update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- go_emotions
|
7 |
+
metrics:
|
8 |
+
- f1
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: pretrained_model
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Text Classification
|
15 |
+
type: text-classification
|
16 |
+
dataset:
|
17 |
+
name: go_emotions
|
18 |
+
type: go_emotions
|
19 |
+
config: simplified
|
20 |
+
split: validation
|
21 |
+
args: simplified
|
22 |
+
metrics:
|
23 |
+
- name: F1
|
24 |
+
type: f1
|
25 |
+
value: 0.572835583796664
|
26 |
+
- name: Accuracy
|
27 |
+
type: accuracy
|
28 |
+
value: 0.45466273497972726
|
29 |
+
---
|
30 |
+
|
31 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
32 |
+
should probably proofread and complete it, then remove this comment. -->
|
33 |
+
|
34 |
+
# pretrained_model
|
35 |
+
|
36 |
+
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the go_emotions dataset.
|
37 |
+
It achieves the following results on the evaluation set:
|
38 |
+
- Loss: 0.1240
|
39 |
+
- F1: 0.5728
|
40 |
+
- Roc Auc: 0.7737
|
41 |
+
- Accuracy: 0.4547
|
42 |
+
|
43 |
+
## Model description
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Intended uses & limitations
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training and evaluation data
|
52 |
+
|
53 |
+
More information needed
|
54 |
+
|
55 |
+
## Training procedure
|
56 |
+
|
57 |
+
### Training hyperparameters
|
58 |
+
|
59 |
+
The following hyperparameters were used during training:
|
60 |
+
- learning_rate: 5e-05
|
61 |
+
- train_batch_size: 64
|
62 |
+
- eval_batch_size: 64
|
63 |
+
- seed: 42
|
64 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
+
- lr_scheduler_type: linear
|
66 |
+
- num_epochs: 10
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
72 |
+
| 0.1205 | 1.0 | 679 | 0.0865 | 0.5632 | 0.7347 | 0.4458 |
|
73 |
+
| 0.0859 | 2.0 | 1358 | 0.0829 | 0.5717 | 0.7378 | 0.4521 |
|
74 |
+
| 0.0727 | 3.0 | 2037 | 0.0827 | 0.5897 | 0.7523 | 0.4753 |
|
75 |
+
| 0.0629 | 4.0 | 2716 | 0.0857 | 0.5808 | 0.7535 | 0.4652 |
|
76 |
+
| 0.0568 | 5.0 | 3395 | 0.0904 | 0.5868 | 0.7616 | 0.4821 |
|
77 |
+
| 0.0423 | 6.0 | 4074 | 0.0989 | 0.5806 | 0.7682 | 0.4724 |
|
78 |
+
| 0.0344 | 7.0 | 4753 | 0.1079 | 0.5736 | 0.7657 | 0.4650 |
|
79 |
+
| 0.0296 | 8.0 | 5432 | 0.1158 | 0.5637 | 0.7649 | 0.4504 |
|
80 |
+
| 0.0206 | 9.0 | 6111 | 0.1200 | 0.5674 | 0.7689 | 0.4486 |
|
81 |
+
| 0.0177 | 10.0 | 6790 | 0.1240 | 0.5728 | 0.7737 | 0.4547 |
|
82 |
+
|
83 |
+
|
84 |
+
### Framework versions
|
85 |
+
|
86 |
+
- Transformers 4.26.0
|
87 |
+
- Pytorch 1.13.1+cu116
|
88 |
+
- Datasets 2.9.0
|
89 |
+
- Tokenizers 0.13.2
|