Commit
·
25a5075
1
Parent(s):
7211222
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
metrics:
|
| 6 |
-
- precision
|
| 7 |
-
- recall
|
| 8 |
-
- f1
|
| 9 |
-
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: my_awesome_propaganda_model
|
| 12 |
results: []
|
|
@@ -17,13 +12,18 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# my_awesome_propaganda_model
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
-
|
| 23 |
-
-
|
| 24 |
-
-
|
| 25 |
-
-
|
| 26 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -50,22 +50,6 @@ The following hyperparameters were used during training:
|
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- num_epochs: 10
|
| 52 |
|
| 53 |
-
### Training results
|
| 54 |
-
|
| 55 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 56 |
-
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 57 |
-
| No log | 1.0 | 193 | 0.5297 | 0.1723 | 0.0333 | 0.0559 | 0.9032 |
|
| 58 |
-
| No log | 2.0 | 386 | 0.5410 | 0.0591 | 0.0522 | 0.0554 | 0.8802 |
|
| 59 |
-
| 0.3857 | 3.0 | 579 | 0.5694 | 0.0631 | 0.0464 | 0.0535 | 0.8820 |
|
| 60 |
-
| 0.3857 | 4.0 | 772 | 0.6084 | 0.0750 | 0.0551 | 0.0635 | 0.8846 |
|
| 61 |
-
| 0.3857 | 5.0 | 965 | 0.6349 | 0.0627 | 0.0587 | 0.0607 | 0.8745 |
|
| 62 |
-
| 0.2157 | 6.0 | 1158 | 0.6700 | 0.0510 | 0.0580 | 0.0542 | 0.8689 |
|
| 63 |
-
| 0.2157 | 7.0 | 1351 | 0.6844 | 0.0658 | 0.0580 | 0.0617 | 0.8811 |
|
| 64 |
-
| 0.1291 | 8.0 | 1544 | 0.7029 | 0.0752 | 0.0601 | 0.0668 | 0.8847 |
|
| 65 |
-
| 0.1291 | 9.0 | 1737 | 0.7117 | 0.0637 | 0.0638 | 0.0637 | 0.8791 |
|
| 66 |
-
| 0.1291 | 10.0 | 1930 | 0.7170 | 0.0570 | 0.0558 | 0.0564 | 0.8793 |
|
| 67 |
-
|
| 68 |
-
|
| 69 |
### Framework versions
|
| 70 |
|
| 71 |
- Transformers 4.30.0
|
|
|
|
| 1 |
---
|
| 2 |
+
license: mit
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: my_awesome_propaganda_model
|
| 7 |
results: []
|
|
|
|
| 12 |
|
| 13 |
# my_awesome_propaganda_model
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- eval_loss: 0.6799
|
| 18 |
+
- eval_precision: 0.0639
|
| 19 |
+
- eval_recall: 0.0725
|
| 20 |
+
- eval_f1: 0.0679
|
| 21 |
+
- eval_accuracy: 0.8635
|
| 22 |
+
- eval_runtime: 12.6134
|
| 23 |
+
- eval_samples_per_second: 66.516
|
| 24 |
+
- eval_steps_per_second: 4.202
|
| 25 |
+
- epoch: 8.0
|
| 26 |
+
- step: 1416
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- num_epochs: 10
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.30.0
|