update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: albert-base-ours-run-4
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# albert-base-ours-run-4
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.9565
|
23 |
+
- Accuracy: 0.72
|
24 |
+
- Precision: 0.6790
|
25 |
+
- Recall: 0.6770
|
26 |
+
- F1: 0.6766
|
27 |
+
|
28 |
+
## Model description
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Intended uses & limitations
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training and evaluation data
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Training procedure
|
41 |
+
|
42 |
+
### Training hyperparameters
|
43 |
+
|
44 |
+
The following hyperparameters were used during training:
|
45 |
+
- learning_rate: 1e-05
|
46 |
+
- train_batch_size: 8
|
47 |
+
- eval_batch_size: 8
|
48 |
+
- seed: 42
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 20
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
57 |
+
| 1.0253 | 1.0 | 200 | 0.8974 | 0.605 | 0.7186 | 0.5341 | 0.4555 |
|
58 |
+
| 0.8121 | 2.0 | 400 | 0.8260 | 0.675 | 0.6792 | 0.6308 | 0.6112 |
|
59 |
+
| 0.6153 | 3.0 | 600 | 0.8504 | 0.66 | 0.6180 | 0.6026 | 0.6073 |
|
60 |
+
| 0.441 | 4.0 | 800 | 0.8917 | 0.685 | 0.6463 | 0.6385 | 0.6403 |
|
61 |
+
| 0.3273 | 5.0 | 1000 | 0.9384 | 0.69 | 0.6534 | 0.6602 | 0.6561 |
|
62 |
+
| 0.2138 | 6.0 | 1200 | 1.3501 | 0.705 | 0.6573 | 0.6374 | 0.6388 |
|
63 |
+
| 0.1435 | 7.0 | 1400 | 1.4614 | 0.71 | 0.6693 | 0.6553 | 0.6601 |
|
64 |
+
| 0.1202 | 8.0 | 1600 | 1.5825 | 0.7 | 0.6648 | 0.6592 | 0.6530 |
|
65 |
+
| 0.0587 | 9.0 | 1800 | 1.7755 | 0.72 | 0.6839 | 0.6849 | 0.6840 |
|
66 |
+
| 0.0237 | 10.0 | 2000 | 1.7240 | 0.735 | 0.6960 | 0.6924 | 0.6940 |
|
67 |
+
| 0.018 | 11.0 | 2200 | 1.7230 | 0.745 | 0.7105 | 0.7003 | 0.7026 |
|
68 |
+
| 0.0096 | 12.0 | 2400 | 1.7812 | 0.75 | 0.7225 | 0.7142 | 0.7158 |
|
69 |
+
| 0.006 | 13.0 | 2600 | 1.8223 | 0.75 | 0.7265 | 0.7082 | 0.7147 |
|
70 |
+
| 0.0033 | 14.0 | 2800 | 1.9872 | 0.76 | 0.7434 | 0.7107 | 0.7188 |
|
71 |
+
| 0.003 | 15.0 | 3000 | 1.8818 | 0.72 | 0.6778 | 0.6766 | 0.6765 |
|
72 |
+
| 0.0027 | 16.0 | 3200 | 1.9816 | 0.75 | 0.7125 | 0.6990 | 0.7043 |
|
73 |
+
| 0.002 | 17.0 | 3400 | 1.9268 | 0.725 | 0.6832 | 0.6834 | 0.6825 |
|
74 |
+
| 0.0023 | 18.0 | 3600 | 1.9456 | 0.73 | 0.6913 | 0.6898 | 0.6898 |
|
75 |
+
| 0.0025 | 19.0 | 3800 | 1.9543 | 0.72 | 0.6790 | 0.6770 | 0.6766 |
|
76 |
+
| 0.0016 | 20.0 | 4000 | 1.9565 | 0.72 | 0.6790 | 0.6770 | 0.6766 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.25.1
|
82 |
+
- Pytorch 1.13.0+cu116
|
83 |
+
- Tokenizers 0.13.2
|