End of training
Browse files
README.md
CHANGED
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model was trained from scratch on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
- Loss: 0.
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -44,13 +44,17 @@ The following hyperparameters were used during training:
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_steps: 30
|
| 47 |
-
- training_steps:
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
-
| Training Loss | Epoch
|
| 52 |
-
|
| 53 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
|
| 55 |
|
| 56 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
This model was trained from scratch on an unknown dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.3129
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_steps: 30
|
| 47 |
+
- training_steps: 500
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 0.1359 | 0.2 | 100 | 0.1768 |
|
| 54 |
+
| 0.0804 | 0.4 | 200 | 0.2530 |
|
| 55 |
+
| 0.0573 | 0.6 | 300 | 0.2863 |
|
| 56 |
+
| 0.0415 | 0.8 | 400 | 0.3172 |
|
| 57 |
+
| 0.0422 | 1.0 | 500 | 0.3129 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|