End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.50625
+      value: 0.475
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 1.2501
-- Accuracy: 0.5062
+- Loss: 1.4479
+- Accuracy: 0.475
 
 ## Model description
 
@@ -52,26 +52,34 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 8e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 10
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 40   | 1.5126          | 0.4562   |
-| No log        | 2.0   | 80   | 1.3084          | 0.4875   |
-| No log        | 3.0   | 120  | 1.2501          | 0.5062   |
+| No log        | 1.0   | 80   | 1.7877          | 0.3      |
+| No log        | 2.0   | 160  | 1.5989          | 0.4062   |
+| No log        | 3.0   | 240  | 1.4993          | 0.4313   |
+| No log        | 4.0   | 320  | 1.4446          | 0.4437   |
+| No log        | 5.0   | 400  | 1.4479          | 0.475    |
+| No log        | 6.0   | 480  | 1.4549          | 0.4437   |
+| 0.6433        | 7.0   | 560  | 1.4635          | 0.45     |
+| 0.6433        | 8.0   | 640  | 1.4767          | 0.4562   |
+| 0.6433        | 9.0   | 720  | 1.4850          | 0.4437   |
+| 0.6433        | 10.0  | 800  | 1.4864          | 0.4437   |
 
 
 ### Framework versions
 
-- Transformers 4.41.1
+- Transformers 4.41.2
 - Pytorch 2.3.0+cu121
-- Datasets 2.19.1
+- Datasets 2.19.2
 - Tokenizers 0.19.1

config.json

@@ -40,5 +40,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.1"
+  "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb070f1b7c595ce353ed495906d5e5efe406bbc826715cf079b4adc694ae4afa
+oid sha256:bddf0a94d3829c0a01c1b071daecd95f5f0f4582a9ecdaa811ba6c64819e3234
 size 343242432

runs/Jun03_10-25-30_3641319fd633/events.out.tfevents.1717410330.3641319fd633.2377.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc5da59352b763d6fbc5fdf241792aeeb89f9017c03b5ef4f9a0dcef0025dad
+size 4184

runs/Jun03_10-28-06_3641319fd633/events.out.tfevents.1717410487.3641319fd633.3280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c876127580364cb439747b9fa497bad8a14065126edb1389228aa45b89a165a
+size 5050

runs/Jun03_10-30-13_3641319fd633/events.out.tfevents.1717410614.3641319fd633.3280.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b26cd67c7dab26ab8b7d0d0506d62828d3eeb88fbd9b0a6ed4825eed8c7417
+size 8838

runs/Jun03_10-30-13_3641319fd633/events.out.tfevents.1717411710.3641319fd633.3280.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4570fe7cafa11efdae4c79055d540b4321063e9b696cbebc5f9ed23ed966ea
+size 411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9ecf00052d21e8b30b55c96f4587b2d721a5fea2a6752399e8416145b34cdf
+oid sha256:da82561673b9ce0173a76b396c0f9c502bbfbcbe3c721c3126439700cf4734a3
 size 5112