Commit
•
0c44243
1
Parent(s):
03a8662
Model save
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: cc-by-nc-4.0
|
|
| 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_full_time_space
|
| 8 |
results: []
|
|
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
# timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_full_time_space
|
| 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 |
|
|
@@ -41,6 +46,18 @@ The following hyperparameters were used during training:
|
|
| 41 |
- lr_scheduler_warmup_ratio: 0.1
|
| 42 |
- training_steps: 300
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.38.2
|
|
|
|
| 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_full_time_space
|
| 10 |
results: []
|
|
|
|
| 16 |
# timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_full_time_space
|
| 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: 0.4630
|
| 21 |
+
- Accuracy: 0.8971
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 46 |
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
- training_steps: 300
|
| 48 |
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 53 |
+
| 0.5915 | 0.17 | 50 | 0.6170 | 0.8611 |
|
| 54 |
+
| 0.2742 | 1.17 | 100 | 0.4572 | 0.8333 |
|
| 55 |
+
| 0.0174 | 2.17 | 150 | 0.3006 | 0.8611 |
|
| 56 |
+
| 0.0309 | 3.17 | 200 | 0.3319 | 0.8889 |
|
| 57 |
+
| 0.0006 | 4.17 | 250 | 0.3438 | 0.8889 |
|
| 58 |
+
| 0.0008 | 5.17 | 300 | 0.3266 | 0.8889 |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
- Transformers 4.38.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343259388
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d189b39df6d76b528ff2539fcc1982b3501c177a479360bd0c238f14da181e6
|
| 3 |
size 343259388
|
runs/Apr05_14-01-57_9e302ecab715/events.out.tfevents.1712325746.9e302ecab715.7141.0
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 sha256:3b7de06c4f6153b0cc64d588ce45d84b5296500192e68951f562674206071a9d
|
| 3 |
+
size 88476
|
runs/Apr05_14-01-57_9e302ecab715/events.out.tfevents.1712326889.9e302ecab715.7141.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4aa786eec1e8c5c56f94df16eb8dfe7fdc358b7b7d65e23b7fef8eba9ff4c662
|
| 3 |
+
size 7415
|