update model card README.md
Browse files
README.md
CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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:
|
20 |
-
- Bleu:
|
21 |
-
- Gen Len: 6.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,16 +43,23 @@ The following hyperparameters were used during training:
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
-
- num_epochs:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
53 |
-
| No log | 1.0 | 31 | 3.
|
54 |
-
| No log | 2.0 | 62 | 3.
|
55 |
-
| No log | 3.0 | 93 | 3.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
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: 2.8772
|
20 |
+
- Bleu: 6.0639
|
21 |
+
- Gen Len: 6.0497
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 10
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
|
53 |
+
| No log | 1.0 | 31 | 3.4204 | 4.1421 | 6.7329 |
|
54 |
+
| No log | 2.0 | 62 | 3.2154 | 4.8111 | 5.9255 |
|
55 |
+
| No log | 3.0 | 93 | 3.1073 | 5.8324 | 5.9317 |
|
56 |
+
| No log | 4.0 | 124 | 3.0242 | 8.0401 | 5.8944 |
|
57 |
+
| No log | 5.0 | 155 | 2.9829 | 5.0246 | 6.0435 |
|
58 |
+
| No log | 6.0 | 186 | 2.9363 | 8.2048 | 5.9752 |
|
59 |
+
| No log | 7.0 | 217 | 2.9103 | 5.9443 | 6.0186 |
|
60 |
+
| No log | 8.0 | 248 | 2.8834 | 6.0896 | 6.0373 |
|
61 |
+
| No log | 9.0 | 279 | 2.8792 | 6.0346 | 6.0621 |
|
62 |
+
| No log | 10.0 | 310 | 2.8772 | 6.0639 | 6.0497 |
|
63 |
|
64 |
|
65 |
### Framework versions
|