Model save
Browse files- README.md +70 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: google/vivit-b-16x2-kinetics400
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: vivit-b-16x2-collected-dataset
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# vivit-b-16x2-collected-dataset
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.2578
|
| 21 |
+
- Accuracy: 0.9610
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
+
- eval_batch_size: 2
|
| 43 |
+
- seed: 42
|
| 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: 14020
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 53 |
+
| 0.1001 | 0.1 | 1403 | 0.8989 | 0.7789 |
|
| 54 |
+
| 0.2646 | 1.1 | 2806 | 0.5655 | 0.8857 |
|
| 55 |
+
| 0.0785 | 2.1 | 4209 | 0.4806 | 0.9053 |
|
| 56 |
+
| 0.0001 | 3.1 | 5612 | 0.3706 | 0.9398 |
|
| 57 |
+
| 0.054 | 4.1 | 7015 | 0.4007 | 0.9368 |
|
| 58 |
+
| 0.0003 | 5.1 | 8418 | 0.2354 | 0.9669 |
|
| 59 |
+
| 0.0001 | 6.1 | 9821 | 0.3900 | 0.9474 |
|
| 60 |
+
| 0.0003 | 7.1 | 11224 | 0.2667 | 0.9579 |
|
| 61 |
+
| 0.0001 | 8.1 | 12627 | 0.2436 | 0.9654 |
|
| 62 |
+
| 0.0 | 9.1 | 14020 | 0.2432 | 0.9654 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.39.0
|
| 68 |
+
- Pytorch 2.1.0
|
| 69 |
+
- Datasets 2.18.0
|
| 70 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 354627680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3844a1bd922a1f16adcdc915bc19230de1c165b15cdb6e3875ef57af6bdfc6b
|
| 3 |
size 354627680
|