Model save

README.md

@@ -0,0 +1,95 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: vit-weldclassifyv2
+  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: 0.8561151079136691
+---
+
+<!-- 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. -->
+
+# vit-weldclassifyv2
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6228
+- Accuracy: 0.8561
+
+## 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 13
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|
+| 1.035         | 0.6410  | 100  | 1.1332          | 0.4029   |
+| 0.6893        | 1.2821  | 200  | 0.7341          | 0.6655   |
+| 0.5618        | 1.9231  | 300  | 0.5596          | 0.7554   |
+| 0.4344        | 2.5641  | 400  | 0.5951          | 0.7770   |
+| 0.1591        | 3.2051  | 500  | 0.4667          | 0.8453   |
+| 0.1821        | 3.8462  | 600  | 0.5082          | 0.8345   |
+| 0.0811        | 4.4872  | 700  | 0.4613          | 0.8633   |
+| 0.1729        | 5.1282  | 800  | 0.6382          | 0.7986   |
+| 0.1174        | 5.7692  | 900  | 0.4974          | 0.8669   |
+| 0.0389        | 6.4103  | 1000 | 0.6049          | 0.8453   |
+| 0.0099        | 7.0513  | 1100 | 0.6147          | 0.8561   |
+| 0.0342        | 7.6923  | 1200 | 0.5603          | 0.8741   |
+| 0.0175        | 8.3333  | 1300 | 0.5679          | 0.8849   |
+| 0.0177        | 8.9744  | 1400 | 0.6592          | 0.8669   |
+| 0.0025        | 9.6154  | 1500 | 0.6000          | 0.8669   |
+| 0.0021        | 10.2564 | 1600 | 0.6060          | 0.8597   |
+| 0.002         | 10.8974 | 1700 | 0.6113          | 0.8597   |
+| 0.0019        | 11.5385 | 1800 | 0.6178          | 0.8561   |
+| 0.0019        | 12.1795 | 1900 | 0.6214          | 0.8561   |
+| 0.002         | 12.8205 | 2000 | 0.6228          | 0.8561   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3cfb7b51b8675632d0d81aa8f3a189c112dd054c0260d0f790cfeadb55e8e3
+oid sha256:42ac608101ac6878963568ed604c414fcb89ad7bc6071a28682d60dbc69932d4
 size 343230128

runs/Jun18_09-18-24_0d141cb2c9f1/events.out.tfevents.1718702311.0d141cb2c9f1.868.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc8a5af5d03f9544720b6ee4ff6f135e5a73f716505ff478c30f5364cea48493
-size 53444
+oid sha256:82e4d5a7a5987c3a1fad2528aa784ea29fe9ebd6fa7a02046a518f6afcb123ec
+size 54220