Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/vit-large-patch16-224",
+  "_name_or_path": "google/vit-base-patch16-224",
   "architectures": [
     "ViTForImageClassification"
   ],
@@ -7,7 +7,7 @@
   "encoder_stride": 16,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "n01443537",
     "1": "n01629819",
@@ -212,7 +212,7 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "n01443537": 0,
     "n01629819": 1,
@@ -417,9 +417,9 @@
   },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",
-  "num_attention_heads": 16,
+  "num_attention_heads": 12,
   "num_channels": 3,
-  "num_hidden_layers": 24,
+  "num_hidden_layers": 12,
   "patch_size": 16,
   "problem_type": "single_label_classification",
   "qkv_bias": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c424c4f3085de07de4e3b84b573353382a7fd539eda8c73f6f1b0257201a0a
-size 1214073080
+oid sha256:3cc43505c04a13126a491e4f19e7f7fb281d4801c48c24c6d861735788cf9cd9
+size 343833032