End of training

README.md

@@ -0,0 +1,125 @@
+---
+license: apache-2.0
+base_model: facebook/deit-tiny-patch16-224
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: hushem_1x_deit_tiny_adamax_001_fold1
+  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: 0.4
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# hushem_1x_deit_tiny_adamax_001_fold1
+
+This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.8178
+- Accuracy: 0.4
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 6    | 1.6382          | 0.2444   |
+| 2.1568        | 2.0   | 12   | 1.3466          | 0.3111   |
+| 2.1568        | 3.0   | 18   | 1.4826          | 0.3333   |
+| 1.204         | 4.0   | 24   | 1.8194          | 0.3778   |
+| 0.8919        | 5.0   | 30   | 1.8241          | 0.4      |
+| 0.8919        | 6.0   | 36   | 2.0897          | 0.4222   |
+| 0.5779        | 7.0   | 42   | 1.2520          | 0.5111   |
+| 0.5779        | 8.0   | 48   | 1.1793          | 0.5333   |
+| 0.6575        | 9.0   | 54   | 1.7606          | 0.4222   |
+| 0.5042        | 10.0  | 60   | 2.4732          | 0.3778   |
+| 0.5042        | 11.0  | 66   | 1.6162          | 0.3778   |
+| 0.4425        | 12.0  | 72   | 1.9786          | 0.3778   |
+| 0.4425        | 13.0  | 78   | 3.2416          | 0.3556   |
+| 0.376         | 14.0  | 84   | 2.0876          | 0.3778   |
+| 0.2172        | 15.0  | 90   | 3.6129          | 0.5111   |
+| 0.2172        | 16.0  | 96   | 5.8826          | 0.3556   |
+| 0.3867        | 17.0  | 102  | 1.7748          | 0.5111   |
+| 0.3867        | 18.0  | 108  | 4.3640          | 0.4      |
+| 0.118         | 19.0  | 114  | 3.4995          | 0.4      |
+| 0.0493        | 20.0  | 120  | 3.8698          | 0.4444   |
+| 0.0493        | 21.0  | 126  | 3.6078          | 0.4889   |
+| 0.0212        | 22.0  | 132  | 5.2731          | 0.4      |
+| 0.0212        | 23.0  | 138  | 4.8918          | 0.4222   |
+| 0.003         | 24.0  | 144  | 5.3873          | 0.4444   |
+| 0.0004        | 25.0  | 150  | 5.6456          | 0.4      |
+| 0.0004        | 26.0  | 156  | 5.7626          | 0.4      |
+| 0.0001        | 27.0  | 162  | 5.8114          | 0.4      |
+| 0.0001        | 28.0  | 168  | 5.8330          | 0.3778   |
+| 0.0001        | 29.0  | 174  | 5.8388          | 0.3778   |
+| 0.0001        | 30.0  | 180  | 5.8388          | 0.3778   |
+| 0.0001        | 31.0  | 186  | 5.8374          | 0.4      |
+| 0.0001        | 32.0  | 192  | 5.8320          | 0.4      |
+| 0.0001        | 33.0  | 198  | 5.8279          | 0.4      |
+| 0.0001        | 34.0  | 204  | 5.8253          | 0.4      |
+| 0.0001        | 35.0  | 210  | 5.8210          | 0.4      |
+| 0.0001        | 36.0  | 216  | 5.8195          | 0.4      |
+| 0.0001        | 37.0  | 222  | 5.8189          | 0.4      |
+| 0.0001        | 38.0  | 228  | 5.8188          | 0.4      |
+| 0.0001        | 39.0  | 234  | 5.8188          | 0.4      |
+| 0.0001        | 40.0  | 240  | 5.8180          | 0.4      |
+| 0.0001        | 41.0  | 246  | 5.8178          | 0.4      |
+| 0.0001        | 42.0  | 252  | 5.8178          | 0.4      |
+| 0.0001        | 43.0  | 258  | 5.8178          | 0.4      |
+| 0.0001        | 44.0  | 264  | 5.8178          | 0.4      |
+| 0.0001        | 45.0  | 270  | 5.8178          | 0.4      |
+| 0.0001        | 46.0  | 276  | 5.8178          | 0.4      |
+| 0.0001        | 47.0  | 282  | 5.8178          | 0.4      |
+| 0.0001        | 48.0  | 288  | 5.8178          | 0.4      |
+| 0.0001        | 49.0  | 294  | 5.8178          | 0.4      |
+| 0.0001        | 50.0  | 300  | 5.8178          | 0.4      |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152d0191c1d023c6eee6a4e43d5c059a61ea7d796295d3179fb06eda1f7f1dc6
+oid sha256:6fd627b84362d02391354cc3b6b97500a27e1f2192733c022e3b2f78fa5263e7
 size 22123464