Model save
Browse files
README.md
CHANGED
|
@@ -1,24 +1,9 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
-
datasets:
|
| 5 |
-
- akahana/GlotCC-V1-jav-Latn
|
| 6 |
-
metrics:
|
| 7 |
-
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: tinybert-javanese
|
| 10 |
-
results:
|
| 11 |
-
- task:
|
| 12 |
-
name: Masked Language Modeling
|
| 13 |
-
type: fill-mask
|
| 14 |
-
dataset:
|
| 15 |
-
name: akahana/GlotCC-V1-jav-Latn default
|
| 16 |
-
type: akahana/GlotCC-V1-jav-Latn
|
| 17 |
-
args: default
|
| 18 |
-
metrics:
|
| 19 |
-
- name: Accuracy
|
| 20 |
-
type: accuracy
|
| 21 |
-
value: 0.1519208618470086
|
| 22 |
---
|
| 23 |
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -26,10 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 26 |
|
| 27 |
# tinybert-javanese
|
| 28 |
|
| 29 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on
|
| 30 |
-
It achieves the following results on the evaluation set:
|
| 31 |
-
- Loss: 5.8252
|
| 32 |
-
- Accuracy: 0.1519
|
| 33 |
|
| 34 |
## Model description
|
| 35 |
|
|
@@ -49,12 +31,12 @@ More information needed
|
|
| 49 |
|
| 50 |
The following hyperparameters were used during training:
|
| 51 |
- learning_rate: 5e-05
|
| 52 |
-
- train_batch_size:
|
| 53 |
- eval_batch_size: 4
|
| 54 |
- seed: 42
|
| 55 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 56 |
- lr_scheduler_type: linear
|
| 57 |
-
- num_epochs:
|
| 58 |
- mixed_precision_training: Native AMP
|
| 59 |
|
| 60 |
### Training results
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
model-index:
|
| 5 |
- name: tinybert-javanese
|
| 6 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 11 |
|
| 12 |
# tinybert-javanese
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
|
|
|
| 31 |
|
| 32 |
The following hyperparameters were used during training:
|
| 33 |
- learning_rate: 5e-05
|
| 34 |
+
- train_batch_size: 32
|
| 35 |
- eval_batch_size: 4
|
| 36 |
- seed: 42
|
| 37 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 38 |
- lr_scheduler_type: linear
|
| 39 |
+
- num_epochs: 30.0
|
| 40 |
- mixed_precision_training: Native AMP
|
| 41 |
|
| 42 |
### Training results
|