JackWong0911
commited on
Commit
•
406b6b7
1
Parent(s):
2a37bf6
Model save
Browse files
README.md
CHANGED
@@ -3,8 +3,6 @@ license: cc-by-nc-4.0
|
|
3 |
base_model: facebook/timesformer-base-finetuned-k400
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
metrics:
|
7 |
-
- accuracy
|
8 |
model-index:
|
9 |
- name: timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_myViT
|
10 |
results: []
|
@@ -16,9 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
# timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_myViT
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
|
19 |
-
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.3731
|
21 |
-
- Accuracy: 0.9412
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -44,19 +39,7 @@ The following hyperparameters were used during training:
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_ratio: 0.1
|
47 |
-
- training_steps:
|
48 |
-
|
49 |
-
### Training results
|
50 |
-
|
51 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
-
| 0.1507 | 0.17 | 50 | 0.4026 | 0.8889 |
|
54 |
-
| 0.0261 | 1.17 | 100 | 0.5326 | 0.8333 |
|
55 |
-
| 0.0047 | 2.17 | 150 | 0.3377 | 0.9167 |
|
56 |
-
| 0.0053 | 3.17 | 200 | 0.2018 | 0.9306 |
|
57 |
-
| 0.0006 | 4.17 | 250 | 0.2301 | 0.9028 |
|
58 |
-
| 0.0004 | 5.17 | 300 | 0.1563 | 0.9306 |
|
59 |
-
|
60 |
|
61 |
### Framework versions
|
62 |
|
|
|
3 |
base_model: facebook/timesformer-base-finetuned-k400
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_myViT
|
8 |
results: []
|
|
|
14 |
# timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_myViT
|
15 |
|
16 |
This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
- lr_scheduler_warmup_ratio: 0.1
|
42 |
+
- training_steps: 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
|
44 |
### Framework versions
|
45 |
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 485087636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d8cfeb40f25e253652afa1b19f1f7b1810e13466e21cb2651c0eb67f79bd175
|
3 |
size 485087636
|
runs/Apr06_04-31-00_fb3317d1dbb6/events.out.tfevents.1712377863.fb3317d1dbb6.3266.0
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 sha256:573370e1ba4e26a9f06727d67eaf1096c16246a4a69fbcecaa389aef4b387584
|
3 |
+
size 144224
|