Sim
commited on
Commit
·
992d921
1
Parent(s):
8b4dad6
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- bleu
|
7 |
+
model-index:
|
8 |
+
- name: nllb-200-distilled-600M-finetuned-pan_Guru-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-200-distilled-600M-finetuned-pan_Guru-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: 0.8728
|
20 |
+
- Bleu: 42.5453
|
21 |
+
- Gen Len: 32.376
|
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: 4
|
42 |
+
- eval_batch_size: 4
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 16
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 6
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
54 |
+
| 1.5153 | 0.72 | 500 | 1.0531 | 34.9696 | 32.548 |
|
55 |
+
| 1.1282 | 1.45 | 1000 | 0.9580 | 38.3648 | 31.832 |
|
56 |
+
| 1.0299 | 2.18 | 1500 | 0.9235 | 40.1212 | 31.964 |
|
57 |
+
| 0.942 | 2.9 | 2000 | 0.8963 | 41.2737 | 31.884 |
|
58 |
+
| 0.8869 | 3.63 | 2500 | 0.8847 | 41.4381 | 31.82 |
|
59 |
+
| 0.8553 | 4.35 | 3000 | 0.8780 | 42.1548 | 32.136 |
|
60 |
+
| 0.8306 | 5.08 | 3500 | 0.8733 | 42.3333 | 32.64 |
|
61 |
+
| 0.8063 | 5.8 | 4000 | 0.8728 | 42.5453 | 32.376 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.21.2
|
67 |
+
- Pytorch 1.12.1+cu113
|
68 |
+
- Datasets 2.4.0
|
69 |
+
- Tokenizers 0.12.1
|