Instructions to use agarc15/mega-base-wikitext-finetuned-INCIBE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use agarc15/mega-base-wikitext-finetuned-INCIBE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="agarc15/mega-base-wikitext-finetuned-INCIBE")# Load model directly from transformers import AutoModelForSequenceClassification model = AutoModelForSequenceClassification.from_pretrained("agarc15/mega-base-wikitext-finetuned-INCIBE", device_map="auto") - Notebooks
- Google Colab
- Kaggle
End of training
Browse files- README.md +27 -27
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [mnaylor/mega-base-wikitext](https://huggingface.co/mnaylor/mega-base-wikitext) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -49,31 +49,31 @@ The following hyperparameters were used during training:
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
-
| No log | 1.0 | 196 | 1.
|
| 53 |
-
| No log | 2.0 | 392 | 1.
|
| 54 |
-
| 1.
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.
|
| 60 |
-
| 1.
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
| 65 |
-
| 1.
|
| 66 |
-
| 1.
|
| 67 |
-
| 1.
|
| 68 |
-
| 1.
|
| 69 |
-
| 1.
|
| 70 |
-
| 1.
|
| 71 |
-
| 1.
|
| 72 |
-
| 1.
|
| 73 |
-
| 1.
|
| 74 |
-
| 1.
|
| 75 |
-
| 1.
|
| 76 |
-
| 1.
|
| 77 |
|
| 78 |
|
| 79 |
### Framework versions
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [mnaylor/mega-base-wikitext](https://huggingface.co/mnaylor/mega-base-wikitext) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.5169
|
| 21 |
+
- Accuracy: 0.3850
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| No log | 1.0 | 196 | 1.5359 | 0.3742 |
|
| 53 |
+
| No log | 2.0 | 392 | 1.5257 | 0.3753 |
|
| 54 |
+
| 1.5035 | 3.0 | 588 | 1.5320 | 0.3719 |
|
| 55 |
+
| 1.5035 | 4.0 | 784 | 1.5231 | 0.3715 |
|
| 56 |
+
| 1.5035 | 5.0 | 980 | 1.5203 | 0.3745 |
|
| 57 |
+
| 1.4755 | 6.0 | 1176 | 1.5217 | 0.3742 |
|
| 58 |
+
| 1.4755 | 7.0 | 1372 | 1.5301 | 0.3719 |
|
| 59 |
+
| 1.4531 | 8.0 | 1568 | 1.5131 | 0.3805 |
|
| 60 |
+
| 1.4531 | 9.0 | 1764 | 1.5212 | 0.3783 |
|
| 61 |
+
| 1.4531 | 10.0 | 1960 | 1.5173 | 0.3771 |
|
| 62 |
+
| 1.4426 | 11.0 | 2156 | 1.5190 | 0.3809 |
|
| 63 |
+
| 1.4426 | 12.0 | 2352 | 1.5122 | 0.3794 |
|
| 64 |
+
| 1.4238 | 13.0 | 2548 | 1.5129 | 0.3794 |
|
| 65 |
+
| 1.4238 | 14.0 | 2744 | 1.5176 | 0.3783 |
|
| 66 |
+
| 1.4238 | 15.0 | 2940 | 1.5139 | 0.3783 |
|
| 67 |
+
| 1.4161 | 16.0 | 3136 | 1.5235 | 0.3805 |
|
| 68 |
+
| 1.4161 | 17.0 | 3332 | 1.5125 | 0.3846 |
|
| 69 |
+
| 1.4115 | 18.0 | 3528 | 1.5171 | 0.3827 |
|
| 70 |
+
| 1.4115 | 19.0 | 3724 | 1.5112 | 0.3827 |
|
| 71 |
+
| 1.4115 | 20.0 | 3920 | 1.5123 | 0.3816 |
|
| 72 |
+
| 1.4052 | 21.0 | 4116 | 1.5126 | 0.3827 |
|
| 73 |
+
| 1.4052 | 22.0 | 4312 | 1.5170 | 0.3850 |
|
| 74 |
+
| 1.4004 | 23.0 | 4508 | 1.5135 | 0.3805 |
|
| 75 |
+
| 1.4004 | 24.0 | 4704 | 1.5157 | 0.3809 |
|
| 76 |
+
| 1.4004 | 25.0 | 4900 | 1.5160 | 0.3824 |
|
| 77 |
|
| 78 |
|
| 79 |
### Framework versions
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 29405448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1516c061194ce44e94c36f4b63fe0d1cf2f948e11e85c27fb72d15b764a153f0
|
| 3 |
size 29405448
|