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-ElderReact-anger-balanced
results: []
timesformer-base-finetuned-k400-finetuned-ElderReact-anger-balanced
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: 0.8048
- Accuracy: 0.5012
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: 16
- eval_batch_size: 16
- 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: 240
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6923 | 0.1 | 25 | 0.8338 | 0.4601 |
| 0.6436 | 1.1 | 50 | 0.9187 | 0.5058 |
| 0.5464 | 2.1 | 75 | 0.8165 | 0.5313 |
| 0.4147 | 3.1 | 100 | 0.9950 | 0.5228 |
| 0.4483 | 4.1 | 125 | 1.0642 | 0.5080 |
| 0.3565 | 5.1 | 150 | 0.8611 | 0.5143 |
| 0.3114 | 6.1 | 175 | 0.9595 | 0.5186 |
| 0.3074 | 7.1 | 200 | 1.0242 | 0.5197 |
| 0.2888 | 8.1 | 225 | 1.1212 | 0.5069 |
| 0.2609 | 9.06 | 240 | 1.1119 | 0.5112 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2