Commit
•
6057056
1
Parent(s):
09729de
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- f1
|
7 |
+
model-index:
|
8 |
+
- name: fine-tuned-DatasetQAS-IDK-MRC-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# fine-tuned-DatasetQAS-IDK-MRC-with-indobert-base-uncased-with-ITTL-without-freeze-LR-1e-05
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.0515
|
20 |
+
- Exact Match: 65.9686
|
21 |
+
- F1: 71.4684
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 1e-05
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 16
|
45 |
+
- total_train_batch_size: 128
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 10
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----------:|:-------:|
|
54 |
+
| 6.1822 | 0.49 | 36 | 2.5004 | 49.8691 | 49.8691 |
|
55 |
+
| 3.6893 | 0.98 | 72 | 1.9896 | 49.8691 | 49.8691 |
|
56 |
+
| 2.2116 | 1.48 | 108 | 1.8516 | 49.2147 | 49.7070 |
|
57 |
+
| 2.2116 | 1.97 | 144 | 1.7367 | 50.1309 | 52.0399 |
|
58 |
+
| 1.9945 | 2.46 | 180 | 1.5956 | 51.7016 | 56.3444 |
|
59 |
+
| 1.7443 | 2.95 | 216 | 1.4508 | 54.9738 | 59.4030 |
|
60 |
+
| 1.5782 | 3.45 | 252 | 1.3234 | 59.9476 | 65.0857 |
|
61 |
+
| 1.5782 | 3.94 | 288 | 1.2652 | 58.1152 | 63.9949 |
|
62 |
+
| 1.4004 | 4.44 | 324 | 1.1784 | 62.0419 | 67.5268 |
|
63 |
+
| 1.241 | 4.93 | 360 | 1.1573 | 60.4712 | 66.5284 |
|
64 |
+
| 1.241 | 5.42 | 396 | 1.1217 | 62.4346 | 67.8923 |
|
65 |
+
| 1.1603 | 5.91 | 432 | 1.0997 | 63.3508 | 68.7351 |
|
66 |
+
| 1.0849 | 6.41 | 468 | 1.0832 | 64.3979 | 69.5781 |
|
67 |
+
| 1.0209 | 6.9 | 504 | 1.0773 | 64.0052 | 69.3072 |
|
68 |
+
| 1.0209 | 7.4 | 540 | 1.0500 | 65.0524 | 70.4355 |
|
69 |
+
| 0.9802 | 7.89 | 576 | 1.0644 | 65.3141 | 70.7507 |
|
70 |
+
| 0.9536 | 8.38 | 612 | 1.0516 | 65.5759 | 70.9704 |
|
71 |
+
| 0.9536 | 8.87 | 648 | 1.0395 | 65.4450 | 71.2117 |
|
72 |
+
| 0.9319 | 9.37 | 684 | 1.0411 | 65.8377 | 71.3692 |
|
73 |
+
| 0.9091 | 9.86 | 720 | 1.0515 | 65.9686 | 71.4684 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.26.1
|
79 |
+
- Pytorch 1.13.1+cu117
|
80 |
+
- Datasets 2.2.0
|
81 |
+
- Tokenizers 0.13.2
|