End of training
Browse files
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- emotion
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: distilbert-emotion-intent
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: emotion
|
17 |
+
type: emotion
|
18 |
+
config: default
|
19 |
+
split: train
|
20 |
+
args: default
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.937
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# distilbert-emotion-intent
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.1989
|
35 |
+
- Accuracy: 0.937
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 5e-05
|
55 |
+
- train_batch_size: 16
|
56 |
+
- eval_batch_size: 16
|
57 |
+
- seed: 33
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 15
|
61 |
+
- mixed_precision_training: Native AMP
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| 0.3939 | 1.0 | 1000 | 0.2123 | 0.9285 |
|
68 |
+
| 0.1539 | 2.0 | 2000 | 0.1635 | 0.936 |
|
69 |
+
| 0.1213 | 3.0 | 3000 | 0.1820 | 0.931 |
|
70 |
+
| 0.1016 | 4.0 | 4000 | 0.1989 | 0.937 |
|
71 |
+
| 0.0713 | 5.0 | 5000 | 0.2681 | 0.935 |
|
72 |
+
| 0.0462 | 6.0 | 6000 | 0.3034 | 0.9365 |
|
73 |
+
| 0.027 | 7.0 | 7000 | 0.3538 | 0.937 |
|
74 |
+
|
75 |
+
|
76 |
+
### Framework versions
|
77 |
+
|
78 |
+
- Transformers 4.22.1
|
79 |
+
- Pytorch 1.12.1+cu113
|
80 |
+
- Datasets 2.5.1
|
81 |
+
- Tokenizers 0.12.1
|
logs/events.out.tfevents.1664027078.6f1754e52420.1493.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a93bb9447c15e382949a5d50bbdbbf0da24e641a66756499bb2e545a8c795e66
|
3 |
+
size 7589
|
logs/events.out.tfevents.1664027569.6f1754e52420.1493.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01a08c11c5fa7b0fabc3c07f160cff6bcda1a4e5496edebbd4df232a5e215766
|
3 |
+
size 363
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267866609
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:956353468ca880022997eca540f6e6df2e40ce78fa8512e801e9f5046426045b
|
3 |
size 267866609
|