metadata
license: apache-2.0
base_model: Raihan004/Action_model
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Action_model
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8488576449912126
Action_model
This model is a fine-tuned version of Raihan004/Action_model on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5034
- Accuracy: 0.8489
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.7766 | 0.75 | 100 | 0.6780 | 0.8225 |
0.61 | 1.49 | 200 | 0.6279 | 0.8243 |
0.4734 | 2.24 | 300 | 0.5593 | 0.8278 |
0.5275 | 2.99 | 400 | 0.5148 | 0.8418 |
0.3767 | 3.73 | 500 | 0.5129 | 0.8436 |
0.3207 | 4.48 | 600 | 0.4966 | 0.8559 |
0.3155 | 5.22 | 700 | 0.5251 | 0.8453 |
0.2565 | 5.97 | 800 | 0.4790 | 0.8629 |
0.2791 | 6.72 | 900 | 0.5111 | 0.8524 |
0.1987 | 7.46 | 1000 | 0.5002 | 0.8453 |
0.2083 | 8.21 | 1100 | 0.5034 | 0.8629 |
0.2567 | 8.96 | 1200 | 0.4995 | 0.8576 |
0.2127 | 9.7 | 1300 | 0.5034 | 0.8489 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2