Model save
Browse files- README.md +35 -30
- model.safetensors +1 -1
README.md
CHANGED
@@ -2,24 +2,11 @@
|
|
2 |
base_model: demdecuong/vihealthbert-base-word
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
datasets:
|
6 |
-
- tmnam20/pretrained-vn-med-nli
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
model-index:
|
10 |
- name: vihealthbert-w_unsup-SynPD
|
11 |
-
results:
|
12 |
-
- task:
|
13 |
-
name: Masked Language Modeling
|
14 |
-
type: fill-mask
|
15 |
-
dataset:
|
16 |
-
name: tmnam20/pretrained-vn-med-nli all
|
17 |
-
type: tmnam20/pretrained-vn-med-nli
|
18 |
-
args: all
|
19 |
-
metrics:
|
20 |
-
- name: Accuracy
|
21 |
-
type: accuracy
|
22 |
-
value: 0.686153705209395
|
23 |
---
|
24 |
|
25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -27,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
27 |
|
28 |
# vihealthbert-w_unsup-SynPD
|
29 |
|
30 |
-
This model is a fine-tuned version of [demdecuong/vihealthbert-base-word](https://huggingface.co/demdecuong/vihealthbert-base-word) on
|
31 |
It achieves the following results on the evaluation set:
|
32 |
-
- Loss: 1.
|
33 |
-
- Accuracy: 0.
|
34 |
|
35 |
## Model description
|
36 |
|
@@ -52,7 +39,7 @@ The following hyperparameters were used during training:
|
|
52 |
- learning_rate: 3e-05
|
53 |
- train_batch_size: 32
|
54 |
- eval_batch_size: 16
|
55 |
-
- seed:
|
56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
- lr_scheduler_type: linear
|
58 |
- lr_scheduler_warmup_ratio: 0.1
|
@@ -62,22 +49,40 @@ The following hyperparameters were used during training:
|
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
64 |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
|
65 |
-
|
|
66 |
-
|
|
67 |
-
|
|
68 |
-
|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
|
77 |
|
78 |
### Framework versions
|
79 |
|
80 |
- Transformers 4.40.2
|
81 |
-
- Pytorch 2.0
|
82 |
- Datasets 2.19.1
|
83 |
- Tokenizers 0.19.1
|
|
|
2 |
base_model: demdecuong/vihealthbert-base-word
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
metrics:
|
6 |
- accuracy
|
7 |
model-index:
|
8 |
- name: vihealthbert-w_unsup-SynPD
|
9 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
14 |
|
15 |
# vihealthbert-w_unsup-SynPD
|
16 |
|
17 |
+
This model is a fine-tuned version of [demdecuong/vihealthbert-base-word](https://huggingface.co/demdecuong/vihealthbert-base-word) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.5576
|
20 |
+
- Accuracy: 0.6883
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
39 |
- learning_rate: 3e-05
|
40 |
- train_batch_size: 32
|
41 |
- eval_batch_size: 16
|
42 |
+
- seed: 19144
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_ratio: 0.1
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:------:|:-----:|:---------------:|:--------:|
|
52 |
+
| 5.8543 | 0.3446 | 2000 | 3.8967 | 0.3950 |
|
53 |
+
| 3.4544 | 0.6893 | 4000 | 2.8119 | 0.5306 |
|
54 |
+
| 2.8312 | 1.0339 | 6000 | 2.4040 | 0.5771 |
|
55 |
+
| 2.5914 | 1.3786 | 8000 | 2.6482 | 0.5350 |
|
56 |
+
| 2.5649 | 1.7232 | 10000 | 2.1335 | 0.6087 |
|
57 |
+
| 2.2749 | 2.0679 | 12000 | 1.9895 | 0.6282 |
|
58 |
+
| 2.1572 | 2.4125 | 14000 | 1.9313 | 0.6353 |
|
59 |
+
| 2.1009 | 2.7572 | 16000 | 1.8646 | 0.6429 |
|
60 |
+
| 2.0609 | 3.1018 | 18000 | 1.8572 | 0.6450 |
|
61 |
+
| 2.0885 | 3.4465 | 20000 | 1.9489 | 0.6285 |
|
62 |
+
| 1.9891 | 3.7911 | 22000 | 1.7700 | 0.6583 |
|
63 |
+
| 1.9368 | 4.1358 | 24000 | 1.7398 | 0.6609 |
|
64 |
+
| 1.9003 | 4.4804 | 26000 | 1.7165 | 0.6664 |
|
65 |
+
| 1.9058 | 4.8251 | 28000 | 1.7032 | 0.6670 |
|
66 |
+
| 1.859 | 5.1697 | 30000 | 1.6771 | 0.6718 |
|
67 |
+
| 1.8401 | 5.5144 | 32000 | 1.6652 | 0.6710 |
|
68 |
+
| 1.8181 | 5.8590 | 34000 | 1.6417 | 0.6754 |
|
69 |
+
| 1.8133 | 6.2037 | 36000 | 1.6431 | 0.6748 |
|
70 |
+
| 1.7888 | 6.5483 | 38000 | 1.6363 | 0.6755 |
|
71 |
+
| 1.7811 | 6.8930 | 40000 | 1.6205 | 0.6793 |
|
72 |
+
| 1.7481 | 7.2376 | 42000 | 1.6190 | 0.6807 |
|
73 |
+
| 1.7509 | 7.5823 | 44000 | 1.6142 | 0.6794 |
|
74 |
+
| 1.7517 | 7.9269 | 46000 | 1.5949 | 0.6819 |
|
75 |
+
| 1.7358 | 8.2716 | 48000 | 1.5909 | 0.6843 |
|
76 |
+
| 1.7287 | 8.6162 | 50000 | 1.5757 | 0.6851 |
|
77 |
+
| 1.7132 | 8.9609 | 52000 | 1.5671 | 0.6885 |
|
78 |
+
| 1.7042 | 9.3055 | 54000 | 1.5685 | 0.6867 |
|
79 |
+
| 1.7051 | 9.6502 | 56000 | 1.5609 | 0.6876 |
|
80 |
+
| 1.7051 | 9.9948 | 58000 | 1.5576 | 0.6883 |
|
81 |
|
82 |
|
83 |
### Framework versions
|
84 |
|
85 |
- Transformers 4.40.2
|
86 |
+
- Pytorch 2.2.0+cu121
|
87 |
- Datasets 2.19.1
|
88 |
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 540279452
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1b789c4c8bb7da3be52210541d04d9e938c01f03c9f44e4ac8beaabb3bdf40f
|
3 |
size 540279452
|