Instructions to use ms8080/calculator_model_test_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ms8080/calculator_model_test_2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ms8080/calculator_model_test_2") model = AutoModelForSeq2SeqLM.from_pretrained("ms8080/calculator_model_test_2") - 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 |
|
|
@@ -46,46 +46,46 @@ The following hyperparameters were used during training:
|
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
-
| 3.
|
| 50 |
-
| 2.
|
| 51 |
-
| 1.
|
| 52 |
-
| 1.
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 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 |
|
| 90 |
|
| 91 |
### 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: 0.4881
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 3.2172 | 1.0 | 14 | 2.4439 |
|
| 50 |
+
| 2.2511 | 2.0 | 28 | 2.0993 |
|
| 51 |
+
| 1.8900 | 3.0 | 42 | 1.6658 |
|
| 52 |
+
| 1.5938 | 4.0 | 56 | 1.5309 |
|
| 53 |
+
| 1.5062 | 5.0 | 70 | 1.4552 |
|
| 54 |
+
| 1.4073 | 6.0 | 84 | 1.3081 |
|
| 55 |
+
| 1.2474 | 7.0 | 98 | 1.1300 |
|
| 56 |
+
| 1.0879 | 8.0 | 112 | 1.0155 |
|
| 57 |
+
| 1.0071 | 9.0 | 126 | 0.9430 |
|
| 58 |
+
| 0.9353 | 10.0 | 140 | 0.8832 |
|
| 59 |
+
| 0.8847 | 11.0 | 154 | 0.8358 |
|
| 60 |
+
| 0.8417 | 12.0 | 168 | 0.7919 |
|
| 61 |
+
| 0.8073 | 13.0 | 182 | 0.7743 |
|
| 62 |
+
| 0.8013 | 14.0 | 196 | 0.8096 |
|
| 63 |
+
| 0.7776 | 15.0 | 210 | 0.7482 |
|
| 64 |
+
| 0.7476 | 16.0 | 224 | 0.7241 |
|
| 65 |
+
| 0.7231 | 17.0 | 238 | 0.7127 |
|
| 66 |
+
| 0.7045 | 18.0 | 252 | 0.6679 |
|
| 67 |
+
| 0.6851 | 19.0 | 266 | 0.6536 |
|
| 68 |
+
| 0.6707 | 20.0 | 280 | 0.6485 |
|
| 69 |
+
| 0.6507 | 21.0 | 294 | 0.6197 |
|
| 70 |
+
| 0.6447 | 22.0 | 308 | 0.6277 |
|
| 71 |
+
| 0.6359 | 23.0 | 322 | 0.6155 |
|
| 72 |
+
| 0.6184 | 24.0 | 336 | 0.6017 |
|
| 73 |
+
| 0.6143 | 25.0 | 350 | 0.5939 |
|
| 74 |
+
| 0.5941 | 26.0 | 364 | 0.5718 |
|
| 75 |
+
| 0.5859 | 27.0 | 378 | 0.5659 |
|
| 76 |
+
| 0.5741 | 28.0 | 392 | 0.5695 |
|
| 77 |
+
| 0.5714 | 29.0 | 406 | 0.5546 |
|
| 78 |
+
| 0.5585 | 30.0 | 420 | 0.5382 |
|
| 79 |
+
| 0.5445 | 31.0 | 434 | 0.5273 |
|
| 80 |
+
| 0.5361 | 32.0 | 448 | 0.5203 |
|
| 81 |
+
| 0.5292 | 33.0 | 462 | 0.5166 |
|
| 82 |
+
| 0.5218 | 34.0 | 476 | 0.5145 |
|
| 83 |
+
| 0.5153 | 35.0 | 490 | 0.5066 |
|
| 84 |
+
| 0.5098 | 36.0 | 504 | 0.4994 |
|
| 85 |
+
| 0.5039 | 37.0 | 518 | 0.4933 |
|
| 86 |
+
| 0.5011 | 38.0 | 532 | 0.4913 |
|
| 87 |
+
| 0.4962 | 39.0 | 546 | 0.4892 |
|
| 88 |
+
| 0.4929 | 40.0 | 560 | 0.4881 |
|
| 89 |
|
| 90 |
|
| 91 |
### Framework versions
|