End of training
Browse files
README.md
CHANGED
@@ -17,12 +17,12 @@ model-index:
|
|
17 |
name: fair_face
|
18 |
type: fair_face
|
19 |
config: '0.25'
|
20 |
-
split:
|
21 |
args: '0.25'
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the fair_face dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -61,15 +61,18 @@ The following hyperparameters were used during training:
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_ratio: 0.2
|
64 |
-
- num_epochs:
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
-
| 4.
|
71 |
-
| 4.
|
72 |
-
| 4.
|
|
|
|
|
|
|
73 |
|
74 |
|
75 |
### Framework versions
|
|
|
17 |
name: fair_face
|
18 |
type: fair_face
|
19 |
config: '0.25'
|
20 |
+
split: validation
|
21 |
args: '0.25'
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.21252510498448055
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
32 |
|
33 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the fair_face dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 3.6347
|
36 |
+
- Accuracy: 0.2125
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_ratio: 0.2
|
64 |
+
- num_epochs: 1
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 4.7855 | 0.15 | 50 | 4.6444 | 0.0511 |
|
71 |
+
| 4.4242 | 0.29 | 100 | 4.2124 | 0.1418 |
|
72 |
+
| 4.0596 | 0.44 | 150 | 3.9402 | 0.1744 |
|
73 |
+
| 3.859 | 0.59 | 200 | 3.7823 | 0.1956 |
|
74 |
+
| 3.7392 | 0.74 | 250 | 3.6877 | 0.2105 |
|
75 |
+
| 3.6424 | 0.88 | 300 | 3.6347 | 0.2125 |
|
76 |
|
77 |
|
78 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343605408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7374de89e549bf73c87b90a1212a8ac5aecda66da64f5eb53a1118943e1860e6
|
3 |
size 343605408
|
runs/Jan09_11-42-40_1e4a6d9d077c/events.out.tfevents.1704800584.1e4a6d9d077c.1435.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92ec682cc457ee5ab7b32f161e8a49dfcf903695696630b212c03924af8ff56e
|
3 |
+
size 13070
|
runs/Jan09_11-45-34_1e4a6d9d077c/events.out.tfevents.1704800739.1e4a6d9d077c.1435.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca3661c551093c85c960a6b69161c66fff5ca6fbbea283072f25e006419a6ace
|
3 |
+
size 16334
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbcfe586223246fd5f507ee5142339d78c96702bc99be991bd83902eb67d10ee
|
3 |
size 4600
|