README.md

metadata

license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: smids_3x_deit_base_sgd_001_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: 0.870216306156406

smids_3x_deit_base_sgd_001_fold2

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

• Loss: 0.3164
• Accuracy: 0.8702

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
0.9356	1.0	225	0.9551	0.6140
0.7266	2.0	450	0.7486	0.7288
0.5616	3.0	675	0.6080	0.7704
0.547	4.0	900	0.5262	0.7937
0.4582	5.0	1125	0.4769	0.7987
0.3947	6.0	1350	0.4429	0.8103
0.3972	7.0	1575	0.4203	0.8270
0.3767	8.0	1800	0.4042	0.8286
0.3401	9.0	2025	0.3910	0.8369
0.3023	10.0	2250	0.3806	0.8419
0.3373	11.0	2475	0.3718	0.8436
0.2966	12.0	2700	0.3663	0.8502
0.2871	13.0	2925	0.3599	0.8502
0.2823	14.0	3150	0.3565	0.8502
0.3247	15.0	3375	0.3500	0.8486
0.3466	16.0	3600	0.3478	0.8486
0.2808	17.0	3825	0.3471	0.8486
0.2148	18.0	4050	0.3407	0.8469
0.245	19.0	4275	0.3382	0.8502
0.2737	20.0	4500	0.3376	0.8486
0.2877	21.0	4725	0.3336	0.8486
0.3056	22.0	4950	0.3302	0.8502
0.3242	23.0	5175	0.3293	0.8519
0.2649	24.0	5400	0.3291	0.8536
0.2721	25.0	5625	0.3296	0.8519
0.2345	26.0	5850	0.3266	0.8519
0.2272	27.0	6075	0.3224	0.8586
0.2367	28.0	6300	0.3218	0.8569
0.2688	29.0	6525	0.3231	0.8552
0.2737	30.0	6750	0.3223	0.8569
0.2277	31.0	6975	0.3231	0.8602
0.2491	32.0	7200	0.3225	0.8602
0.2511	33.0	7425	0.3193	0.8602
0.2122	34.0	7650	0.3202	0.8569
0.2292	35.0	7875	0.3193	0.8602
0.243	36.0	8100	0.3185	0.8619
0.2358	37.0	8325	0.3187	0.8652
0.2127	38.0	8550	0.3178	0.8669
0.2259	39.0	8775	0.3182	0.8686
0.2023	40.0	9000	0.3176	0.8686
0.194	41.0	9225	0.3177	0.8686
0.2145	42.0	9450	0.3163	0.8669
0.188	43.0	9675	0.3174	0.8686
0.2222	44.0	9900	0.3170	0.8686
0.2664	45.0	10125	0.3165	0.8652
0.2195	46.0	10350	0.3166	0.8686
0.2046	47.0	10575	0.3165	0.8686
0.1994	48.0	10800	0.3164	0.8669
0.2327	49.0	11025	0.3164	0.8702
0.1935	50.0	11250	0.3164	0.8702

Framework versions

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