End of training
Browse files
README.md
ADDED
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- ag_news
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: roberta_agnews_padding10model
|
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: 0.9502631578947368
|
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 |
+
# roberta_agnews_padding10model
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the ag_news dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.5337
|
36 |
+
- Accuracy: 0.9503
|
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 |
+
| 0.1966 | 1.0 | 7500 | 0.2068 | 0.9404 |
|
68 |
+
| 0.1632 | 2.0 | 15000 | 0.1954 | 0.9457 |
|
69 |
+
| 0.1432 | 3.0 | 22500 | 0.2422 | 0.9478 |
|
70 |
+
| 0.1223 | 4.0 | 30000 | 0.2275 | 0.9486 |
|
71 |
+
| 0.0994 | 5.0 | 37500 | 0.2442 | 0.9486 |
|
72 |
+
| 0.079 | 6.0 | 45000 | 0.3053 | 0.9486 |
|
73 |
+
| 0.0759 | 7.0 | 52500 | 0.3104 | 0.9463 |
|
74 |
+
| 0.0506 | 8.0 | 60000 | 0.3757 | 0.9472 |
|
75 |
+
| 0.0436 | 9.0 | 67500 | 0.3468 | 0.9470 |
|
76 |
+
| 0.025 | 10.0 | 75000 | 0.4170 | 0.9468 |
|
77 |
+
| 0.0303 | 11.0 | 82500 | 0.4168 | 0.9462 |
|
78 |
+
| 0.0273 | 12.0 | 90000 | 0.4173 | 0.9486 |
|
79 |
+
| 0.024 | 13.0 | 97500 | 0.4305 | 0.9476 |
|
80 |
+
| 0.0139 | 14.0 | 105000 | 0.4549 | 0.9480 |
|
81 |
+
| 0.0111 | 15.0 | 112500 | 0.4961 | 0.9483 |
|
82 |
+
| 0.0102 | 16.0 | 120000 | 0.4733 | 0.9488 |
|
83 |
+
| 0.0036 | 17.0 | 127500 | 0.5044 | 0.9493 |
|
84 |
+
| 0.0025 | 18.0 | 135000 | 0.5070 | 0.95 |
|
85 |
+
| 0.0024 | 19.0 | 142500 | 0.5196 | 0.9508 |
|
86 |
+
| 0.0018 | 20.0 | 150000 | 0.5337 | 0.9503 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.32.1
|
92 |
+
- Pytorch 2.1.1
|
93 |
+
- Datasets 2.12.0
|
94 |
+
- Tokenizers 0.13.3
|