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_5x_beit_base_rms_0001_fold2
    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: 0.9068219633943427

smids_5x_beit_base_rms_0001_fold2

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: 0.9869
• Accuracy: 0.9068

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: 0.0001
• 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
0.3386	1.0	375	0.2631	0.8902
0.2769	2.0	750	0.2812	0.8852
0.1948	3.0	1125	0.4161	0.8686
0.1489	4.0	1500	0.3316	0.8852
0.1015	5.0	1875	0.3966	0.8835
0.0659	6.0	2250	0.5521	0.8686
0.0987	7.0	2625	0.4706	0.8852
0.0304	8.0	3000	0.6100	0.8835
0.0177	9.0	3375	0.5599	0.8835
0.0365	10.0	3750	0.5970	0.8902
0.07	11.0	4125	0.5587	0.8869
0.025	12.0	4500	0.6283	0.8885
0.013	13.0	4875	0.4540	0.9035
0.0155	14.0	5250	0.6593	0.8869
0.0612	15.0	5625	0.6571	0.8935
0.0058	16.0	6000	0.6333	0.8835
0.0564	17.0	6375	0.5490	0.8918
0.0204	18.0	6750	0.7225	0.8985
0.0128	19.0	7125	0.4844	0.9135
0.0241	20.0	7500	0.5085	0.9018
0.0042	21.0	7875	0.5500	0.9135
0.0209	22.0	8250	0.6987	0.8869
0.0277	23.0	8625	0.7227	0.8902
0.027	24.0	9000	0.8023	0.8769
0.0061	25.0	9375	0.7219	0.8985
0.0004	26.0	9750	0.7303	0.8935
0.0002	27.0	10125	0.6194	0.9118
0.0002	28.0	10500	0.7358	0.9085
0.0068	29.0	10875	0.7598	0.9002
0.0002	30.0	11250	0.7703	0.8935
0.0136	31.0	11625	0.7951	0.8902
0.0053	32.0	12000	0.8891	0.8918
0.0038	33.0	12375	0.7625	0.9018
0.0002	34.0	12750	0.8776	0.9052
0.0	35.0	13125	0.9210	0.9002
0.0195	36.0	13500	0.7510	0.9151
0.0008	37.0	13875	0.7794	0.9135
0.0007	38.0	14250	0.8315	0.9085
0.0005	39.0	14625	0.7854	0.9151
0.0033	40.0	15000	0.8459	0.9101
0.0001	41.0	15375	0.9023	0.9002
0.0027	42.0	15750	1.0108	0.9018
0.0026	43.0	16125	1.0264	0.8952
0.0026	44.0	16500	0.9790	0.9035
0.0027	45.0	16875	0.9445	0.9101
0.0	46.0	17250	0.9135	0.9185
0.0057	47.0	17625	0.9222	0.9085
0.0	48.0	18000	0.9390	0.9085
0.0052	49.0	18375	0.9876	0.9052
0.0025	50.0	18750	0.9869	0.9068

Framework versions

• Transformers 4.32.1
• Pytorch 2.1.0+cu121
• Datasets 2.12.0
• Tokenizers 0.13.2