Marcos12886
commited on
Commit
•
892bbae
1
Parent(s):
baca402
End of training
Browse files
README.md
CHANGED
@@ -6,9 +6,36 @@ tags:
|
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- audiofolder
|
|
|
|
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: distilhubert-finetuned-cry-detector
|
11 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
---
|
13 |
|
14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -17,6 +44,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# distilhubert-finetuned-cry-detector
|
18 |
|
19 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -44,13 +77,22 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: cosine
|
46 |
- lr_scheduler_warmup_ratio: 0.001
|
47 |
-
- num_epochs:
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
52 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
53 |
-
| No log | 0.9412 | 12 | 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
|
56 |
### Framework versions
|
|
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- audiofolder
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
- f1
|
12 |
+
- precision
|
13 |
+
- recall
|
14 |
model-index:
|
15 |
- name: distilhubert-finetuned-cry-detector
|
16 |
+
results:
|
17 |
+
- task:
|
18 |
+
name: Audio Classification
|
19 |
+
type: audio-classification
|
20 |
+
dataset:
|
21 |
+
name: audiofolder
|
22 |
+
type: audiofolder
|
23 |
+
config: default
|
24 |
+
split: train
|
25 |
+
args: default
|
26 |
+
metrics:
|
27 |
+
- name: Accuracy
|
28 |
+
type: accuracy
|
29 |
+
value: 0.9852941176470589
|
30 |
+
- name: F1
|
31 |
+
type: f1
|
32 |
+
value: 0.9853150765112866
|
33 |
+
- name: Precision
|
34 |
+
type: precision
|
35 |
+
value: 0.9853868369053048
|
36 |
+
- name: Recall
|
37 |
+
type: recall
|
38 |
+
value: 0.9852941176470589
|
39 |
---
|
40 |
|
41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
44 |
# distilhubert-finetuned-cry-detector
|
45 |
|
46 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the audiofolder dataset.
|
47 |
+
It achieves the following results on the evaluation set:
|
48 |
+
- Loss: 0.0332
|
49 |
+
- Accuracy: 0.9853
|
50 |
+
- F1: 0.9853
|
51 |
+
- Precision: 0.9854
|
52 |
+
- Recall: 0.9853
|
53 |
|
54 |
## Model description
|
55 |
|
|
|
77 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
78 |
- lr_scheduler_type: cosine
|
79 |
- lr_scheduler_warmup_ratio: 0.001
|
80 |
+
- num_epochs: 10
|
81 |
|
82 |
### Training results
|
83 |
|
84 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
85 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
86 |
+
| No log | 0.9412 | 12 | 0.1931 | 0.9363 | 0.9365 | 0.9372 | 0.9363 |
|
87 |
+
| No log | 1.9608 | 25 | 0.0950 | 0.9706 | 0.9704 | 0.9710 | 0.9706 |
|
88 |
+
| No log | 2.9804 | 38 | 0.0611 | 0.9804 | 0.9804 | 0.9804 | 0.9804 |
|
89 |
+
| No log | 4.0 | 51 | 0.0492 | 0.9853 | 0.9853 | 0.9853 | 0.9853 |
|
90 |
+
| No log | 4.9412 | 63 | 0.0588 | 0.9804 | 0.9805 | 0.9814 | 0.9804 |
|
91 |
+
| No log | 5.9608 | 76 | 0.0368 | 0.9853 | 0.9853 | 0.9854 | 0.9853 |
|
92 |
+
| No log | 6.9804 | 89 | 0.0382 | 0.9902 | 0.9902 | 0.9903 | 0.9902 |
|
93 |
+
| No log | 8.0 | 102 | 0.0318 | 0.9951 | 0.9951 | 0.9951 | 0.9951 |
|
94 |
+
| No log | 8.9412 | 114 | 0.0331 | 0.9853 | 0.9853 | 0.9854 | 0.9853 |
|
95 |
+
| No log | 9.4118 | 120 | 0.0332 | 0.9853 | 0.9853 | 0.9854 | 0.9853 |
|
96 |
|
97 |
|
98 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 94763496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:098c90d2cba195ac20033090c5954f7ef596abcdeebba724cb1365151033b05e
|
3 |
size 94763496
|
runs/Sep01_13-01-56_ubumarcos/events.out.tfevents.1725188518.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47699197c72dcec085f85612f80b753c7cc8dbe0771b4fc7e232ef7fbf4ed4c0
|
3 |
+
size 10789
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b77b2a33ca88330b7909aacab81332695e9c9dcf797e7a7757ca31ffcde6f31
|
3 |
size 5240
|