metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: finetuned-FER2013
    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: 0.7011494252873564

finetuned-FER2013

This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.8313
Accuracy: 0.7011

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-06
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.7483	1.0	202	1.7005	0.3386
1.4419	2.0	404	1.3213	0.5315
1.2917	3.0	606	1.1559	0.5785
1.2437	4.0	808	1.0729	0.6162
1.1635	5.0	1010	1.0161	0.6311
1.1087	6.0	1212	0.9862	0.6465
1.0964	7.0	1414	0.9901	0.6440
1.0895	8.0	1616	0.9410	0.6555
1.0384	9.0	1818	0.9221	0.6628
1.0333	10.0	2020	0.9142	0.6681
1.0016	11.0	2222	0.9081	0.6681
0.9503	12.0	2424	0.9013	0.6712
0.9804	13.0	2626	0.8937	0.6771
0.9712	14.0	2828	0.8809	0.6830
1.0151	15.0	3030	0.8704	0.6855
0.9739	16.0	3232	0.8886	0.6775
0.9267	17.0	3434	0.8653	0.6855
0.9428	18.0	3636	0.8633	0.6848
0.9654	19.0	3838	0.8697	0.6809
0.9256	20.0	4040	0.8559	0.6855
0.9345	21.0	4242	0.8533	0.6883
0.9479	22.0	4444	0.8548	0.6907
0.8829	23.0	4646	0.8461	0.6851
0.8999	24.0	4848	0.8399	0.6883
0.9047	25.0	5050	0.8403	0.6973
0.9415	26.0	5252	0.8437	0.6952
0.937	27.0	5454	0.8393	0.6931
0.8692	28.0	5656	0.8331	0.6977
0.9396	29.0	5858	0.8418	0.6973
0.8712	30.0	6060	0.8392	0.6921
0.9426	31.0	6262	0.8324	0.7011
0.884	32.0	6464	0.8325	0.6959
0.8433	33.0	6666	0.8300	0.6987
0.8869	34.0	6868	0.8328	0.6963
0.89	35.0	7070	0.8324	0.6973
0.8639	36.0	7272	0.8317	0.6956
0.8844	37.0	7474	0.8315	0.6970
0.8621	38.0	7676	0.8334	0.6991
0.8942	39.0	7878	0.8350	0.6998
0.8609	40.0	8080	0.8313	0.7011

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0