End of training
Browse files
README.md
CHANGED
|
@@ -15,6 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# git-base-caption
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -39,11 +42,18 @@ The following hyperparameters were used during training:
|
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
-
- num_epochs:
|
| 43 |
- mixed_precision_training: Native AMP
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
|
|
|
| 15 |
# git-base-caption
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 6.6179
|
| 20 |
+
- Wer Score: 9.0625
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 50
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
| 52 |
+
| 10.1592 | 10.0 | 10 | 8.7538 | 31.2656 |
|
| 53 |
+
| 8.2408 | 20.0 | 20 | 7.7825 | 31.5 |
|
| 54 |
+
| 7.4378 | 30.0 | 30 | 7.1866 | 15.625 |
|
| 55 |
+
| 6.9092 | 40.0 | 40 | 6.7962 | 9.375 |
|
| 56 |
+
| 6.5994 | 50.0 | 50 | 6.6179 | 9.0625 |
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|