README.md

metadata

license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_1x_beit_base_rms_0001_fold4
    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: 0.7333333333333333

smids_1x_beit_base_rms_0001_fold4

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

• Loss: 0.6670
• Accuracy: 0.7333

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: 0.001
• 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
1.1121	1.0	75	1.0797	0.495
1.1167	2.0	150	1.0990	0.3383
1.1124	3.0	225	1.0945	0.3583
1.0914	4.0	300	1.0750	0.35
1.0647	5.0	375	0.8667	0.5733
0.9583	6.0	450	0.8905	0.51
0.8629	7.0	525	0.7806	0.5767
0.8438	8.0	600	0.7603	0.5833
0.812	9.0	675	0.7613	0.595
0.7427	10.0	750	0.8115	0.5917
0.8147	11.0	825	0.7428	0.63
0.7859	12.0	900	0.7365	0.635
0.8142	13.0	975	0.7468	0.6033
0.7961	14.0	1050	0.7567	0.5983
0.6725	15.0	1125	0.7876	0.6067
0.7608	16.0	1200	0.7339	0.635
0.7146	17.0	1275	0.7178	0.645
0.6646	18.0	1350	0.7089	0.67
0.7767	19.0	1425	0.7436	0.6433
0.7149	20.0	1500	0.7664	0.655
0.7622	21.0	1575	0.7227	0.6617
0.6643	22.0	1650	0.7547	0.64
0.7546	23.0	1725	0.7439	0.6483
0.727	24.0	1800	0.7101	0.6633
0.7334	25.0	1875	0.7022	0.6583
0.6824	26.0	1950	0.7040	0.6767
0.7383	27.0	2025	0.6953	0.6733
0.6459	28.0	2100	0.6860	0.6883
0.7094	29.0	2175	0.6882	0.695
0.7817	30.0	2250	0.6855	0.6883
0.6417	31.0	2325	0.6762	0.705
0.7236	32.0	2400	0.6870	0.6917
0.6676	33.0	2475	0.7290	0.685
0.5839	34.0	2550	0.6648	0.7117
0.6323	35.0	2625	0.6543	0.7017
0.6129	36.0	2700	0.6910	0.6883
0.5785	37.0	2775	0.6666	0.7217
0.6055	38.0	2850	0.6452	0.7233
0.5778	39.0	2925	0.6586	0.7217
0.5892	40.0	3000	0.6725	0.7233
0.6346	41.0	3075	0.6632	0.715
0.5806	42.0	3150	0.6697	0.7217
0.6328	43.0	3225	0.6659	0.7117
0.5711	44.0	3300	0.6651	0.71
0.5685	45.0	3375	0.6727	0.7283
0.4903	46.0	3450	0.6607	0.7383
0.5197	47.0	3525	0.6770	0.7283
0.5572	48.0	3600	0.6616	0.7183
0.5197	49.0	3675	0.6636	0.73
0.489	50.0	3750	0.6670	0.7333

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0