update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,9 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: esp-to-lsm-model-split
|
| 7 |
results: []
|
|
@@ -14,15 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-es](https://huggingface.co/Helsinki-NLP/opus-mt-es-es) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
-
|
| 18 |
-
-
|
| 19 |
-
-
|
| 20 |
-
-
|
| 21 |
-
-
|
| 22 |
-
- eval_runtime: 4.9306
|
| 23 |
-
- eval_samples_per_second: 60.845
|
| 24 |
-
- eval_steps_per_second: 2.028
|
| 25 |
-
- step: 0
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -50,6 +49,32 @@ The following hyperparameters were used during training:
|
|
| 50 |
- num_epochs: 20
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.26.1
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- bleu
|
| 7 |
+
- rouge
|
| 8 |
model-index:
|
| 9 |
- name: esp-to-lsm-model-split
|
| 10 |
results: []
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-es](https://huggingface.co/Helsinki-NLP/opus-mt-es-es) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5258
|
| 21 |
+
- Bleu: 83.8782
|
| 22 |
+
- Ter: 10.6805
|
| 23 |
+
- Rouge1: 0.9238
|
| 24 |
+
- Rouge2: 0.8539
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 49 |
- num_epochs: 20
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Ter | Rouge1 | Rouge2 |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:------:|:------:|
|
| 56 |
+
| 1.0312 | 1.0 | 75 | 0.6799 | 70.9487 | 17.7958 | 0.8736 | 0.7858 |
|
| 57 |
+
| 0.4186 | 2.0 | 150 | 0.4926 | 50.7542 | 12.2855 | 0.9190 | 0.8516 |
|
| 58 |
+
| 0.2945 | 3.0 | 225 | 0.4174 | 72.8458 | 17.0732 | 0.9290 | 0.8649 |
|
| 59 |
+
| 0.1752 | 4.0 | 300 | 0.4505 | 81.4327 | 10.3884 | 0.9254 | 0.8485 |
|
| 60 |
+
| 0.1483 | 5.0 | 375 | 0.4863 | 39.1763 | 10.7498 | 0.9139 | 0.8411 |
|
| 61 |
+
| 0.1049 | 6.0 | 450 | 0.4795 | 81.2675 | 10.0271 | 0.9250 | 0.8572 |
|
| 62 |
+
| 0.0808 | 7.0 | 525 | 0.4824 | 80.2681 | 11.9241 | 0.9145 | 0.8251 |
|
| 63 |
+
| 0.0723 | 8.0 | 600 | 0.4388 | 83.9041 | 11.0208 | 0.9308 | 0.8690 |
|
| 64 |
+
| 0.0652 | 9.0 | 675 | 0.4277 | 85.0942 | 9.3948 | 0.9306 | 0.8718 |
|
| 65 |
+
| 0.0469 | 10.0 | 750 | 0.4310 | 84.8003 | 9.2141 | 0.9337 | 0.8766 |
|
| 66 |
+
| 0.043 | 11.0 | 825 | 0.4471 | 84.1771 | 9.9368 | 0.9297 | 0.8669 |
|
| 67 |
+
| 0.0278 | 12.0 | 900 | 0.4326 | 86.4289 | 8.5818 | 0.9404 | 0.8829 |
|
| 68 |
+
| 0.0258 | 13.0 | 975 | 0.4369 | 85.7966 | 8.7624 | 0.9363 | 0.8772 |
|
| 69 |
+
| 0.0258 | 14.0 | 1050 | 0.4296 | 86.5295 | 8.4914 | 0.9393 | 0.8856 |
|
| 70 |
+
| 0.0216 | 15.0 | 1125 | 0.4379 | 78.3156 | 14.7245 | 0.9321 | 0.8710 |
|
| 71 |
+
| 0.0132 | 16.0 | 1200 | 0.4400 | 87.1342 | 8.0397 | 0.9392 | 0.8839 |
|
| 72 |
+
| 0.0129 | 17.0 | 1275 | 0.4438 | 86.9282 | 8.1301 | 0.9383 | 0.8831 |
|
| 73 |
+
| 0.0109 | 18.0 | 1350 | 0.4445 | 86.7807 | 8.4914 | 0.9372 | 0.8813 |
|
| 74 |
+
| 0.0109 | 19.0 | 1425 | 0.4455 | 86.7006 | 8.4914 | 0.9371 | 0.8808 |
|
| 75 |
+
| 0.014 | 20.0 | 1500 | 0.4472 | 86.8515 | 8.3107 | 0.9378 | 0.882 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
### Framework versions
|
| 79 |
|
| 80 |
- Transformers 4.26.1
|