End of training
Browse files
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: roberta-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: roberta_sst2_padding0model
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# roberta_sst2_padding0model
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4539
|
21 |
+
- Accuracy: 0.9484
|
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: 2e-05
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 16
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 20
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 1.0 | 433 | 0.1891 | 0.9407 |
|
53 |
+
| 0.3324 | 2.0 | 866 | 0.3948 | 0.9176 |
|
54 |
+
| 0.1922 | 3.0 | 1299 | 0.2418 | 0.9379 |
|
55 |
+
| 0.126 | 4.0 | 1732 | 0.3080 | 0.9407 |
|
56 |
+
| 0.069 | 5.0 | 2165 | 0.4075 | 0.9396 |
|
57 |
+
| 0.0358 | 6.0 | 2598 | 0.3955 | 0.9418 |
|
58 |
+
| 0.0298 | 7.0 | 3031 | 0.4060 | 0.9429 |
|
59 |
+
| 0.0298 | 8.0 | 3464 | 0.4284 | 0.9379 |
|
60 |
+
| 0.0207 | 9.0 | 3897 | 0.4804 | 0.9401 |
|
61 |
+
| 0.0197 | 10.0 | 4330 | 0.5089 | 0.9347 |
|
62 |
+
| 0.0177 | 11.0 | 4763 | 0.5430 | 0.9336 |
|
63 |
+
| 0.0143 | 12.0 | 5196 | 0.4997 | 0.9385 |
|
64 |
+
| 0.0138 | 13.0 | 5629 | 0.4695 | 0.9429 |
|
65 |
+
| 0.0066 | 14.0 | 6062 | 0.5391 | 0.9363 |
|
66 |
+
| 0.0066 | 15.0 | 6495 | 0.5354 | 0.9412 |
|
67 |
+
| 0.0042 | 16.0 | 6928 | 0.4295 | 0.9473 |
|
68 |
+
| 0.0067 | 17.0 | 7361 | 0.4948 | 0.9429 |
|
69 |
+
| 0.0053 | 18.0 | 7794 | 0.4720 | 0.9473 |
|
70 |
+
| 0.0041 | 19.0 | 8227 | 0.4552 | 0.9451 |
|
71 |
+
| 0.0068 | 20.0 | 8660 | 0.4539 | 0.9484 |
|
72 |
+
|
73 |
+
|
74 |
+
### Framework versions
|
75 |
+
|
76 |
+
- Transformers 4.32.1
|
77 |
+
- Pytorch 2.1.1
|
78 |
+
- Datasets 2.12.0
|
79 |
+
- Tokenizers 0.13.3
|