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-finetuned-kinetic400-subset-epoch6-num_frame_10_spatial_only
results: []
timesformer-base-finetuned-k400-finetuned-kinetic400-subset-epoch6-num_frame_10_spatial_only
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: 0.7364
- Accuracy: 0.8382
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: 1
- eval_batch_size: 1
- 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: 300
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0337 | 0.17 | 50 | 0.6661 | 0.8333 |
| 0.0027 | 1.17 | 100 | 0.9499 | 0.7778 |
| 0.0224 | 2.17 | 150 | 0.3809 | 0.9028 |
| 0.0006 | 3.17 | 200 | 0.4298 | 0.875 |
| 0.0003 | 4.17 | 250 | 0.4078 | 0.875 |
| 0.0009 | 5.17 | 300 | 0.4182 | 0.875 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2