Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/vit-base-patch32-224-in21k",
+  "_name_or_path": "google/vit-huge-patch14-224-in21k",
   "architectures": [
     "ViTForImageClassification"
   ],
@@ -7,7 +7,7 @@
   "encoder_stride": 16,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
+  "hidden_size": 1280,
   "id2label": {
     "0": "T - shirt / top",
     "1": "Trouser",
@@ -22,7 +22,7 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 5120,
   "label2id": {
     "Ankle boot": "9",
     "Bag": "8",
@@ -37,10 +37,10 @@
   },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",
-  "num_attention_heads": 12,
+  "num_attention_heads": 16,
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 32,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdda31814d30f298826c0b5d7521f979c7105db4881ee290291641b026293c80
-size 349874904
+oid sha256:dedd69df50a5c4a21c558f98ad1b4c99eb1ea78c8159ac9abcfa99d7c1030e76
+size 2523172784

runs/May06_22-17-26_tron55.umiacs.umd.edu/events.out.tfevents.1715048249.tron55.umiacs.umd.edu.452840.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0219040a83ba760599406d634fd49dfc063300c526949f91191cb9acf92803
+size 13128

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e22d67c937a54abacafa401b3c178216ad858ff65ecb0ed0f4b446c8898bc6
+oid sha256:f84fb4de6bdf7d0d30b8f9734228ab747e633a394c4a9b8753b5ba7ff5d1ef2b
 size 5048