Commit
•
c04c2df
1
Parent(s):
23d1f4c
End of training
Browse files- README.md +10 -4
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -10,12 +10,12 @@ model-index:
|
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
|
| 13 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pawankrgunjan/huggingface/runs/
|
| 14 |
# license_plate_recognizer
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [microsoft/trocr-base-handwritten](https://huggingface.co/microsoft/trocr-base-handwritten) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
| 19 |
- Cer: 0.0231
|
| 20 |
|
| 21 |
## Model description
|
|
@@ -41,13 +41,19 @@ The following hyperparameters were used during training:
|
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
- num_epochs:
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 50 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
|
|
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
|
| 13 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/pawankrgunjan/huggingface/runs/v5cu1qdh)
|
| 14 |
# license_plate_recognizer
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [microsoft/trocr-base-handwritten](https://huggingface.co/microsoft/trocr-base-handwritten) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0653
|
| 19 |
- Cer: 0.0231
|
| 20 |
|
| 21 |
## Model description
|
|
|
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 7
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 50 |
+
| 0.2605 | 1.0 | 254 | 0.0798 | 0.0253 |
|
| 51 |
+
| 0.138 | 2.0 | 508 | 0.0660 | 0.0177 |
|
| 52 |
+
| 0.0435 | 3.0 | 762 | 0.0645 | 0.0146 |
|
| 53 |
+
| 0.0344 | 4.0 | 1016 | 0.0594 | 0.0173 |
|
| 54 |
+
| 0.011 | 5.0 | 1270 | 0.0626 | 0.0160 |
|
| 55 |
+
| 0.0021 | 6.0 | 1524 | 0.0567 | 0.0120 |
|
| 56 |
+
| 0.0007 | 7.0 | 1778 | 0.0599 | 0.0137 |
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1335747032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:525634beb9097999b4dbaab4fda23135a57584a999e6d000593cdda8a4988895
|
| 3 |
size 1335747032
|