Commit
·
9c22793
1
Parent(s):
72d836e
Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,9 @@ tags:
|
|
| 5 |
model-index:
|
| 6 |
- name: xtremedistil-l6-h256-uncased-future-time-references-D2
|
| 7 |
results: []
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
|
@@ -12,9 +15,13 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# xtremedistil-l6-h256-uncased-future-time-references-D2
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -38,7 +45,15 @@ The following hyperparameters were used during training:
|
|
| 38 |
|
| 39 |
### Training results
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
|
|
|
| 42 |
|
| 43 |
### Framework versions
|
| 44 |
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: xtremedistil-l6-h256-uncased-future-time-references-D2
|
| 7 |
results: []
|
| 8 |
+
datasets:
|
| 9 |
+
- jonaskoenig/trump_administration_statement
|
| 10 |
+
- jonaskoenig/future-time-refernces-static-filter-D2
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
|
|
|
| 15 |
|
| 16 |
# xtremedistil-l6-h256-uncased-future-time-references-D2
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [microsoft/xtremedistil-l6-h256-uncased](https://huggingface.co/microsoft/xtremedistil-l6-h256-uncased) on [jonaskoenig/future-time-refernces-static-filter-D2](https://huggingface.co/datasets/jonaskoenig/future-time-refernces-static-filter-D2) and [jonaskoenig/trump_administration_statement](https://huggingface.co/datasets/jonaskoenig/trump_administration_statement).
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Train Loss: 0.0055
|
| 21 |
+
- Train Sparse Categorical Accuracy: 0.9984
|
| 22 |
+
- Validation Loss: 0.0074
|
| 23 |
+
- Validation Sparse Categorical Accuracy: 0.9984
|
| 24 |
+
- Epoch: 4
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
+
| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
|
| 49 |
+
|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
|
| 50 |
+
| 0.0388 | 0.9891 | 0.0154 | 0.9957 | 0 |
|
| 51 |
+
| 0.0133 | 0.9962 | 0.0088 | 0.9975 | 1 |
|
| 52 |
+
| 0.0087 | 0.9974 | 0.0081 | 0.9978 | 2 |
|
| 53 |
+
| 0.0068 | 0.9980 | 0.0074 | 0.9982 | 3 |
|
| 54 |
+
| 0.0055 | 0.9984 | 0.0074 | 0.9984 | 4 |
|
| 55 |
|
| 56 |
+
The test accuracy is: 99.81%
|
| 57 |
|
| 58 |
### Framework versions
|
| 59 |
|