Update README.md
Browse files
README.md
CHANGED
@@ -37,7 +37,7 @@ It achieves the following results on the evaluation set:
|
|
37 |
|
38 |
## Model description
|
39 |
|
40 |
-
For more information on how it was created, check out the following link:
|
41 |
|
42 |
## Intended uses & limitations
|
43 |
|
@@ -47,6 +47,14 @@ This model is intended to demonstrate my ability to solve a complex problem usin
|
|
47 |
|
48 |
Dataset Source: https://huggingface.co/datasets/paolo-ruggirello/biomedical-dataset
|
49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
## Training procedure
|
51 |
|
52 |
### Training hyperparameters
|
@@ -60,16 +68,15 @@ The following hyperparameters were used during training:
|
|
60 |
- lr_scheduler_type: linear
|
61 |
- num_epochs: 1
|
62 |
|
63 |
-
### Training results
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | RougeL | RougeLsum | Meteor | Prediction Lengths |
|
66 |
| :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: |
|
67 |
| 1.0165 | 1.0 | 2636 | 0.9425 | 38.9893 | 0.6826 | 0.4737 | 0.6586 | 0.6585 | 0.6270 | 24.3627 |
|
68 |
|
69 |
-
<br />
|
70 |
Footnotes:
|
71 |
|
72 |
-
|
73 |
|
74 |
### Framework versions
|
75 |
|
|
|
37 |
|
38 |
## Model description
|
39 |
|
40 |
+
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Machine%20Translation/Biomedical%20Translation%20(EN%20to%20IT)/Biomedical%20-%20Translation%20Project.ipynb
|
41 |
|
42 |
## Intended uses & limitations
|
43 |
|
|
|
47 |
|
48 |
Dataset Source: https://huggingface.co/datasets/paolo-ruggirello/biomedical-dataset
|
49 |
|
50 |
+
### Histogram of English Input Word Counts
|
51 |
+
|
52 |
+
![English Input Lengths](https://raw.githubusercontent.com/DunnBC22/NLP_Projects/main/Machine%20Translation/Biomedical%20Translation%20(EN%20to%20IT)/Images/Histogram%20of%20English%20Lengths.png)
|
53 |
+
|
54 |
+
### Histogram of Italian Input Word Counts
|
55 |
+
|
56 |
+
![Italian Input Lengths](https://raw.githubusercontent.com/DunnBC22/NLP_Projects/main/Machine%20Translation/Biomedical%20Translation%20(EN%20to%20IT)/Images/Histogram%20of%20Italian%20Inputs.png)
|
57 |
+
|
58 |
## Training procedure
|
59 |
|
60 |
### Training hyperparameters
|
|
|
68 |
- lr_scheduler_type: linear
|
69 |
- num_epochs: 1
|
70 |
|
71 |
+
### Training results*
|
72 |
|
73 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | RougeL | RougeLsum | Meteor | Prediction Lengths |
|
74 |
| :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: | :-------------: |
|
75 |
| 1.0165 | 1.0 | 2636 | 0.9425 | 38.9893 | 0.6826 | 0.4737 | 0.6586 | 0.6585 | 0.6270 | 24.3627 |
|
76 |
|
|
|
77 |
Footnotes:
|
78 |
|
79 |
+
*: All results in this table are rounded to the nearest ten-thousandths of the decimal.
|
80 |
|
81 |
### Framework versions
|
82 |
|