README.md

metadata

library_name: transformers
license: apache-2.0
base_model: Melo1512/vit-msn-small-lateral_flow_ivalidation_train_test_6
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: vit-msn-small-lateral_flow_ivalidation_train_test_7
    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: 0.8754578754578755

vit-msn-small-lateral_flow_ivalidation_train_test_7

This model is a fine-tuned version of Melo1512/vit-msn-small-lateral_flow_ivalidation_train_test_6 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.4368
• Accuracy: 0.8755

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-07
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: reduce_lr_on_plateau
• lr_scheduler_warmup_ratio: 0.5
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.6154	1	0.4368	0.8755
No log	1.8462	3	0.4440	0.8681
No log	2.4615	4	0.4470	0.8645
No log	3.6923	6	0.4443	0.8645
No log	4.9231	8	0.4393	0.8645
No log	5.5385	9	0.4372	0.8681
0.3118	6.7692	11	0.4340	0.8645
0.3118	8.0	13	0.4319	0.8608
0.3118	8.6154	14	0.4313	0.8608
0.3118	9.8462	16	0.4312	0.8681
0.3118	10.4615	17	0.4314	0.8718
0.3118	11.6923	19	0.4306	0.8718
0.3019	12.9231	21	0.4294	0.8718
0.3019	13.5385	22	0.4290	0.8718
0.3019	14.7692	24	0.4262	0.8718
0.3019	16.0	26	0.4223	0.8718
0.3019	16.6154	27	0.4204	0.8718
0.3019	17.8462	29	0.4170	0.8718
0.2922	18.4615	30	0.4160	0.8718
0.2922	19.6923	32	0.4161	0.8718
0.2922	20.9231	34	0.4161	0.8718
0.2922	21.5385	35	0.4162	0.8718
0.2922	22.7692	37	0.4164	0.8718
0.2922	24.0	39	0.4166	0.8718
0.2993	24.6154	40	0.4168	0.8718
0.2993	25.8462	42	0.4170	0.8718
0.2993	26.4615	43	0.4171	0.8718
0.2993	27.6923	45	0.4176	0.8718
0.2993	28.9231	47	0.4179	0.8718
0.2993	29.5385	48	0.4179	0.8718
0.298	30.7692	50	0.4179	0.8718
0.298	32.0	52	0.4179	0.8718
0.298	32.6154	53	0.4179	0.8718
0.298	33.8462	55	0.4179	0.8718
0.298	34.4615	56	0.4179	0.8718
0.298	35.6923	58	0.4179	0.8718
0.2936	36.9231	60	0.4178	0.8718
0.2936	37.5385	61	0.4178	0.8718
0.2936	38.7692	63	0.4178	0.8718
0.2936	40.0	65	0.4178	0.8718
0.2936	40.6154	66	0.4178	0.8718
0.2936	41.8462	68	0.4178	0.8718
0.2936	42.4615	69	0.4177	0.8718
0.2948	43.6923	71	0.4177	0.8718
0.2948	44.9231	73	0.4177	0.8718
0.2948	45.5385	74	0.4176	0.8718
0.2948	46.7692	76	0.4176	0.8718
0.2948	48.0	78	0.4176	0.8718
0.2948	48.6154	79	0.4176	0.8718
0.2965	49.8462	81	0.4176	0.8718
0.2965	50.4615	82	0.4175	0.8718
0.2965	51.6923	84	0.4175	0.8718
0.2965	52.9231	86	0.4175	0.8718
0.2965	53.5385	87	0.4175	0.8718
0.2965	54.7692	89	0.4174	0.8718
0.292	56.0	91	0.4174	0.8718
0.292	56.6154	92	0.4174	0.8718
0.292	57.8462	94	0.4174	0.8718
0.292	58.4615	95	0.4173	0.8718
0.292	59.6923	97	0.4173	0.8718
0.292	60.9231	99	0.4173	0.8718
0.2962	61.5385	100	0.4173	0.8718

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1