Commit
·
04bb66c
1
Parent(s):
adc7eb0
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- un_multi
|
| 7 |
+
metrics:
|
| 8 |
+
- bleu
|
| 9 |
+
model-index:
|
| 10 |
+
- name: m2m100_418M-evaluated-en-to-ar-2000instancesUNMULTI-leaningRate2e-05-batchSize8-regu2
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Sequence-to-sequence Language Modeling
|
| 14 |
+
type: text2text-generation
|
| 15 |
+
dataset:
|
| 16 |
+
name: un_multi
|
| 17 |
+
type: un_multi
|
| 18 |
+
args: ar-en
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Bleu
|
| 21 |
+
type: bleu
|
| 22 |
+
value: 40.8245
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# m2m100_418M-evaluated-en-to-ar-2000instancesUNMULTI-leaningRate2e-05-batchSize8-regu2
|
| 29 |
+
|
| 30 |
+
This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the un_multi dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.3642
|
| 33 |
+
- Bleu: 40.8245
|
| 34 |
+
- Meteor: 0.4272
|
| 35 |
+
- Gen Len: 41.8075
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 2e-05
|
| 55 |
+
- train_batch_size: 8
|
| 56 |
+
- eval_batch_size: 8
|
| 57 |
+
- seed: 42
|
| 58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 59 |
+
- lr_scheduler_type: linear
|
| 60 |
+
- num_epochs: 11
|
| 61 |
+
- mixed_precision_training: Native AMP
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor | Gen Len |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|
|
| 67 |
+
| 5.1584 | 0.5 | 100 | 3.2518 | 30.3723 | 0.3633 | 41.5 |
|
| 68 |
+
| 2.1351 | 1.0 | 200 | 0.9929 | 32.9915 | 0.3833 | 41.8225 |
|
| 69 |
+
| 0.568 | 1.5 | 300 | 0.4312 | 33.705 | 0.3896 | 42.6225 |
|
| 70 |
+
| 0.3749 | 2.0 | 400 | 0.3697 | 36.9316 | 0.4084 | 40.57 |
|
| 71 |
+
| 0.2376 | 2.5 | 500 | 0.3587 | 37.6782 | 0.4124 | 41.99 |
|
| 72 |
+
| 0.2435 | 3.0 | 600 | 0.3529 | 37.9931 | 0.4128 | 42.02 |
|
| 73 |
+
| 0.1706 | 3.5 | 700 | 0.3531 | 39.9972 | 0.4252 | 41.8025 |
|
| 74 |
+
| 0.165 | 4.0 | 800 | 0.3514 | 39.3155 | 0.42 | 41.0275 |
|
| 75 |
+
| 0.1273 | 4.5 | 900 | 0.3606 | 40.0765 | 0.4234 | 41.6175 |
|
| 76 |
+
| 0.1307 | 5.0 | 1000 | 0.3550 | 40.4468 | 0.428 | 41.72 |
|
| 77 |
+
| 0.0926 | 5.5 | 1100 | 0.3603 | 40.5454 | 0.4307 | 41.765 |
|
| 78 |
+
| 0.1096 | 6.0 | 1200 | 0.3613 | 40.5691 | 0.4298 | 42.31 |
|
| 79 |
+
| 0.0826 | 6.5 | 1300 | 0.3642 | 40.8245 | 0.4272 | 41.8075 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.20.1
|
| 85 |
+
- Pytorch 1.11.0
|
| 86 |
+
- Datasets 2.1.0
|
| 87 |
+
- Tokenizers 0.12.1
|