Instructions to use filip503/calculator_model_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use filip503/calculator_model_test with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("filip503/calculator_model_test") model = AutoModelForSeq2SeqLM.from_pretrained("filip503/calculator_model_test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 0.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -45,46 +45,46 @@ The following hyperparameters were used during training:
|
|
| 45 |
|
| 46 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
-
| 3.
|
| 49 |
-
| 2.
|
| 50 |
-
| 1.
|
| 51 |
-
| 1.
|
| 52 |
-
| 1.
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
-
|
|
| 70 |
-
|
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
|
|
| 75 |
-
|
|
| 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 |
|
| 89 |
|
| 90 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.1003
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 45 |
|
| 46 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 3.0175 | 1.0 | 6 | 2.2573 |
|
| 49 |
+
| 2.0272 | 2.0 | 12 | 1.7403 |
|
| 50 |
+
| 1.5671 | 3.0 | 18 | 1.3060 |
|
| 51 |
+
| 1.2173 | 4.0 | 24 | 1.1009 |
|
| 52 |
+
| 1.0625 | 5.0 | 30 | 0.9983 |
|
| 53 |
+
| 0.9170 | 6.0 | 36 | 0.8397 |
|
| 54 |
+
| 0.7955 | 7.0 | 42 | 0.7340 |
|
| 55 |
+
| 0.7371 | 8.0 | 48 | 0.6631 |
|
| 56 |
+
| 0.6518 | 9.0 | 54 | 0.6219 |
|
| 57 |
+
| 0.6083 | 10.0 | 60 | 0.5827 |
|
| 58 |
+
| 0.5642 | 11.0 | 66 | 0.5429 |
|
| 59 |
+
| 0.5501 | 12.0 | 72 | 0.5558 |
|
| 60 |
+
| 0.5364 | 13.0 | 78 | 0.4899 |
|
| 61 |
+
| 0.4912 | 14.0 | 84 | 0.4801 |
|
| 62 |
+
| 0.4754 | 15.0 | 90 | 0.4480 |
|
| 63 |
+
| 0.4503 | 16.0 | 96 | 0.4217 |
|
| 64 |
+
| 0.4251 | 17.0 | 102 | 0.4097 |
|
| 65 |
+
| 0.4247 | 18.0 | 108 | 0.3976 |
|
| 66 |
+
| 0.3967 | 19.0 | 114 | 0.3619 |
|
| 67 |
+
| 0.3719 | 20.0 | 120 | 0.3548 |
|
| 68 |
+
| 0.3544 | 21.0 | 126 | 0.3338 |
|
| 69 |
+
| 0.3415 | 22.0 | 132 | 0.3567 |
|
| 70 |
+
| 0.3538 | 23.0 | 138 | 0.2841 |
|
| 71 |
+
| 0.3021 | 24.0 | 144 | 0.2793 |
|
| 72 |
+
| 0.2794 | 25.0 | 150 | 0.2528 |
|
| 73 |
+
| 0.2619 | 26.0 | 156 | 0.2398 |
|
| 74 |
+
| 0.2540 | 27.0 | 162 | 0.2195 |
|
| 75 |
+
| 0.2251 | 28.0 | 168 | 0.2062 |
|
| 76 |
+
| 0.2169 | 29.0 | 174 | 0.1901 |
|
| 77 |
+
| 0.2054 | 30.0 | 180 | 0.1702 |
|
| 78 |
+
| 0.1903 | 31.0 | 186 | 0.1608 |
|
| 79 |
+
| 0.1745 | 32.0 | 192 | 0.1485 |
|
| 80 |
+
| 0.1652 | 33.0 | 198 | 0.1359 |
|
| 81 |
+
| 0.1547 | 34.0 | 204 | 0.1293 |
|
| 82 |
+
| 0.1459 | 35.0 | 210 | 0.1196 |
|
| 83 |
+
| 0.1415 | 36.0 | 216 | 0.1139 |
|
| 84 |
+
| 0.1350 | 37.0 | 222 | 0.1079 |
|
| 85 |
+
| 0.1366 | 38.0 | 228 | 0.1026 |
|
| 86 |
+
| 0.1252 | 39.0 | 234 | 0.1012 |
|
| 87 |
+
| 0.1217 | 40.0 | 240 | 0.1003 |
|
| 88 |
|
| 89 |
|
| 90 |
### Framework versions
|