update model card README.md
Browse files
README.md
CHANGED
@@ -2,9 +2,6 @@
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
metrics:
|
6 |
-
- f1
|
7 |
-
- bleu
|
8 |
model-index:
|
9 |
- name: medlid-define
|
10 |
results: []
|
@@ -15,17 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# medlid-define
|
17 |
|
18 |
-
This model is a fine-tuned version of [GanjinZero/biobart-v2-
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- F1: 0.0024
|
22 |
-
- R1: 0.5714
|
23 |
-
- R2: 0.0
|
24 |
-
- Rl: 0.5714
|
25 |
-
- Bleu: 0.0588
|
26 |
-
- Bertscore precision:: 0.9153
|
27 |
-
- Bertscore recall: 0.9115
|
28 |
-
- Bertscore f1: 0.9134
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -45,20 +34,20 @@ More information needed
|
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
- learning_rate: 2e-05
|
48 |
-
- train_batch_size:
|
49 |
-
- eval_batch_size:
|
50 |
-
- seed:
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
- num_epochs: 3
|
54 |
|
55 |
### Training results
|
56 |
|
57 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
58 |
-
|
59 |
-
| No log | 1.0 |
|
60 |
-
| No log | 2.0 |
|
61 |
-
| No log | 3.0 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
|
|
5 |
model-index:
|
6 |
- name: medlid-define
|
7 |
results: []
|
|
|
12 |
|
13 |
# medlid-define
|
14 |
|
15 |
+
This model is a fine-tuned version of [GanjinZero/biobart-v2-large](https://huggingface.co/GanjinZero/biobart-v2-large) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.6287
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 2e-05
|
37 |
+
- train_batch_size: 32
|
38 |
+
- eval_batch_size: 32
|
39 |
+
- seed: 27
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
- num_epochs: 3
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
+
| No log | 1.0 | 27 | 0.6819 |
|
49 |
+
| No log | 2.0 | 54 | 0.6384 |
|
50 |
+
| No log | 3.0 | 81 | 0.6287 |
|
51 |
|
52 |
|
53 |
### Framework versions
|