update model card README.md
Browse files
README.md
CHANGED
|
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the common_language dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 1.
|
| 23 |
-
- Accuracy: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -42,14 +42,14 @@ The following hyperparameters were used during training:
|
|
| 42 |
- learning_rate: 0.0001
|
| 43 |
- train_batch_size: 1
|
| 44 |
- eval_batch_size: 4
|
| 45 |
-
- seed:
|
| 46 |
- distributed_type: IPU
|
| 47 |
- gradient_accumulation_steps: 32
|
| 48 |
- total_train_batch_size: 128
|
| 49 |
- total_eval_batch_size: 64
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
-
- lr_scheduler_warmup_ratio: 0.
|
| 53 |
- num_epochs: 10.0
|
| 54 |
- training precision: Mixed Precision
|
| 55 |
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the common_language dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.3477
|
| 23 |
+
- Accuracy: 0.7317
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 42 |
- learning_rate: 0.0001
|
| 43 |
- train_batch_size: 1
|
| 44 |
- eval_batch_size: 4
|
| 45 |
+
- seed: 0
|
| 46 |
- distributed_type: IPU
|
| 47 |
- gradient_accumulation_steps: 32
|
| 48 |
- total_train_batch_size: 128
|
| 49 |
- total_eval_batch_size: 64
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.25
|
| 53 |
- num_epochs: 10.0
|
| 54 |
- training precision: Mixed Precision
|
| 55 |
|