Model save

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8011152416356877
+      value: 0.8494423791821561
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.5222
-- Accuracy: 0.8011
+- Loss: 0.3989
+- Accuracy: 0.8494
 
 ## Model description
 
@@ -53,8 +53,8 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 2
+- learning_rate: 5e-05
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -64,18 +64,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.717         | 1.0   | 1522  | 0.8198          | 0.5186   |
-| 0.7935        | 2.0   | 3044  | 0.6689          | 0.6989   |
-| 0.7885        | 3.0   | 4566  | 0.5983          | 0.7082   |
-| 0.7315        | 4.0   | 6088  | 0.6050          | 0.7398   |
-| 0.7526        | 5.0   | 7610  | 0.6488          | 0.7454   |
-| 0.7844        | 6.0   | 9132  | 0.6292          | 0.7584   |
-| 0.8785        | 7.0   | 10654 | 0.5291          | 0.7900   |
-| 0.529         | 8.0   | 12176 | 0.4577          | 0.8160   |
-| 0.9946        | 9.0   | 13698 | 0.4851          | 0.8160   |
-| 0.7006        | 10.0  | 15220 | 0.5222          | 0.8011   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.5083        | 1.0   | 761  | 0.4226          | 0.8234   |
+| 0.5171        | 2.0   | 1522 | 0.4868          | 0.7825   |
+| 0.5042        | 3.0   | 2283 | 0.4948          | 0.7862   |
+| 0.282         | 4.0   | 3044 | 0.4702          | 0.8067   |
+| 0.8396        | 5.0   | 3805 | 0.4037          | 0.8290   |
+| 0.2213        | 6.0   | 4566 | 0.5371          | 0.7918   |
+| 0.636         | 7.0   | 5327 | 0.4830          | 0.8234   |
+| 0.5217        | 8.0   | 6088 | 0.3411          | 0.8829   |
+| 0.3796        | 9.0   | 6849 | 0.3674          | 0.8680   |
+| 0.286         | 10.0  | 7610 | 0.3989          | 0.8494   |
 
 
 ### Framework versions

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 4.547751389590703,
-    "eval_accuracy": 0.8986752595775153,
-    "eval_loss": 0.23256993293762207,
-    "eval_runtime": 23.3593,
-    "eval_samples_per_second": 119.567,
-    "eval_steps_per_second": 14.983,
-    "total_flos": 5.577253476541415e+18,
-    "train_loss": 0.37995564444859825,
-    "train_runtime": 4981.1969,
-    "train_samples_per_second": 14.454,
-    "train_steps_per_second": 1.807
+    "epoch": 10.0,
+    "eval_accuracy": 0.8159851301115242,
+    "eval_loss": 0.4577201008796692,
+    "eval_runtime": 39.5349,
+    "eval_samples_per_second": 13.608,
+    "eval_steps_per_second": 1.72,
+    "total_flos": 2.3588561638681805e+18,
+    "train_loss": 0.6660665354183563,
+    "train_runtime": 3972.9927,
+    "train_samples_per_second": 7.662,
+    "train_steps_per_second": 3.831
 }

config.json

@@ -8,17 +8,9 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
-  "id2label": {
-    "0": 0,
-    "1": 1
-  },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "0": "0",
-    "1": "1"
-  },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",
   "num_attention_heads": 12,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.547751389590703,
-    "eval_accuracy": 0.8986752595775153,
-    "eval_loss": 0.23256993293762207,
-    "eval_runtime": 23.3593,
-    "eval_samples_per_second": 119.567,
-    "eval_steps_per_second": 14.983
+    "epoch": 10.0,
+    "eval_accuracy": 0.8159851301115242,
+    "eval_loss": 0.4577201008796692,
+    "eval_runtime": 39.5349,
+    "eval_samples_per_second": 13.608,
+    "eval_steps_per_second": 1.72
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f96ad6896ae934f3ebc65ef27bc7bc9170fa060f905eeba7398b34f6cfa6737
+oid sha256:e085bd41d3ced724160e4e6a831b38b59e2ceaa9fd4174c2be4c780e18fd9fa0
 size 343223968

runs/Oct02_14-40-06_dcbb13f74eeb/events.out.tfevents.1727884063.dcbb13f74eeb.1604.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0862fb5b9dad3e54293e69d2115044873ceccc7fa5a31412cda832fde852f45
+size 411

runs/Oct02_15-48-20_dcbb13f74eeb/events.out.tfevents.1727884113.dcbb13f74eeb.1604.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4461684f37c01f570caf4685930105807c86449829d8cc62ab2782bb0bea48fb
+size 168890

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.547751389590703,
-    "total_flos": 5.577253476541415e+18,
-    "train_loss": 0.37995564444859825,
-    "train_runtime": 4981.1969,
-    "train_samples_per_second": 14.454,
-    "train_steps_per_second": 1.807
+    "epoch": 10.0,
+    "total_flos": 2.3588561638681805e+18,
+    "train_loss": 0.6660665354183563,
+    "train_runtime": 3972.9927,
+    "train_samples_per_second": 7.662,
+    "train_steps_per_second": 3.831
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abeb52e96ac7f76ce392655f864ffc8d4f25020703f19d61bcd76e5c61524d99
+oid sha256:b02f5ba5c3d83c0ad50c77c85ef3a05cbfe37dda066133605acd4a4a5bd9d34b
 size 5176