Training in progress, epoch 1

config.json

@@ -1,44 +1,68 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "facebook/convnext-large-224-22k-1k",
   "architectures": [
-    "ViTForImageClassification"
+    "ConvNextForImageClassification"
   ],
-  "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
+  "depths": [
+    3,
+    3,
+    27,
+    3
+  ],
+  "drop_path_rate": 0.0,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
+  "hidden_sizes": [
+    192,
+    384,
+    768,
+    1536
+  ],
   "id2label": {
-    "0": "anger",
-    "1": "contempt",
-    "2": "disgust",
-    "3": "fear",
-    "4": "happy",
-    "5": "neutral",
-    "6": "sad",
-    "7": "surprise"
+    "0": "goldfish",
+    "1": "scuba diver",
+    "2": "seashore",
+    "3": "green lizard",
+    "4": "ski",
+    "5": "flamingo",
+    "6": "red wine",
+    "7": "volcano",
+    "8": "jack-o'-lantern",
+    "9": "cowboy boot"
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
-    "anger": "0",
-    "contempt": "1",
-    "disgust": "2",
-    "fear": "3",
-    "happy": "4",
-    "neutral": "5",
-    "sad": "6",
-    "surprise": "7"
+    "cowboy boot": "9",
+    "flamingo": "5",
+    "goldfish": "0",
+    "green lizard": "3",
+    "jack-o'-lantern": "8",
+    "red wine": "6",
+    "scuba diver": "1",
+    "seashore": "2",
+    "ski": "4",
+    "volcano": "7"
   },
   "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
+  "layer_scale_init_value": 1e-06,
+  "model_type": "convnext",
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
+  "num_stages": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
   "problem_type": "single_label_classification",
-  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.33.2"
+  "transformers_version": "4.33.3"
 }

preprocessor_config.json

@@ -1,22 +1,22 @@
 {
+  "crop_pct": 0.875,
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.5,
-    0.5,
-    0.5
+    0.485,
+    0.456,
+    0.406
   ],
-  "image_processor_type": "ViTImageProcessor",
+  "image_processor_type": "ConvNextImageProcessor",
   "image_std": [
-    0.5,
-    0.5,
-    0.5
+    0.229,
+    0.224,
+    0.225
   ],
-  "resample": 2,
+  "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "height": 224,
-    "width": 224
+    "shortest_edge": 224
   }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ca1ba59eba4ebed53c838f76965f7db91d79ff05fda79231d69e4225ad67b5d
-size 343287149
+oid sha256:75dcf18584575de5a8ba63d5c1094b76150e02b1f1452286c44647766ef51f94
+size 785101485

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd65d9929e7df3343379a31a5a1308e4adeeccd13d3675fecfaeda48cfef7bf
+oid sha256:41266e6011f6ab4c659287ad0a7652494ea82bac523b86d498edc7d31d4e398c
 size 4091