metadata

library_name: transformers
license: apache-2.0
base_model: microsoft/resnet-18
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: resnet-18-finetuned-papsmear
    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: 0.9117647058823529

resnet-18-finetuned-papsmear

This model is a fine-tuned version of microsoft/resnet-18 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.2838
Accuracy: 0.9118

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: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
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
No log	0.9231	9	1.9256	0.1691
1.9692	1.9487	19	1.6557	0.2868
1.7979	2.9744	29	1.3300	0.5368
1.5079	4.0	39	1.0482	0.6324
1.217	4.9231	48	0.9019	0.6618
0.9536	5.9487	58	0.7687	0.6691
0.7881	6.9744	68	0.6150	0.7721
0.68	8.0	78	0.5481	0.7868
0.5678	8.9231	87	0.5341	0.7868
0.5169	9.9487	97	0.4800	0.7941
0.4838	10.9744	107	0.4356	0.8235
0.4738	12.0	117	0.4573	0.8162
0.3798	12.9231	126	0.4263	0.8088
0.3431	13.9487	136	0.4159	0.8382
0.3282	14.9744	146	0.3787	0.8603
0.3167	16.0	156	0.4234	0.8382
0.3186	16.9231	165	0.3853	0.8235
0.2568	17.9487	175	0.3904	0.8456
0.2528	18.9744	185	0.4013	0.8309
0.2661	20.0	195	0.3275	0.8824
0.2287	20.9231	204	0.3219	0.8824
0.2465	21.9487	214	0.3410	0.8529
0.2422	22.9744	224	0.3256	0.8603
0.222	24.0	234	0.3232	0.875
0.1917	24.9231	243	0.3307	0.8676
0.194	25.9487	253	0.3146	0.8971
0.212	26.9744	263	0.3125	0.8897
0.1718	28.0	273	0.3015	0.9044
0.1975	28.9231	282	0.3195	0.8824
0.1948	29.9487	292	0.3536	0.8971
0.1809	30.9744	302	0.3105	0.875
0.1744	32.0	312	0.3032	0.8824
0.1731	32.9231	321	0.2936	0.8971
0.1513	33.9487	331	0.2889	0.8824
0.1527	34.9744	341	0.2875	0.8897
0.1693	36.0	351	0.2754	0.8897
0.1743	36.9231	360	0.2875	0.8971
0.1463	37.9487	370	0.2961	0.8971
0.1429	38.9744	380	0.2848	0.8971
0.1483	40.0	390	0.2873	0.8897
0.1483	40.9231	399	0.2856	0.875
0.1613	41.9487	409	0.2801	0.8971
0.1358	42.9744	419	0.2838	0.9118
0.1453	44.0	429	0.2783	0.8971
0.1383	44.9231	438	0.2897	0.8897
0.1655	45.9487	448	0.2847	0.9044
0.1489	46.1538	450	0.2861	0.8897

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1