Model save
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: Helsinki-NLP/opus-mt-es-es
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: esp-to-lsm-model
|
| 8 |
results: []
|
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# esp-to-lsm-model
|
| 15 |
|
| 16 |
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.
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -41,6 +46,32 @@ The following hyperparameters were used during training:
|
|
| 41 |
- num_epochs: 20
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.41.2
|
|
|
|
| 3 |
base_model: Helsinki-NLP/opus-mt-es-es
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- bleu
|
| 8 |
model-index:
|
| 9 |
- name: esp-to-lsm-model
|
| 10 |
results: []
|
|
|
|
| 16 |
# esp-to-lsm-model
|
| 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: 0.4524
|
| 21 |
+
- Bleu: 68.8807
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 46 |
- num_epochs: 20
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 53 |
+
| 3.7222 | 1.0 | 75 | 2.6073 | 14.3097 |
|
| 54 |
+
| 1.9035 | 2.0 | 150 | 1.5408 | 44.9883 |
|
| 55 |
+
| 1.2424 | 3.0 | 225 | 1.1446 | 60.7215 |
|
| 56 |
+
| 0.9993 | 4.0 | 300 | 0.9445 | 49.9656 |
|
| 57 |
+
| 0.8131 | 5.0 | 375 | 0.8136 | 51.1677 |
|
| 58 |
+
| 0.68 | 6.0 | 450 | 0.7128 | 38.5475 |
|
| 59 |
+
| 0.63 | 7.0 | 525 | 0.6493 | 49.2921 |
|
| 60 |
+
| 0.4891 | 8.0 | 600 | 0.5980 | 67.6139 |
|
| 61 |
+
| 0.434 | 9.0 | 675 | 0.5642 | 74.1258 |
|
| 62 |
+
| 0.3897 | 10.0 | 750 | 0.5409 | 73.4943 |
|
| 63 |
+
| 0.3651 | 11.0 | 825 | 0.5166 | 56.0140 |
|
| 64 |
+
| 0.3205 | 12.0 | 900 | 0.4993 | 75.9506 |
|
| 65 |
+
| 0.3043 | 13.0 | 975 | 0.4861 | 76.3040 |
|
| 66 |
+
| 0.2814 | 14.0 | 1050 | 0.4757 | 52.8020 |
|
| 67 |
+
| 0.2571 | 15.0 | 1125 | 0.4648 | 67.2947 |
|
| 68 |
+
| 0.2743 | 16.0 | 1200 | 0.4632 | 52.5347 |
|
| 69 |
+
| 0.2327 | 17.0 | 1275 | 0.4568 | 69.9258 |
|
| 70 |
+
| 0.227 | 18.0 | 1350 | 0.4550 | 69.4897 |
|
| 71 |
+
| 0.2317 | 19.0 | 1425 | 0.4535 | 67.6997 |
|
| 72 |
+
| 0.2236 | 20.0 | 1500 | 0.4524 | 68.8807 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
### Framework versions
|
| 76 |
|
| 77 |
- Transformers 4.41.2
|