metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: emo-vit-base-patch16-224-in21k
    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: 0.6

emo-vit-base-patch16-224-in21k

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 1.1350
Accuracy: 0.6

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 10
num_epochs: 250

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0786	1.0	10	2.0448	0.2875
2.0107	2.0	20	1.9673	0.3125
1.8902	3.0	30	1.8561	0.4125
1.7355	4.0	40	1.6772	0.475
1.5861	5.0	50	1.5472	0.5
1.4665	6.0	60	1.4588	0.5375
1.3571	7.0	70	1.3812	0.5188
1.2465	8.0	80	1.3115	0.5312
1.1512	9.0	90	1.2910	0.525
1.0691	10.0	100	1.2342	0.5125
0.9837	11.0	110	1.2130	0.5437
0.9008	12.0	120	1.2073	0.5563
0.8315	13.0	130	1.1994	0.55
0.7634	14.0	140	1.1707	0.5563
0.709	15.0	150	1.1815	0.5563
0.6516	16.0	160	1.1622	0.5938
0.5933	17.0	170	1.2124	0.5312
0.5902	18.0	180	1.1782	0.5625
0.5122	19.0	190	1.2203	0.5625
0.4661	20.0	200	1.1928	0.5563
0.4797	21.0	210	1.1350	0.6
0.4459	22.0	220	1.2052	0.5563
0.4308	23.0	230	1.1729	0.5875
0.4121	24.0	240	1.2045	0.5375
0.3571	25.0	250	1.1906	0.6
0.3294	26.0	260	1.2311	0.5563
0.3661	27.0	270	1.2366	0.5375
0.328	28.0	280	1.2087	0.6
0.3352	29.0	290	1.2005	0.575
0.2923	30.0	300	1.2005	0.5813
0.2607	31.0	310	1.2309	0.5563
0.277	32.0	320	1.2385	0.5813
0.2678	33.0	330	1.2511	0.5563
0.2611	34.0	340	1.2675	0.575
0.2559	35.0	350	1.2869	0.575
0.2813	36.0	360	1.3965	0.55
0.2527	37.0	370	1.2851	0.6
0.2466	38.0	380	1.3265	0.55
0.2648	39.0	390	1.3024	0.575
0.2607	40.0	400	1.3884	0.5375
0.222	41.0	410	1.2922	0.5625
0.2095	42.0	420	1.3410	0.5437
0.197	43.0	430	1.3482	0.575
0.1964	44.0	440	1.3416	0.5687
0.2133	45.0	450	1.4440	0.5687
0.2095	46.0	460	1.3465	0.5437

Framework versions

Transformers 4.33.1
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3