End of training
Browse files
README.md
CHANGED
|
@@ -7,6 +7,7 @@ metrics:
|
|
| 7 |
- precision
|
| 8 |
- recall
|
| 9 |
- f1
|
|
|
|
| 10 |
model-index:
|
| 11 |
- name: my_awesome_wnut_model3
|
| 12 |
results: []
|
|
@@ -19,24 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [Atheer174/my_awesome_wnut_model3](https://huggingface.co/Atheer174/my_awesome_wnut_model3) on an unknown dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
| 23 |
-
- Precision: 0.
|
| 24 |
-
- Recall: 0.
|
| 25 |
-
- F1: 0.
|
| 26 |
-
-
|
| 27 |
-
|
| 28 |
-
Country 1.00 1.00 1.00 9877
|
| 29 |
-
HSCode 1.00 1.00 1.00 9877
|
| 30 |
-
HSCodeEn 1.00 1.00 1.00 9877
|
| 31 |
-
Manufacturer 1.00 1.00 1.00 9877
|
| 32 |
-
ModelNo 1.00 1.00 1.00 9877
|
| 33 |
-
Product 1.00 1.00 1.00 9877
|
| 34 |
-
Trademark 1.00 1.00 1.00 9877
|
| 35 |
-
|
| 36 |
-
micro avg 1.00 1.00 1.00 69139
|
| 37 |
-
macro avg 1.00 1.00 1.00 69139
|
| 38 |
-
weighted avg 1.00 1.00 1.00 69139
|
| 39 |
-
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
|
@@ -61,40 +49,13 @@ The following hyperparameters were used during training:
|
|
| 61 |
- seed: 42
|
| 62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
- lr_scheduler_type: linear
|
| 64 |
-
- num_epochs:
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
-
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|
| 69 |
-
|
| 70 |
-
| 0.0005 | 1.0 | 2470 | 0.
|
| 71 |
-
|
| 72 |
-
Country 1.00 1.00 1.00 9877
|
| 73 |
-
HSCode 1.00 1.00 1.00 9877
|
| 74 |
-
HSCodeEn 1.00 1.00 1.00 9877
|
| 75 |
-
Manufacturer 0.99 0.99 0.99 9877
|
| 76 |
-
ModelNo 1.00 1.00 1.00 9877
|
| 77 |
-
Product 1.00 1.00 1.00 9877
|
| 78 |
-
Trademark 1.00 1.00 1.00 9877
|
| 79 |
-
|
| 80 |
-
micro avg 1.00 1.00 1.00 69139
|
| 81 |
-
macro avg 1.00 1.00 1.00 69139
|
| 82 |
-
weighted avg 1.00 1.00 1.00 69139
|
| 83 |
-
|
|
| 84 |
-
| 0.0001 | 2.0 | 4940 | 0.0079 | 0.9980 | 0.9982 | 0.9981 | precision recall f1-score support
|
| 85 |
-
|
| 86 |
-
Country 1.00 1.00 1.00 9877
|
| 87 |
-
HSCode 1.00 1.00 1.00 9877
|
| 88 |
-
HSCodeEn 1.00 1.00 1.00 9877
|
| 89 |
-
Manufacturer 1.00 1.00 1.00 9877
|
| 90 |
-
ModelNo 1.00 1.00 1.00 9877
|
| 91 |
-
Product 1.00 1.00 1.00 9877
|
| 92 |
-
Trademark 1.00 1.00 1.00 9877
|
| 93 |
-
|
| 94 |
-
micro avg 1.00 1.00 1.00 69139
|
| 95 |
-
macro avg 1.00 1.00 1.00 69139
|
| 96 |
-
weighted avg 1.00 1.00 1.00 69139
|
| 97 |
-
|
|
| 98 |
|
| 99 |
|
| 100 |
### Framework versions
|
|
|
|
| 7 |
- precision
|
| 8 |
- recall
|
| 9 |
- f1
|
| 10 |
+
- accuracy
|
| 11 |
model-index:
|
| 12 |
- name: my_awesome_wnut_model3
|
| 13 |
results: []
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [Atheer174/my_awesome_wnut_model3](https://huggingface.co/Atheer174/my_awesome_wnut_model3) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.0102
|
| 24 |
+
- Precision: 0.9975
|
| 25 |
+
- Recall: 0.9979
|
| 26 |
+
- F1: 0.9977
|
| 27 |
+
- Accuracy: 0.9987
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 49 |
- seed: 42
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 1
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| 0.0005 | 1.0 | 2470 | 0.0102 | 0.9975 | 0.9979 | 0.9977 | 0.9987 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|