Downloads · 30 days
4
21% of all-time downloads
person_activity_model_vidclass_1.pth-finetuned-subset
gauti83/person_activity_model_vidclass_1.pth-finetuned-subset
person_activity_model_vidclass_1.pth-finetuned-subset is a machine learning model from gauti83. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
All-time downloads
19
Public
Parameters
86.2M
13.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors345 MB · 100%
At a glance
- Model type
- videomae
- Access
- Public
- Created
- Aug 2, 2024
- Updated
- Aug 2, 2024
- SHA
- 5454b591
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
person_activity_model_vidclass_1.pth-finetuned-subset
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2220
- Accuracy: 0.3401
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 2880
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.0843 | 0.0253 | 73 | 3.1468 | 0.1522 |
| 2.9775 | 1.0253 | 146 | 3.1720 | 0.1139 |
| 2.5261 | 2.0253 | 219 | 3.0337 | 0.1971 |
| 3.0475 | 3.0253 | 292 | 3.1015 | 0.1095 |
| 2.9277 | 4.0253 | 365 | 3.4242 | 0.0774 |
| 3.112 | 5.0253 | 438 | 3.3036 | 0.0920 |
| 2.8737 | 6.0253 | 511 | 2.8488 | 0.2146 |
| 2.7474 | 7.0253 | 584 | 3.0054 | 0.2 |
| 2.2951 | 8.0253 | 657 | 3.0941 | 0.1839 |
| 2.3981 | 9.0253 | 730 | 2.9081 | 0.2336 |
| 2.3622 | 10.0253 | 803 | 2.9013 | 0.2161 |
| 1.9721 | 11.0253 | 876 | 2.9779 | 0.2161 |
| 1.9668 | 12.0253 | 949 | 2.9319 | 0.2044 |
| 1.3276 | 13.0253 | 1022 | 3.2656 | 0.1942 |
| 1.3972 | 14.0253 | 1095 | 2.8820 | 0.2832 |
| 1.3842 | 15.0253 | 1168 | 2.9859 | 0.2204 |
| 1.1888 | 16.0253 | 1241 | 2.8233 | 0.2380 |
| 0.7741 | 17.0253 | 1314 | 2.8740 | 0.2745 |
| 0.912 | 18.0253 | 1387 | 2.9991 | 0.2745 |
| 0.8878 | 19.0253 | 1460 | 2.8563 | 0.3358 |
| 0.8254 | 20.0253 | 1533 | 3.0791 | 0.2803 |
| 0.4527 | 21.0253 | 1606 | 3.1713 | 0.2642 |
| 0.9218 | 22.0253 | 1679 | 3.1070 | 0.2745 |
| 0.6942 | 23.0253 | 1752 | 3.1531 | 0.2745 |
| 0.6404 | 24.0253 | 1825 | 3.1300 | 0.3095 |
| 0.3504 | 25.0253 | 1898 | 3.2553 | 0.2715 |
| 0.7663 | 26.0253 | 1971 | 3.2086 | 0.2467 |
| 0.1879 | 27.0253 | 2044 | 3.0527 | 0.3299 |
| 0.3953 | 28.0253 | 2117 | 3.0623 | 0.3241 |
| 0.3036 | 29.0253 | 2190 | 3.2308 | 0.2715 |
| 0.2092 | 30.0253 | 2263 | 3.2329 | 0.2599 |
| 0.3355 | 31.0253 | 2336 | 3.2865 | 0.2569 |
| 0.0778 | 32.0253 | 2409 | 3.1850 | 0.3036 |
| 0.094 | 33.0253 | 2482 | 3.1503 | 0.3606 |
| 0.1938 | 34.0253 | 2555 | 3.2509 | 0.2949 |
| 0.045 | 35.0253 | 2628 | 3.2420 | 0.3080 |
| 0.1364 | 36.0253 | 2701 | 3.2328 | 0.3416 |
| 0.0607 | 37.0253 | 2774 | 3.2086 | 0.3489 |
| 0.038 | 38.0253 | 2847 | 3.2208 | 0.3416 |
| 0.1923 | 39.0115 | 2880 | 3.2220 | 0.3401 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.0.1+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1
- Type
- videomae
- Created
- Aug 2, 2024
- Updated
- Aug 2, 2024