Daniel Bogdoll
commited on
End of training
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [SenseTime/deformable-detr](https://huggingface.co/SenseTime/deformable-detr) on the generator dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 1.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -38,33 +38,27 @@ More information needed
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 5e-05
|
| 41 |
-
- train_batch_size:
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 0
|
| 44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
-
- num_epochs:
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 53 |
-
| 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.5054 | 10.0 | 52880 | 1.1585 |
|
| 63 |
-
| 0.4795 | 11.0 | 58168 | 1.2366 |
|
| 64 |
-
| 0.4809 | 12.0 | 63456 | 1.2193 |
|
| 65 |
-
| 0.4825 | 13.0 | 68744 | 1.2375 |
|
| 66 |
-
| 0.4535 | 14.0 | 74032 | 1.2542 |
|
| 67 |
-
| 0.4357 | 15.0 | 79320 | 1.2359 |
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [SenseTime/deformable-detr](https://huggingface.co/SenseTime/deformable-detr) on the generator dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.2335
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 0
|
| 44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
+
- num_epochs: 36
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:-----:|:---------------:|
|
| 53 |
+
| 0.8943 | 1.0 | 5288 | 1.5330 |
|
| 54 |
+
| 0.7865 | 2.0 | 10576 | 1.4108 |
|
| 55 |
+
| 0.7238 | 3.0 | 15864 | 1.2660 |
|
| 56 |
+
| 0.6657 | 4.0 | 21152 | 1.2084 |
|
| 57 |
+
| 0.646 | 5.0 | 26440 | 1.2666 |
|
| 58 |
+
| 0.6269 | 6.0 | 31728 | 1.2555 |
|
| 59 |
+
| 0.6049 | 7.0 | 37016 | 1.2350 |
|
| 60 |
+
| 0.5894 | 8.0 | 42304 | 1.2940 |
|
| 61 |
+
| 0.5484 | 9.0 | 47592 | 1.2335 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
runs/Feb15_04-53-41_mcity-rtx-4090/events.out.tfevents.1739613221.mcity-rtx-4090.1139582.13
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93de94cc75d18269d165cd9faf7c20ffd5808e146a29556ad9ad2e22ca94fbe6
|
| 3 |
+
size 29356
|