End of training
Browse files- README.md +94 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- ag_news
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: N_distilbert_agnews_padding60model
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: ag_news
|
18 |
+
type: ag_news
|
19 |
+
config: default
|
20 |
+
split: test
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.945
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# N_distilbert_agnews_padding60model
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ag_news dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.6714
|
36 |
+
- Accuracy: 0.945
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 2e-05
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 16
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 20
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
67 |
+
| 0.1829 | 1.0 | 7500 | 0.1828 | 0.9445 |
|
68 |
+
| 0.1406 | 2.0 | 15000 | 0.1995 | 0.9436 |
|
69 |
+
| 0.1229 | 3.0 | 22500 | 0.2025 | 0.9470 |
|
70 |
+
| 0.0893 | 4.0 | 30000 | 0.2578 | 0.9464 |
|
71 |
+
| 0.0547 | 5.0 | 37500 | 0.3250 | 0.9392 |
|
72 |
+
| 0.0394 | 6.0 | 45000 | 0.3882 | 0.9391 |
|
73 |
+
| 0.0368 | 7.0 | 52500 | 0.4054 | 0.9383 |
|
74 |
+
| 0.0221 | 8.0 | 60000 | 0.4602 | 0.9396 |
|
75 |
+
| 0.0179 | 9.0 | 67500 | 0.4535 | 0.9430 |
|
76 |
+
| 0.015 | 10.0 | 75000 | 0.4745 | 0.9421 |
|
77 |
+
| 0.0177 | 11.0 | 82500 | 0.5035 | 0.9439 |
|
78 |
+
| 0.0147 | 12.0 | 90000 | 0.4848 | 0.9436 |
|
79 |
+
| 0.0077 | 13.0 | 97500 | 0.5222 | 0.9447 |
|
80 |
+
| 0.0039 | 14.0 | 105000 | 0.5591 | 0.9432 |
|
81 |
+
| 0.0042 | 15.0 | 112500 | 0.5863 | 0.9433 |
|
82 |
+
| 0.0017 | 16.0 | 120000 | 0.6075 | 0.9457 |
|
83 |
+
| 0.003 | 17.0 | 127500 | 0.6207 | 0.9455 |
|
84 |
+
| 0.0017 | 18.0 | 135000 | 0.6482 | 0.9454 |
|
85 |
+
| 0.0004 | 19.0 | 142500 | 0.6646 | 0.9457 |
|
86 |
+
| 0.0017 | 20.0 | 150000 | 0.6714 | 0.945 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.33.2
|
92 |
+
- Pytorch 2.0.1+cu117
|
93 |
+
- Datasets 2.14.5
|
94 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268045997
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eab2e3f4033a8d4febd098589bcf37842aa0e53c920138807ef41fcb5322ec0e
|
3 |
size 268045997
|