End of training
Browse files- README.md +72 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: google/vivit-b-16x2-kinetics400
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: VIVIT-d2
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# VIVIT-d2
|
| 18 |
+
|
| 19 |
+
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.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.9103
|
| 22 |
+
- Accuracy: 0.4210
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 5e-05
|
| 42 |
+
- train_batch_size: 1
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- training_steps: 6650
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 2.556 | 0.1 | 665 | 2.3470 | 0.2123 |
|
| 56 |
+
| 2.0142 | 1.1 | 1330 | 2.1601 | 0.3180 |
|
| 57 |
+
| 2.122 | 2.1 | 1995 | 2.0851 | 0.4047 |
|
| 58 |
+
| 1.7405 | 3.1 | 2660 | 2.3452 | 0.4205 |
|
| 59 |
+
| 1.2998 | 4.1 | 3325 | 2.3814 | 0.4557 |
|
| 60 |
+
| 1.4591 | 5.1 | 3990 | 2.7093 | 0.3820 |
|
| 61 |
+
| 0.8984 | 6.1 | 4655 | 2.5562 | 0.3584 |
|
| 62 |
+
| 0.3971 | 7.1 | 5320 | 3.1583 | 0.4057 |
|
| 63 |
+
| 0.5996 | 8.1 | 5985 | 2.9134 | 0.4154 |
|
| 64 |
+
| 0.8684 | 9.1 | 6650 | 2.9103 | 0.4210 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.46.2
|
| 70 |
+
- Pytorch 2.5.1+cu124
|
| 71 |
+
- Datasets 3.1.0
|
| 72 |
+
- Tokenizers 0.20.3
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 354649220
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbb974efffdc2446410eb7d2eb1ddc7a950283341dae5c983fcb87b24f0adb99
|
| 3 |
size 354649220
|