Update README.md
Browse files
README.md
CHANGED
@@ -16,10 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# romaneng2nep_v2
|
18 |
|
19 |
-
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 2.7225
|
22 |
-
- Bleu: 0.0
|
23 |
- Gen Len: 5.2131
|
24 |
|
25 |
## Model description
|
@@ -49,23 +48,23 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
-
|
54 |
-
| 15.2574 | 0.0626 | 1000 | 5.7371 |
|
55 |
-
| 6.1453 | 0.1251 | 2000 | 4.5094 |
|
56 |
-
| 5.3182 | 0.1877 | 3000 | 4.0351 |
|
57 |
-
| 4.9218 | 0.2503 | 4000 | 3.6947 |
|
58 |
-
| 4.6397 | 0.3128 | 5000 | 3.4644 |
|
59 |
-
| 4.433 | 0.3754 | 6000 | 3.3009 |
|
60 |
-
| 4.2494 | 0.4380 | 7000 | 3.1525 |
|
61 |
-
| 4.1467 | 0.5005 | 8000 | 3.0482 |
|
62 |
-
| 4.0272 | 0.5631 | 9000 | 2.9592 |
|
63 |
-
| 3.9598 | 0.6257 | 10000 | 2.8917 |
|
64 |
-
| 3.9116 | 0.6882 | 11000 | 2.8292 |
|
65 |
-
| 3.8435 | 0.7508 | 12000 | 2.7871 |
|
66 |
-
| 3.8047 | 0.8134 | 13000 | 2.7574 |
|
67 |
-
| 3.7818 | 0.8759 | 14000 | 2.7338 |
|
68 |
-
| 3.7764 | 0.9385 | 15000 | 2.7225 |
|
69 |
|
70 |
|
71 |
### Framework versions
|
|
|
16 |
|
17 |
# romaneng2nep_v2
|
18 |
|
19 |
+
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an [syubraj/roman2nepali-transliteration](https://huggingface.co/datasets/syubraj/roman2nepali-transliteration).
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 2.7225
|
|
|
22 |
- Gen Len: 5.2131
|
23 |
|
24 |
## Model description
|
|
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Gen Len |
|
52 |
+
|:-------------:|:------:|:-----:|:---------------:|:-------:|
|
53 |
+
| 15.2574 | 0.0626 | 1000 | 5.7371 | 2.0266 |
|
54 |
+
| 6.1453 | 0.1251 | 2000 | 4.5094 | 4.5514 |
|
55 |
+
| 5.3182 | 0.1877 | 3000 | 4.0351 | 4.7656 |
|
56 |
+
| 4.9218 | 0.2503 | 4000 | 3.6947 | 4.9841 |
|
57 |
+
| 4.6397 | 0.3128 | 5000 | 3.4644 | 5.1216 |
|
58 |
+
| 4.433 | 0.3754 | 6000 | 3.3009 | 5.2036 |
|
59 |
+
| 4.2494 | 0.4380 | 7000 | 3.1525 | 5.1748 |
|
60 |
+
| 4.1467 | 0.5005 | 8000 | 3.0482 | 5.232 |
|
61 |
+
| 4.0272 | 0.5631 | 9000 | 2.9592 | 5.253 |
|
62 |
+
| 3.9598 | 0.6257 | 10000 | 2.8917 | 5.1893 |
|
63 |
+
| 3.9116 | 0.6882 | 11000 | 2.8292 | 5.2252 |
|
64 |
+
| 3.8435 | 0.7508 | 12000 | 2.7871 | 5.2148 |
|
65 |
+
| 3.8047 | 0.8134 | 13000 | 2.7574 | 5.2123 |
|
66 |
+
| 3.7818 | 0.8759 | 14000 | 2.7338 | 5.2409 |
|
67 |
+
| 3.7764 | 0.9385 | 15000 | 2.7225 | 5.2131 |
|
68 |
|
69 |
|
70 |
### Framework versions
|