Commit
·
6476401
1
Parent(s):
262421b
update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# tokipona_model_v0.3
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 1.
|
| 20 |
-
- Bleu: 0.
|
| 21 |
- Gen Len: 19.0
|
| 22 |
|
| 23 |
## Model description
|
|
@@ -43,19 +43,23 @@ The following hyperparameters were used during training:
|
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
-
- num_epochs:
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
| 53 |
-
| No log | 1.0 | 55 |
|
| 54 |
-
| No log | 2.0 | 110 |
|
| 55 |
-
| No log | 3.0 | 165 |
|
| 56 |
-
| No log | 4.0 | 220 | 1.
|
| 57 |
-
| No log | 5.0 | 275 | 1.
|
| 58 |
-
| No log | 6.0 | 330 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
# tokipona_model_v0.3
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.8676
|
| 20 |
+
- Bleu: 0.0537
|
| 21 |
- Gen Len: 19.0
|
| 22 |
|
| 23 |
## Model description
|
|
|
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 10
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
| 53 |
+
| No log | 1.0 | 55 | 2.2419 | 0.0523 | 19.0 |
|
| 54 |
+
| No log | 2.0 | 110 | 2.0286 | 0.1719 | 19.0 |
|
| 55 |
+
| No log | 3.0 | 165 | 2.1105 | 0.1719 | 19.0 |
|
| 56 |
+
| No log | 4.0 | 220 | 1.9847 | 0.0393 | 19.0 |
|
| 57 |
+
| No log | 5.0 | 275 | 1.9553 | 0.0523 | 19.0 |
|
| 58 |
+
| No log | 6.0 | 330 | 2.0231 | 0.1719 | 19.0 |
|
| 59 |
+
| No log | 7.0 | 385 | 1.9451 | 0.1719 | 19.0 |
|
| 60 |
+
| No log | 8.0 | 440 | 1.9201 | 0.0537 | 19.0 |
|
| 61 |
+
| No log | 9.0 | 495 | 1.8968 | 0.0537 | 19.0 |
|
| 62 |
+
| 2.0859 | 10.0 | 550 | 1.8676 | 0.0537 | 19.0 |
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|