Update README.md
Browse files
README.md
CHANGED
@@ -18,8 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# cl_ct_custom_model
|
20 |
|
21 |
-
This model is a fine-tuned version of [bioformers/bioformer-16L](https://huggingface.co/bioformers/bioformer-16L) on
|
22 |
It achieves the following results on the evaluation set:
|
|
|
23 |
- Loss: 0.2590
|
24 |
- F1: 0.7609
|
25 |
- Precision: 0.7112
|
@@ -69,6 +70,33 @@ The following hyperparameters were used during training:
|
|
69 |
| 0.1241 | 8.9971 | 2337 | 0.1892 | 0.8559 | 0.8401 | 0.8724 | 0.9432 |
|
70 |
| 0.1199 | 9.9711 | 2590 | 0.1899 | 0.8552 | 0.8392 | 0.8718 | 0.9431 |
|
71 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
### Framework versions
|
74 |
|
|
|
18 |
|
19 |
# cl_ct_custom_model
|
20 |
|
21 |
+
This model is a fine-tuned version of [bioformers/bioformer-16L](https://huggingface.co/bioformers/bioformer-16L) on the (https://huggingface.co/datasets/tner/bionlp2004) dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
|
24 |
- Loss: 0.2590
|
25 |
- F1: 0.7609
|
26 |
- Precision: 0.7112
|
|
|
70 |
| 0.1241 | 8.9971 | 2337 | 0.1892 | 0.8559 | 0.8401 | 0.8724 | 0.9432 |
|
71 |
| 0.1199 | 9.9711 | 2590 | 0.1899 | 0.8552 | 0.8392 | 0.8718 | 0.9431 |
|
72 |
|
73 |
+
## Eval Classification report
|
74 |
+
|
75 |
+
| Class | Precision | Recall | F1-Score | Support |
|
76 |
+
|-------------|------------|--------|----------|---------|
|
77 |
+
| DNA | 0.78 | 0.84 | 0.81 | 2494 |
|
78 |
+
| RNA | 0.83 | 0.89 | 0.86 | 238 |
|
79 |
+
| Cell Line | 0.81 | 0.85 | 0.83 | 1050 |
|
80 |
+
| Cell Type | 0.74 | 0.79 | 0.77 | 775 |
|
81 |
+
| Protein | 0.88 | 0.90 | 0.89 | 6196 |
|
82 |
+
| **Micro Avg** | **0.84** | **0.87** | **0.86** | **10753** |
|
83 |
+
| **Macro Avg** | **0.81** | **0.86** | **0.83** | **10753** |
|
84 |
+
| **Weighted Avg** | **0.84** | **0.87** | **0.86** | **10753** |
|
85 |
+
|
86 |
+
|
87 |
+
## Test Results
|
88 |
+
|
89 |
+
| Class | Precision | Recall | F1-Score | Support |
|
90 |
+
|-------------|-----------|--------|----------|---------|
|
91 |
+
| DNA | 0.74 | 0.79 | 0.76 | 2210 |
|
92 |
+
| RNA | 0.73 | 0.76 | 0.75 | 287 |
|
93 |
+
| Cell Line | 0.50 | 0.76 | 0.61 | 1057 |
|
94 |
+
| Cell Type | 0.75 | 0.68 | 0.71 | 2761 |
|
95 |
+
| Protein | 0.72 | 0.87 | 0.79 | 10082 |
|
96 |
+
| **Micro Avg** | **0.71** | **0.82** | **0.76** | **16397** |
|
97 |
+
| **Macro Avg** | **0.69** | **0.77** | **0.72** | **16397** |
|
98 |
+
| **Weighted Avg** | **0.72** | **0.82** | **0.76** | **16397** |
|
99 |
+
|
100 |
|
101 |
### Framework versions
|
102 |
|