Sim
commited on
Commit
•
a292260
1
Parent(s):
8b662f6
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- bleu
|
| 7 |
+
model-index:
|
| 8 |
+
- name: NLLB-600m-vie_Latn-to-eng_Latn
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# NLLB-600m-vie_Latn-to-eng_Latn
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.1189
|
| 20 |
+
- Bleu: 36.6767
|
| 21 |
+
- Gen Len: 47.504
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 3
|
| 42 |
+
- eval_batch_size: 3
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 8
|
| 45 |
+
- total_train_batch_size: 24
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- training_steps: 10000
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
| 55 |
+
| 1.9294 | 2.24 | 1000 | 1.5970 | 23.6201 | 48.1 |
|
| 56 |
+
| 1.4 | 4.47 | 2000 | 1.3216 | 28.9526 | 45.156 |
|
| 57 |
+
| 1.2071 | 6.71 | 3000 | 1.2245 | 32.5538 | 46.576 |
|
| 58 |
+
| 1.0893 | 8.95 | 4000 | 1.1720 | 34.265 | 46.052 |
|
| 59 |
+
| 1.0064 | 11.19 | 5000 | 1.1497 | 34.9249 | 46.508 |
|
| 60 |
+
| 0.9562 | 13.42 | 6000 | 1.1331 | 36.4619 | 47.244 |
|
| 61 |
+
| 0.9183 | 15.66 | 7000 | 1.1247 | 36.4723 | 47.26 |
|
| 62 |
+
| 0.8858 | 17.9 | 8000 | 1.1198 | 36.7058 | 47.376 |
|
| 63 |
+
| 0.8651 | 20.13 | 9000 | 1.1201 | 36.7897 | 47.496 |
|
| 64 |
+
| 0.8546 | 22.37 | 10000 | 1.1189 | 36.6767 | 47.504 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.22.1
|
| 70 |
+
- Pytorch 1.12.1+cu113
|
| 71 |
+
- Datasets 2.4.0
|
| 72 |
+
- Tokenizers 0.12.1
|