End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: google/vit-base-patch16-224
+base_model: Lalith47/custom-cloud-model
 tags:
 - generated_from_trainer
 datasets:
@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8415637612342834
+      value: 0.9320987462997437
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # custom-cloud-model
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
+This model is a fine-tuned version of [Lalith47/custom-cloud-model](https://huggingface.co/Lalith47/custom-cloud-model) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5912
-- Accuracy: 0.8416
+- Loss: 0.3020
+- Accuracy: 0.9321
 
 ## Model description
 
@@ -53,7 +53,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -62,20 +62,68 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3
+- num_epochs: 50
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 8    | 1.1553          | 0.5926   |
-| 1.5306        | 2.0   | 16   | 0.6816          | 0.8128   |
-| 0.7025        | 3.0   | 24   | 0.5912          | 0.8416   |
+| No log        | 1.0   | 8    | 0.3390          | 0.9198   |
+| 0.0216        | 2.0   | 16   | 0.2984          | 0.9218   |
+| 0.013         | 3.0   | 24   | 0.3312          | 0.9115   |
+| 0.0064        | 4.0   | 32   | 0.2721          | 0.9218   |
+| 0.0078        | 5.0   | 40   | 0.4045          | 0.9053   |
+| 0.0078        | 6.0   | 48   | 0.3621          | 0.9074   |
+| 0.008         | 7.0   | 56   | 0.4359          | 0.8971   |
+| 0.0159        | 8.0   | 64   | 0.2895          | 0.9136   |
+| 0.0146        | 9.0   | 72   | 0.3281          | 0.9239   |
+| 0.0085        | 10.0  | 80   | 0.2521          | 0.9342   |
+| 0.0085        | 11.0  | 88   | 0.3220          | 0.9239   |
+| 0.0245        | 12.0  | 96   | 0.3519          | 0.9300   |
+| 0.0233        | 13.0  | 104  | 0.2775          | 0.9383   |
+| 0.0139        | 14.0  | 112  | 0.3821          | 0.9136   |
+| 0.0029        | 15.0  | 120  | 0.3485          | 0.9300   |
+| 0.0029        | 16.0  | 128  | 0.3152          | 0.9280   |
+| 0.0069        | 17.0  | 136  | 0.3738          | 0.9156   |
+| 0.0139        | 18.0  | 144  | 0.3162          | 0.9259   |
+| 0.0118        | 19.0  | 152  | 0.3019          | 0.9321   |
+| 0.0083        | 20.0  | 160  | 0.3667          | 0.9259   |
+| 0.0083        | 21.0  | 168  | 0.3780          | 0.9280   |
+| 0.0027        | 22.0  | 176  | 0.3745          | 0.9177   |
+| 0.0046        | 23.0  | 184  | 0.3194          | 0.9177   |
+| 0.0027        | 24.0  | 192  | 0.3407          | 0.9280   |
+| 0.0075        | 25.0  | 200  | 0.2790          | 0.9444   |
+| 0.0075        | 26.0  | 208  | 0.3145          | 0.9259   |
+| 0.0104        | 27.0  | 216  | 0.3710          | 0.9362   |
+| 0.0034        | 28.0  | 224  | 0.3193          | 0.9300   |
+| 0.0078        | 29.0  | 232  | 0.2847          | 0.9362   |
+| 0.0168        | 30.0  | 240  | 0.3794          | 0.9280   |
+| 0.0168        | 31.0  | 248  | 0.3004          | 0.9362   |
+| 0.0311        | 32.0  | 256  | 0.3145          | 0.9403   |
+| 0.008         | 33.0  | 264  | 0.3280          | 0.9239   |
+| 0.0372        | 34.0  | 272  | 0.3942          | 0.9239   |
+| 0.0053        | 35.0  | 280  | 0.2987          | 0.9362   |
+| 0.0053        | 36.0  | 288  | 0.2894          | 0.9321   |
+| 0.0346        | 37.0  | 296  | 0.2983          | 0.9362   |
+| 0.0017        | 38.0  | 304  | 0.3405          | 0.9198   |
+| 0.0439        | 39.0  | 312  | 0.3143          | 0.9280   |
+| 0.0356        | 40.0  | 320  | 0.3170          | 0.9198   |
+| 0.0356        | 41.0  | 328  | 0.2854          | 0.9321   |
+| 0.0293        | 42.0  | 336  | 0.3164          | 0.9239   |
+| 0.0193        | 43.0  | 344  | 0.2730          | 0.9506   |
+| 0.0062        | 44.0  | 352  | 0.2789          | 0.9383   |
+| 0.012         | 45.0  | 360  | 0.3509          | 0.9156   |
+| 0.012         | 46.0  | 368  | 0.3115          | 0.9424   |
+| 0.0071        | 47.0  | 376  | 0.2921          | 0.9259   |
+| 0.0296        | 48.0  | 384  | 0.3333          | 0.9362   |
+| 0.0112        | 49.0  | 392  | 0.2881          | 0.9321   |
+| 0.0333        | 50.0  | 400  | 0.3020          | 0.9321   |
 
 
 ### Framework versions
 
 - Transformers 4.57.1
-- Pytorch 2.8.0+cu126
+- Pytorch 2.9.0+cu126
 - Datasets 4.0.0
 - Tokenizers 0.22.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71c74f261d85b3ee6300acf3b59777a8b726fcd702641cb49788291d74591d48
+oid sha256:bb70d880608ce59ba32209619a66cee4a229c94686285e1a099fd5f8cad0acb0
 size 343239356