End of training
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
base_model: samzirbo/mT5.en-es.pretrained
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: baseline.europarl
|
| 7 |
results: []
|
|
@@ -13,6 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
# baseline.europarl
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [samzirbo/mT5.en-es.pretrained](https://huggingface.co/samzirbo/mT5.en-es.pretrained) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -40,6 +47,32 @@ The following hyperparameters were used during training:
|
|
| 40 |
- lr_scheduler_warmup_steps: 1000
|
| 41 |
- training_steps: 50000
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
### Framework versions
|
| 44 |
|
| 45 |
- Transformers 4.38.0
|
|
|
|
| 2 |
base_model: samzirbo/mT5.en-es.pretrained
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- bleu
|
| 7 |
model-index:
|
| 8 |
- name: baseline.europarl
|
| 9 |
results: []
|
|
|
|
| 15 |
# baseline.europarl
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [samzirbo/mT5.en-es.pretrained](https://huggingface.co/samzirbo/mT5.en-es.pretrained) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 3.5556
|
| 20 |
+
- Bleu: 28.4134
|
| 21 |
+
- Meteor: 0.548
|
| 22 |
+
- Chrf++: 50.7588
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 47 |
- lr_scheduler_warmup_steps: 1000
|
| 48 |
- training_steps: 50000
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor | Chrf++ |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|
|
| 54 |
+
| 3.7368 | 0.06 | 2500 | 3.7330 | 16.6348 | 0.4263 | 38.9851 |
|
| 55 |
+
| 1.9501 | 0.11 | 5000 | 3.6988 | 20.5694 | 0.4632 | 42.6268 |
|
| 56 |
+
| 1.7374 | 0.17 | 7500 | 3.6554 | 21.8374 | 0.4825 | 44.4332 |
|
| 57 |
+
| 1.6252 | 0.23 | 10000 | 3.6674 | 23.1212 | 0.4954 | 45.8093 |
|
| 58 |
+
| 1.5421 | 0.28 | 12500 | 3.6407 | 24.144 | 0.5063 | 47.0076 |
|
| 59 |
+
| 1.4867 | 0.34 | 15000 | 3.6991 | 23.9884 | 0.5055 | 46.9973 |
|
| 60 |
+
| 1.4413 | 0.39 | 17500 | 3.6669 | 25.0356 | 0.5135 | 47.6982 |
|
| 61 |
+
| 1.4017 | 0.45 | 20000 | 3.5988 | 25.4766 | 0.5201 | 48.3754 |
|
| 62 |
+
| 1.3769 | 0.51 | 22500 | 3.6120 | 26.17 | 0.5295 | 49.037 |
|
| 63 |
+
| 1.3476 | 0.56 | 25000 | 3.6225 | 26.8343 | 0.5341 | 49.5501 |
|
| 64 |
+
| 1.3252 | 0.62 | 27500 | 3.5913 | 26.7117 | 0.5321 | 49.3981 |
|
| 65 |
+
| 1.307 | 0.68 | 30000 | 3.6205 | 27.3269 | 0.5385 | 49.9517 |
|
| 66 |
+
| 1.2926 | 0.73 | 32500 | 3.5624 | 27.7597 | 0.5446 | 50.3568 |
|
| 67 |
+
| 1.2823 | 0.79 | 35000 | 3.5449 | 27.8457 | 0.5458 | 50.5179 |
|
| 68 |
+
| 1.2728 | 0.85 | 37500 | 3.5383 | 27.9605 | 0.5444 | 50.3421 |
|
| 69 |
+
| 1.2663 | 0.9 | 40000 | 3.5556 | 28.1962 | 0.5465 | 50.5512 |
|
| 70 |
+
| 1.2628 | 0.96 | 42500 | 3.5498 | 28.3077 | 0.5477 | 50.7074 |
|
| 71 |
+
| 1.2514 | 1.01 | 45000 | 3.5519 | 28.3543 | 0.548 | 50.7669 |
|
| 72 |
+
| 1.239 | 1.07 | 47500 | 3.5555 | 28.2177 | 0.5473 | 50.6922 |
|
| 73 |
+
| 1.2357 | 1.13 | 50000 | 3.5556 | 28.4134 | 0.548 | 50.7588 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
### Framework versions
|
| 77 |
|
| 78 |
- Transformers 4.38.0
|