README.md

metadata

license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: meat_calssify_fresh_crop_fixed_overlap_V_0_2
    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: 0.9050632911392406

meat_calssify_fresh_crop_fixed_overlap_V_0_2

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: 0.3158
• Accuracy: 0.9051

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: 1
• 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
1.0836	1.0	20	1.0836	0.3892
1.0325	2.0	40	1.0308	0.5032
0.9331	3.0	60	0.9478	0.5506
0.8711	4.0	80	0.9827	0.5380
0.8252	5.0	100	0.9171	0.5665
0.7597	6.0	120	0.8175	0.6234
0.6528	7.0	140	0.7884	0.6835
0.5646	8.0	160	0.7034	0.7025
0.5026	9.0	180	0.6805	0.7025
0.4534	10.0	200	0.6223	0.7690
0.4244	11.0	220	0.6262	0.7405
0.4077	12.0	240	0.6230	0.7595
0.3962	13.0	260	0.6731	0.7184
0.3587	14.0	280	0.5633	0.7911
0.316	15.0	300	0.5808	0.7848
0.2472	16.0	320	0.5478	0.7943
0.277	17.0	340	0.5609	0.8038
0.2586	18.0	360	0.5427	0.8133
0.2405	19.0	380	0.5207	0.8165
0.2141	20.0	400	0.4552	0.8323
0.2052	21.0	420	0.5201	0.8006
0.2182	22.0	440	0.3928	0.8544
0.1698	23.0	460	0.4459	0.8449
0.1618	24.0	480	0.4502	0.8323
0.1915	25.0	500	0.4057	0.8703
0.1596	26.0	520	0.4650	0.8386
0.1446	27.0	540	0.3713	0.8766
0.17	28.0	560	0.4394	0.8544
0.141	29.0	580	0.5494	0.8196
0.1563	30.0	600	0.5431	0.8196
0.1216	31.0	620	0.5010	0.8481
0.1081	32.0	640	0.4454	0.8608
0.1205	33.0	660	0.4664	0.8418
0.1325	34.0	680	0.4690	0.8481
0.1152	35.0	700	0.3433	0.9019
0.1218	36.0	720	0.4063	0.8671
0.1163	37.0	740	0.3552	0.8861
0.0976	38.0	760	0.4137	0.8734
0.1163	39.0	780	0.4193	0.8797
0.1034	40.0	800	0.3740	0.8892
0.1033	41.0	820	0.4036	0.8671
0.0806	42.0	840	0.4396	0.8639
0.0764	43.0	860	0.4137	0.8608
0.0955	44.0	880	0.4019	0.8734
0.0768	45.0	900	0.3778	0.8829
0.0824	46.0	920	0.3930	0.8829
0.0837	47.0	940	0.3524	0.8924
0.0817	48.0	960	0.3113	0.9177
0.0767	49.0	980	0.3881	0.8797
0.0769	50.0	1000	0.3158	0.9051

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0
• Datasets 2.19.2
• Tokenizers 0.19.1