metadata
license: cc-by-nc-4.0
base_model: namnh2002/model_timesformer_subset_02
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: model_timesformer_subset_02
results: []
model_timesformer_subset_02
This model is a fine-tuned version of namnh2002/model_timesformer_subset_02 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8445
- Accuracy: 0.5395
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9537 | 0.12 | 250 | 1.6973 | 0.5245 |
| 0.8751 | 1.12 | 500 | 1.7124 | 0.5345 |
| 0.7491 | 2.12 | 750 | 1.7508 | 0.5365 |
| 0.6867 | 3.12 | 1000 | 1.7845 | 0.5325 |
| 0.5597 | 4.12 | 1250 | 1.8160 | 0.539 |
| 0.4531 | 5.12 | 1500 | 1.8213 | 0.5455 |
| 0.3253 | 6.12 | 1750 | 1.9083 | 0.5435 |
| 0.3531 | 7.12 | 2000 | 1.8445 | 0.5395 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2