Commit
•
0028392
1
Parent(s):
cb8d0f0
Training in progress epoch 0
Browse files- README.md +7 -35
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -15,8 +15,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [Davlan/afro-xlmr-small](https://huggingface.co/Davlan/afro-xlmr-small) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Train Loss: 0.
|
| 19 |
-
-
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -35,43 +36,14 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps':
|
| 39 |
- training_precision: mixed_float16
|
| 40 |
|
| 41 |
### Training results
|
| 42 |
|
| 43 |
-
| Train Loss | Epoch |
|
| 44 |
-
|
| 45 |
-
| 0.
|
| 46 |
-
| 0.4847 | 1 |
|
| 47 |
-
| 0.4696 | 2 |
|
| 48 |
-
| 0.4725 | 3 |
|
| 49 |
-
| 0.4649 | 4 |
|
| 50 |
-
| 0.4871 | 5 |
|
| 51 |
-
| 0.4881 | 6 |
|
| 52 |
-
| 0.4765 | 7 |
|
| 53 |
-
| 0.4761 | 8 |
|
| 54 |
-
| 0.4765 | 9 |
|
| 55 |
-
| 0.4690 | 10 |
|
| 56 |
-
| 0.4781 | 11 |
|
| 57 |
-
| 0.4706 | 12 |
|
| 58 |
-
| 0.4818 | 13 |
|
| 59 |
-
| 0.4917 | 14 |
|
| 60 |
-
| 0.4783 | 15 |
|
| 61 |
-
| 0.4583 | 16 |
|
| 62 |
-
| 0.4575 | 17 |
|
| 63 |
-
| 0.4832 | 18 |
|
| 64 |
-
| 0.4638 | 19 |
|
| 65 |
-
| 0.4770 | 20 |
|
| 66 |
-
| 0.4709 | 21 |
|
| 67 |
-
| 0.4705 | 22 |
|
| 68 |
-
| 0.4715 | 23 |
|
| 69 |
-
| 0.4858 | 24 |
|
| 70 |
-
| 0.4592 | 25 |
|
| 71 |
-
| 0.4917 | 26 |
|
| 72 |
-
| 0.4635 | 27 |
|
| 73 |
-
| 0.4506 | 28 |
|
| 74 |
-
| 0.4860 | 29 |
|
| 75 |
|
| 76 |
|
| 77 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [Davlan/afro-xlmr-small](https://huggingface.co/Davlan/afro-xlmr-small) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 0.4984
|
| 19 |
+
- Validation Loss: 0.0
|
| 20 |
+
- Epoch: 0
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
+
- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 171, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.03}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
|
| 40 |
- training_precision: mixed_float16
|
| 41 |
|
| 42 |
### Training results
|
| 43 |
|
| 44 |
+
| Train Loss | Validation Loss | Epoch |
|
| 45 |
+
|:----------:|:---------------:|:-----:|
|
| 46 |
+
| 0.4984 | 0.0 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559016168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bc20d0a69e04f56528aed767023cc91f01bc54de498fcabb3bda296199cc53a
|
| 3 |
size 559016168
|