metadata

license: apache-2.0
base_model: microsoft/beit-large-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_10x_beit_large_adamax_00001_fold1
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: test
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9282136894824707

smids_10x_beit_large_adamax_00001_fold1

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

Loss: 0.8887
Accuracy: 0.9282

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: 1e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1288	1.0	751	0.2785	0.9065
0.0676	2.0	1502	0.3146	0.9149
0.0264	3.0	2253	0.4181	0.9115
0.025	4.0	3004	0.5488	0.9199
0.0069	5.0	3755	0.5526	0.9182
0.0049	6.0	4506	0.6296	0.9165
0.0005	7.0	5257	0.7054	0.9149
0.0001	8.0	6008	0.7404	0.9182
0.0362	9.0	6759	0.7520	0.9132
0.0001	10.0	7510	0.8011	0.9149
0.0001	11.0	8261	0.7591	0.9199
0.0002	12.0	9012	0.7216	0.9215
0.0024	13.0	9763	0.8101	0.9132
0.0	14.0	10514	0.8382	0.9249
0.0	15.0	11265	0.8571	0.9165
0.0	16.0	12016	0.8307	0.9249
0.0002	17.0	12767	0.8135	0.9098
0.0	18.0	13518	0.9070	0.9132
0.0	19.0	14269	0.8650	0.9115
0.0	20.0	15020	0.8297	0.9265
0.0	21.0	15771	0.8359	0.9282
0.0	22.0	16522	0.8827	0.9265
0.0	23.0	17273	0.8484	0.9215
0.0	24.0	18024	0.8739	0.9182
0.0004	25.0	18775	0.8728	0.9232
0.0	26.0	19526	0.8742	0.9149
0.0	27.0	20277	0.9029	0.9199
0.0	28.0	21028	0.8812	0.9232
0.0109	29.0	21779	0.9326	0.9215
0.0	30.0	22530	0.9197	0.9115
0.0001	31.0	23281	0.8910	0.9215
0.0	32.0	24032	0.8659	0.9215
0.0	33.0	24783	0.8759	0.9232
0.0	34.0	25534	0.9176	0.9199
0.0	35.0	26285	0.8674	0.9249
0.0	36.0	27036	0.8364	0.9249
0.0	37.0	27787	0.8518	0.9265
0.0	38.0	28538	0.8614	0.9232
0.0	39.0	29289	0.8789	0.9215
0.0	40.0	30040	0.8979	0.9215
0.0	41.0	30791	0.9262	0.9199
0.0107	42.0	31542	0.8969	0.9232
0.0	43.0	32293	0.9021	0.9265
0.0	44.0	33044	0.8921	0.9282
0.0	45.0	33795	0.9002	0.9249
0.0007	46.0	34546	0.9147	0.9199
0.0	47.0	35297	0.8904	0.9249
0.0	48.0	36048	0.8842	0.9282
0.0	49.0	36799	0.8899	0.9265
0.0	50.0	37550	0.8887	0.9282

Framework versions

Transformers 4.32.1
Pytorch 2.1.0+cu121
Datasets 2.12.0
Tokenizers 0.13.2