 | 4.0 | 120 | 2.1651 |
|
| 55 |
+
| 2.2171 | 5.0 | 150 | 2.0614 |
|
| 56 |
+
| 2.127 | 6.0 | 180 | 2.0405 |
|
| 57 |
+
| 2.0748 | 7.0 | 210 | 2.0092 |
|
| 58 |
+
| 2.0511 | 8.0 | 240 | 1.9798 |
|
| 59 |
+
| 2.0097 | 9.0 | 270 | 1.8662 |
|
| 60 |
+
| 1.9969 | 10.0 | 300 | 1.9257 |
|
| 61 |
+
| 2.0006 | 11.0 | 330 | 1.9386 |
|
| 62 |
+
| 1.9273 | 12.0 | 360 | 1.9357 |
|
| 63 |
+
| 1.9177 | 13.0 | 390 | 1.8983 |
|
| 64 |
+
| 1.9128 | 14.0 | 420 | 1.8990 |
|
| 65 |
+
| 1.8979 | 15.0 | 450 | 1.9037 |
|
| 66 |
+
| 1.8721 | 16.0 | 480 | 1.8440 |
|
| 67 |
+
| 1.8998 | 17.0 | 510 | 1.8404 |
|
| 68 |
+
| 1.8862 | 18.0 | 540 | 1.9193 |
|
| 69 |
+
| 1.9133 | 19.0 | 570 | 1.8494 |
|
| 70 |
+
| 1.8799 | 20.0 | 600 | 1.8192 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.20.1
|
| 76 |
+
- Pytorch 1.11.0+cu113
|
| 77 |
+
- Datasets 2.3.2
|
| 78 |
+
- Tokenizers 0.12.1
|