metadata

license: apache-2.0
base_model: google/vit-large-patch16-224
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: 0.50-Train-Test-vit-large
    results: []

0.50-Train-Test-vit-large

This model is a fine-tuned version of google/vit-large-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8804
Accuracy: 0.8098

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
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.3722	0.9825	14	1.8140	0.3758
1.7117	1.9649	28	0.9446	0.7383
0.3741	2.9474	42	0.8083	0.7338
0.1709	4.0	57	0.7460	0.7562
0.0166	4.9825	71	0.7632	0.7763
0.0087	5.9649	85	0.9165	0.7629
0.013	6.9474	99	0.8161	0.7942
0.0029	8.0	114	0.8216	0.7964
0.0016	8.9825	128	0.8461	0.7919
0.0009	9.9649	142	0.8528	0.7919
0.0007	10.9474	156	0.8539	0.8031
0.0006	12.0	171	0.8586	0.8054
0.0006	12.9825	185	0.8622	0.8076
0.0005	13.9649	199	0.8649	0.8098
0.0005	14.9474	213	0.8677	0.8098
0.0005	16.0	228	0.8706	0.8098
0.0004	16.9825	242	0.8729	0.8098
0.0004	17.9649	256	0.8747	0.8098
0.0004	18.9474	270	0.8764	0.8076
0.0004	20.0	285	0.8776	0.8098
0.0004	20.9825	299	0.8789	0.8076
0.0003	21.9649	313	0.8794	0.8098
0.0003	22.9474	327	0.8801	0.8098
0.0003	24.0	342	0.8804	0.8098
0.0003	24.5614	350	0.8804	0.8098

Framework versions

Transformers 4.41.2
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.19.1