Model save
Browse files- README.md +91 -85
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
license: cc-by-4.0
|
| 4 |
base_model: facebook/nougat-base
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
@@ -14,10 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# dhivehi-nougat-base
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [facebook/nougat-base](https://huggingface.co/facebook/nougat-base) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
|
| 20 |
-
- Loss: 0.0300
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -36,7 +34,6 @@ More information needed
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
-
|
| 40 |
- learning_rate: 0.0001
|
| 41 |
- train_batch_size: 3
|
| 42 |
- eval_batch_size: 3
|
|
@@ -51,86 +48,95 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
| 2.
|
| 64 |
-
| 1.
|
| 65 |
-
| 1.
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 134 |
|
| 135 |
|
| 136 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
| 3 |
base_model: facebook/nougat-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 13 |
|
| 14 |
# dhivehi-nougat-base
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [facebook/nougat-base](https://huggingface.co/facebook/nougat-base) on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0142
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 34 |
### Training hyperparameters
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
|
|
|
| 37 |
- learning_rate: 0.0001
|
| 38 |
- train_batch_size: 3
|
| 39 |
- eval_batch_size: 3
|
|
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:------:|:----:|:---------------:|
|
| 51 |
+
| 6.4404 | 0.0057 | 100 | 1.0417 |
|
| 52 |
+
| 5.7761 | 0.0114 | 200 | 0.9055 |
|
| 53 |
+
| 5.1723 | 0.0171 | 300 | 0.8193 |
|
| 54 |
+
| 4.8315 | 0.0228 | 400 | 0.7661 |
|
| 55 |
+
| 4.4217 | 0.0285 | 500 | 0.7232 |
|
| 56 |
+
| 3.9861 | 0.0342 | 600 | 0.6724 |
|
| 57 |
+
| 3.7268 | 0.0400 | 700 | 0.5966 |
|
| 58 |
+
| 3.5393 | 0.0457 | 800 | 0.5337 |
|
| 59 |
+
| 2.8666 | 0.0514 | 900 | 0.4108 |
|
| 60 |
+
| 2.0269 | 0.0571 | 1000 | 0.2803 |
|
| 61 |
+
| 1.4121 | 0.0628 | 1100 | 0.1904 |
|
| 62 |
+
| 1.0161 | 0.0685 | 1200 | 0.1351 |
|
| 63 |
+
| 0.867 | 0.0742 | 1300 | 0.1130 |
|
| 64 |
+
| 0.7506 | 0.0799 | 1400 | 0.0950 |
|
| 65 |
+
| 0.5764 | 0.0856 | 1500 | 0.0801 |
|
| 66 |
+
| 0.5123 | 0.0913 | 1600 | 0.0716 |
|
| 67 |
+
| 0.558 | 0.0970 | 1700 | 0.0650 |
|
| 68 |
+
| 0.5242 | 0.1027 | 1800 | 0.0616 |
|
| 69 |
+
| 0.4229 | 0.1084 | 1900 | 0.0556 |
|
| 70 |
+
| 0.3721 | 0.1142 | 2000 | 0.0545 |
|
| 71 |
+
| 0.3388 | 0.1199 | 2100 | 0.0519 |
|
| 72 |
+
| 0.4042 | 0.1256 | 2200 | 0.0499 |
|
| 73 |
+
| 0.3593 | 0.1313 | 2300 | 0.0449 |
|
| 74 |
+
| 0.3837 | 0.1370 | 2400 | 0.0421 |
|
| 75 |
+
| 0.3291 | 0.1427 | 2500 | 0.0407 |
|
| 76 |
+
| 0.3092 | 0.1484 | 2600 | 0.0388 |
|
| 77 |
+
| 0.2762 | 0.1541 | 2700 | 0.0380 |
|
| 78 |
+
| 0.3073 | 0.1598 | 2800 | 0.0422 |
|
| 79 |
+
| 0.2577 | 0.1655 | 2900 | 0.0340 |
|
| 80 |
+
| 0.2596 | 0.1712 | 3000 | 0.0331 |
|
| 81 |
+
| 0.3397 | 0.1769 | 3100 | 0.0328 |
|
| 82 |
+
| 0.3019 | 0.1826 | 3200 | 0.0307 |
|
| 83 |
+
| 0.2522 | 0.1884 | 3300 | 0.0314 |
|
| 84 |
+
| 0.2546 | 0.1941 | 3400 | 0.0289 |
|
| 85 |
+
| 0.1972 | 0.1998 | 3500 | 0.0282 |
|
| 86 |
+
| 0.2231 | 0.2055 | 3600 | 0.0300 |
|
| 87 |
+
| 0.2342 | 0.2112 | 3700 | 0.0278 |
|
| 88 |
+
| 0.2152 | 0.2169 | 3800 | 0.0276 |
|
| 89 |
+
| 0.2059 | 0.2226 | 3900 | 0.0260 |
|
| 90 |
+
| 0.2165 | 0.2283 | 4000 | 0.0257 |
|
| 91 |
+
| 0.1919 | 0.2340 | 4100 | 0.0253 |
|
| 92 |
+
| 0.1608 | 0.2397 | 4200 | 0.0244 |
|
| 93 |
+
| 0.1673 | 0.2454 | 4300 | 0.0242 |
|
| 94 |
+
| 0.2004 | 0.2511 | 4400 | 0.0248 |
|
| 95 |
+
| 0.2277 | 0.2568 | 4500 | 0.0230 |
|
| 96 |
+
| 0.1831 | 0.2625 | 4600 | 0.0228 |
|
| 97 |
+
| 0.1905 | 0.2683 | 4700 | 0.0221 |
|
| 98 |
+
| 0.0996 | 0.2740 | 4800 | 0.0215 |
|
| 99 |
+
| 0.1596 | 0.2797 | 4900 | 0.0213 |
|
| 100 |
+
| 0.168 | 0.2854 | 5000 | 0.0208 |
|
| 101 |
+
| 0.2119 | 0.2911 | 5100 | 0.0215 |
|
| 102 |
+
| 0.1436 | 0.2968 | 5200 | 0.0202 |
|
| 103 |
+
| 0.1656 | 0.3025 | 5300 | 0.0202 |
|
| 104 |
+
| 0.1183 | 0.3082 | 5400 | 0.0194 |
|
| 105 |
+
| 0.1397 | 0.3139 | 5500 | 0.0202 |
|
| 106 |
+
| 0.1248 | 0.3196 | 5600 | 0.0191 |
|
| 107 |
+
| 0.1202 | 0.3253 | 5700 | 0.0191 |
|
| 108 |
+
| 0.1175 | 0.3310 | 5800 | 0.0207 |
|
| 109 |
+
| 0.1427 | 0.3367 | 5900 | 0.0183 |
|
| 110 |
+
| 0.1487 | 0.3425 | 6000 | 0.0178 |
|
| 111 |
+
| 0.1597 | 0.3482 | 6100 | 0.0174 |
|
| 112 |
+
| 0.1363 | 0.3539 | 6200 | 0.0172 |
|
| 113 |
+
| 0.1266 | 0.3596 | 6300 | 0.0171 |
|
| 114 |
+
| 0.1288 | 0.3653 | 6400 | 0.0170 |
|
| 115 |
+
| 0.1202 | 0.3710 | 6500 | 0.0170 |
|
| 116 |
+
| 0.1174 | 0.3767 | 6600 | 0.0164 |
|
| 117 |
+
| 0.1334 | 0.3824 | 6700 | 0.0168 |
|
| 118 |
+
| 0.1627 | 0.3881 | 6800 | 0.0164 |
|
| 119 |
+
| 0.0982 | 0.3938 | 6900 | 0.0161 |
|
| 120 |
+
| 0.1038 | 0.3995 | 7000 | 0.0160 |
|
| 121 |
+
| 0.1523 | 0.4052 | 7100 | 0.0160 |
|
| 122 |
+
| 0.1337 | 0.4109 | 7200 | 0.0157 |
|
| 123 |
+
| 0.2063 | 0.4167 | 7300 | 0.0153 |
|
| 124 |
+
| 0.1476 | 0.4224 | 7400 | 0.0156 |
|
| 125 |
+
| 0.0838 | 0.4281 | 7500 | 0.0150 |
|
| 126 |
+
| 0.082 | 0.4338 | 7600 | 0.0158 |
|
| 127 |
+
| 0.1269 | 0.4395 | 7700 | 0.0159 |
|
| 128 |
+
| 0.1168 | 0.4452 | 7800 | 0.0147 |
|
| 129 |
+
| 0.1024 | 0.4509 | 7900 | 0.0147 |
|
| 130 |
+
| 0.1138 | 0.4566 | 8000 | 0.0145 |
|
| 131 |
+
| 0.1188 | 0.4623 | 8100 | 0.0146 |
|
| 132 |
+
| 0.0881 | 0.4680 | 8200 | 0.0142 |
|
| 133 |
+
| 0.0752 | 0.4737 | 8300 | 0.0138 |
|
| 134 |
+
| 0.1165 | 0.4794 | 8400 | 0.0141 |
|
| 135 |
+
| 0.1017 | 0.4851 | 8500 | 0.0137 |
|
| 136 |
+
| 0.0971 | 0.4909 | 8600 | 0.0135 |
|
| 137 |
+
| 0.135 | 0.4966 | 8700 | 0.0136 |
|
| 138 |
+
| 0.0732 | 0.5023 | 8800 | 0.0137 |
|
| 139 |
+
| 0.1217 | 0.5080 | 8900 | 0.0142 |
|
| 140 |
|
| 141 |
|
| 142 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 697843112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b7cbb7ab78adceef62705533444f2b7319cd63fe277514fd6be07c2a3029295
|
| 3 |
size 697843112
|