metadata
license: cc-by-nc-4.0
base_model: facebook/timesformer-base-finetuned-k400
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: >-
timesformer-base-finetuned-k400-kinetic400-subset-epoch10real-num_frame_10_myViT_more_data
results: []
timesformer-base-finetuned-k400-kinetic400-subset-epoch10real-num_frame_10_myViT_more_data
This model is a fine-tuned version of facebook/timesformer-base-finetuned-k400 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2695
- Accuracy: 0.93
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: 1250
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2067 | 0.1 | 125 | 0.1522 | 0.96 |
| 0.3735 | 1.1 | 250 | 1.3726 | 0.75 |
| 0.0037 | 2.1 | 375 | 0.1194 | 0.98 |
| 0.0005 | 3.1 | 500 | 0.2509 | 0.95 |
| 0.0003 | 4.1 | 625 | 0.2948 | 0.96 |
| 0.0007 | 5.1 | 750 | 0.4483 | 0.92 |
| 0.0018 | 6.1 | 875 | 0.3135 | 0.94 |
| 0.0001 | 7.1 | 1000 | 0.3060 | 0.95 |
| 0.0001 | 8.1 | 1125 | 0.3100 | 0.95 |
| 0.0001 | 9.1 | 1250 | 0.3124 | 0.95 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2