Instructions to use somukandula/maskara-tiny-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use somukandula/maskara-tiny-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="somukandula/maskara-tiny-v2")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("somukandula/maskara-tiny-v2") model = AutoModelForTokenClassification.from_pretrained("somukandula/maskara-tiny-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- README.md +10 -10
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -21,9 +21,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
This model is a fine-tuned version of [somukandula/maskara-tiny](https://huggingface.co/somukandula/maskara-tiny) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 1.1264
|
| 24 |
-
- Precision: 0.
|
| 25 |
-
- Recall: 0.
|
| 26 |
-
- F1: 0.
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -55,13 +55,13 @@ The following hyperparameters were used during training:
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|
| 57 |
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.1062 | 0.1873 | 2000 | 1.
|
| 60 |
-
| 1.0024 | 0.2809 | 3000 | 1.2243 | 0.0605 | 0.
|
| 61 |
-
| 1.
|
| 62 |
-
| 0.962 | 0.4682 | 5000 | 1.
|
| 63 |
-
| 0.9539 | 0.5618 | 6000 | 1.
|
| 64 |
-
| 0.
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
|
|
|
| 21 |
This model is a fine-tuned version of [somukandula/maskara-tiny](https://huggingface.co/somukandula/maskara-tiny) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 1.1264
|
| 24 |
+
- Precision: 0.0627
|
| 25 |
+
- Recall: 0.2523
|
| 26 |
+
- F1: 0.1004
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|
| 57 |
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|
|
| 58 |
+
| 1.2386 | 0.0936 | 1000 | 1.4658 | 0.0466 | 0.1926 | 0.0751 |
|
| 59 |
+
| 1.1062 | 0.1873 | 2000 | 1.2917 | 0.0576 | 0.2296 | 0.0921 |
|
| 60 |
+
| 1.0024 | 0.2809 | 3000 | 1.2243 | 0.0605 | 0.2386 | 0.0966 |
|
| 61 |
+
| 1.0004 | 0.3745 | 4000 | 1.1891 | 0.0600 | 0.2425 | 0.0961 |
|
| 62 |
+
| 0.962 | 0.4682 | 5000 | 1.1587 | 0.0641 | 0.2515 | 0.1022 |
|
| 63 |
+
| 0.9539 | 0.5618 | 6000 | 1.1307 | 0.0627 | 0.2444 | 0.0998 |
|
| 64 |
+
| 0.9417 | 0.6554 | 7000 | 1.1264 | 0.0627 | 0.2523 | 0.1004 |
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 90327228
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a4ca7bd665f516fc40f6c6bc3d9c7beeed269245d288a304a127ae1716b1b51
|
| 3 |
size 90327228
|