Commit
•
7a89f64
1
Parent(s):
01dd95f
Training completed!
Browse files- README.md +94 -0
- model.safetensors +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 |
+
- emotion
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: distilbert-base-uncased-finetuned-emotion
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Text Classification
|
16 |
+
type: text-classification
|
17 |
+
dataset:
|
18 |
+
name: emotion
|
19 |
+
type: emotion
|
20 |
+
config: split
|
21 |
+
split: validation
|
22 |
+
args: split
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.94
|
27 |
+
- name: F1
|
28 |
+
type: f1
|
29 |
+
value: 0.9399138482178033
|
30 |
+
---
|
31 |
+
|
32 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
33 |
+
should probably proofread and complete it, then remove this comment. -->
|
34 |
+
|
35 |
+
# distilbert-base-uncased-finetuned-emotion
|
36 |
+
|
37 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
|
38 |
+
It achieves the following results on the evaluation set:
|
39 |
+
- Loss: 0.2319
|
40 |
+
- Accuracy: 0.94
|
41 |
+
- F1: 0.9399
|
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: 2e-05
|
61 |
+
- train_batch_size: 256
|
62 |
+
- eval_batch_size: 256
|
63 |
+
- seed: 42
|
64 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
65 |
+
- lr_scheduler_type: linear
|
66 |
+
- num_epochs: 15
|
67 |
+
|
68 |
+
### Training results
|
69 |
+
|
70 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
71 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
72 |
+
| No log | 1.0 | 63 | 0.1858 | 0.9375 | 0.9373 |
|
73 |
+
| No log | 2.0 | 126 | 0.2010 | 0.9295 | 0.9300 |
|
74 |
+
| No log | 3.0 | 189 | 0.1832 | 0.936 | 0.9365 |
|
75 |
+
| 0.0589 | 4.0 | 252 | 0.1928 | 0.9345 | 0.9340 |
|
76 |
+
| 0.0589 | 5.0 | 315 | 0.2094 | 0.937 | 0.9367 |
|
77 |
+
| 0.0589 | 6.0 | 378 | 0.2016 | 0.937 | 0.9369 |
|
78 |
+
| 0.0589 | 7.0 | 441 | 0.2205 | 0.936 | 0.9354 |
|
79 |
+
| 0.0427 | 8.0 | 504 | 0.2143 | 0.936 | 0.9355 |
|
80 |
+
| 0.0427 | 9.0 | 567 | 0.2184 | 0.9355 | 0.9357 |
|
81 |
+
| 0.0427 | 10.0 | 630 | 0.2216 | 0.9365 | 0.9365 |
|
82 |
+
| 0.0427 | 11.0 | 693 | 0.2313 | 0.938 | 0.9380 |
|
83 |
+
| 0.0261 | 12.0 | 756 | 0.2311 | 0.9395 | 0.9394 |
|
84 |
+
| 0.0261 | 13.0 | 819 | 0.2274 | 0.9395 | 0.9394 |
|
85 |
+
| 0.0261 | 14.0 | 882 | 0.2302 | 0.9395 | 0.9395 |
|
86 |
+
| 0.0261 | 15.0 | 945 | 0.2319 | 0.94 | 0.9399 |
|
87 |
+
|
88 |
+
|
89 |
+
### Framework versions
|
90 |
+
|
91 |
+
- Transformers 4.35.0
|
92 |
+
- Pytorch 2.1.0+cu121
|
93 |
+
- Datasets 2.14.6
|
94 |
+
- Tokenizers 0.14.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267844872
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c80665f9a529cd2c0fac6d2f929b4a2f930184afd64a2a560aeca60d4968427a
|
3 |
size 267844872
|