metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/timesformer-base-finetuned-k400
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: VideoMAE_LSA64_SR_24
results: []
TimeSformer_LSA64_SR_24
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: 0.0155
- Accuracy: 0.9922
- Precision: 0.9948
- Recall: 0.9922
- F1: 0.9917
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 8640
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 14.399 | 0.0333 | 288 | 2.0813 | 0.6953 | 0.6686 | 0.6953 | 0.6468 |
| 2.5013 | 1.0333 | 576 | 0.3335 | 0.9531 | 0.9673 | 0.9531 | 0.9518 |
| 0.2412 | 2.0333 | 864 | 0.0600 | 0.9961 | 0.9969 | 0.9961 | 0.9960 |
| 0.0331 | 3.0333 | 1152 | 0.0037 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0739 | 4.0333 | 1440 | 0.0085 | 0.9922 | 0.9938 | 0.9922 | 0.9921 |
| 0.0022 | 5.0333 | 1728 | 0.0112 | 0.9961 | 0.9969 | 0.9961 | 0.9960 |
| 0.0011 | 6.0333 | 2016 | 0.0008 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.0006 | 7.0333 | 2304 | 0.0004 | 1.0 | 1.0 | 1.0 | 1.0 |
| 0.001 | 8.0333 | 2592 | 0.0155 | 0.9922 | 0.9948 | 0.9922 | 0.9917 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.1