Marcos12886
commited on
Commit
•
6081dcf
1
Parent(s):
39f3488
End of training
Browse files
README.md
CHANGED
@@ -4,6 +4,11 @@ license: apache-2.0
|
|
4 |
base_model: ntu-spml/distilhubert
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
7 |
model-index:
|
8 |
- name: distilhubert-finetuned-cry-detector
|
9 |
results: []
|
@@ -15,6 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
# distilhubert-finetuned-cry-detector
|
16 |
|
17 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -42,13 +53,20 @@ The following hyperparameters were used during training:
|
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
- lr_scheduler_warmup_ratio: 0.001
|
45 |
-
- num_epochs:
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
50 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
51 |
-
| No log | 0.9956 | 85 | 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
4 |
base_model: ntu-spml/distilhubert
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
model-index:
|
13 |
- name: distilhubert-finetuned-cry-detector
|
14 |
results: []
|
|
|
20 |
# distilhubert-finetuned-cry-detector
|
21 |
|
22 |
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.0878
|
25 |
+
- Accuracy: 0.9861
|
26 |
+
- Precision: 0.9861
|
27 |
+
- Recall: 0.9861
|
28 |
+
- F1: 0.9861
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
53 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
- lr_scheduler_type: cosine
|
55 |
- lr_scheduler_warmup_ratio: 0.001
|
56 |
+
- num_epochs: 8
|
57 |
|
58 |
### Training results
|
59 |
|
60 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
61 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
62 |
+
| No log | 0.9956 | 85 | 0.1204 | 0.9641 | 0.9641 | 0.9641 | 0.9638 |
|
63 |
+
| No log | 1.9912 | 170 | 0.0847 | 0.9773 | 0.9772 | 0.9773 | 0.9773 |
|
64 |
+
| No log | 2.9985 | 256 | 0.1025 | 0.9766 | 0.9769 | 0.9766 | 0.9766 |
|
65 |
+
| No log | 3.9941 | 341 | 0.0869 | 0.9832 | 0.9835 | 0.9832 | 0.9832 |
|
66 |
+
| No log | 4.9898 | 426 | 0.0746 | 0.9832 | 0.9834 | 0.9832 | 0.9832 |
|
67 |
+
| 0.0538 | 5.9971 | 512 | 0.0870 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
|
68 |
+
| 0.0538 | 6.9927 | 597 | 0.0890 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
|
69 |
+
| 0.0538 | 7.9649 | 680 | 0.0878 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
|
70 |
|
71 |
|
72 |
### 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:dbc5b2463f7b10d6accd90a38663b1fe5924ce417d20bd4c4b022491ab407a53
|
3 |
size 94763496
|
runs/Sep08_19-43-06_ubumarcos/events.out.tfevents.1725817387.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71b8ca02ef5caa8bb118cb998118582f177965559b0050a180598244ff3359d7
|
3 |
+
size 6661
|
runs/Sep08_19-57-45_ubumarcos/events.out.tfevents.1725818266.ubumarcos
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:baff4a5ec9071f4919cc3c8fb3eb07f523c18644538fec4decc9a9a9cc8b0691
|
3 |
+
size 10183
|
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:cda0bf828ccc04cd6d3fb7933f60f34ca3c8ba14b14579f9e878d688bc739b4a
|
3 |
size 5240
|