Marcos12886
commited on
Commit
•
4625a94
1
Parent(s):
69b7db8
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 +77,15 @@ 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 | 0.9956 | 85 | 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: 0.989010989010989
|
30 |
+
- name: F1
|
31 |
+
type: f1
|
32 |
+
value: 0.9890405015532383
|
33 |
+
- name: Precision
|
34 |
+
type: precision
|
35 |
+
value: 0.9891330367917903
|
36 |
+
- name: Recall
|
37 |
+
type: recall
|
38 |
+
value: 0.989010989010989
|
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: 0.0398
|
49 |
+
- Accuracy: 0.9890
|
50 |
+
- F1: 0.9890
|
51 |
+
- Precision: 0.9891
|
52 |
+
- Recall: 0.9890
|
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: 3
|
81 |
|
82 |
### Training results
|
83 |
|
84 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
85 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
86 |
+
| No log | 0.9956 | 85 | 0.0769 | 0.9758 | 0.9760 | 0.9764 | 0.9758 |
|
87 |
+
| No log | 1.9912 | 170 | 0.0444 | 0.9875 | 0.9876 | 0.9876 | 0.9875 |
|
88 |
+
| No log | 2.9868 | 255 | 0.0398 | 0.9890 | 0.9890 | 0.9891 | 0.9890 |
|
89 |
|
90 |
|
91 |
### 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 sha256:9f4d1bcece15f285a46eb855f203bd43924522bb36fe48d2d6c26990580d046d
|
3 |
size 94763496
|
runs/Sep02_01-09-27_ubumarcos/events.out.tfevents.1725232180.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49995861ce24f79defd1239b0a9255f1722c4193a1d606c6c2355783b9200a96
|
3 |
+
size 7570
|
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 sha256:37edd9986d3659d5cfeb9aa8cfbe6429149a6cd74482bcfbbbae5877c8eae7df
|
3 |
size 5240
|