Training in progress, epoch 1

config.json

@@ -1,21 +1,13 @@
 {
-  "_name_or_path": "microsoft/swin-base-patch4-window7-224-in22k",
+  "_name_or_path": "dennisjooo/emotion_classification",
   "architectures": [
-    "SwinForImageClassification"
+    "ViTForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "depths": [
-    2,
-    2,
-    18,
-    2
-  ],
-  "drop_path_rate": 0.1,
-  "embed_dim": 128,
-  "encoder_stride": 32,
+  "encoder_stride": 16,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "anger",
     "1": "contempt",
@@ -28,6 +20,7 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "anger": "0",
     "contempt": "1",
@@ -38,36 +31,14 @@
     "sad": "6",
     "surprise": "7"
   },
-  "layer_norm_eps": 1e-05,
-  "mlp_ratio": 4.0,
-  "model_type": "swin",
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
   "num_channels": 3,
-  "num_heads": [
-    4,
-    8,
-    16,
-    32
-  ],
-  "num_layers": 4,
-  "out_features": [
-    "stage4"
-  ],
-  "out_indices": [
-    4
-  ],
-  "patch_size": 4,
-  "path_norm": true,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4"
-  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
-  "use_absolute_embeddings": false,
-  "window_size": 7
+  "transformers_version": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a0972d5594f4717fa03f2797e2673626ced42dd5d344ace86b78fe455d324b5
-size 347523416
+oid sha256:faea7e99e40441915a874032f1e9d43c26ea73b51f371f6ecb8a8708533d6838
+size 343242432

preprocessor_config.json

@@ -3,17 +3,17 @@
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.485,
-    0.456,
-    0.406
+    0.5,
+    0.5,
+    0.5
   ],
   "image_processor_type": "ViTImageProcessor",
   "image_std": [
-    0.229,
-    0.224,
-    0.225
+    0.5,
+    0.5,
+    0.5
   ],
-  "resample": 3,
+  "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
     "height": 224,

runs/Sep06_13-57-32_0f6a57d125fc/events.out.tfevents.1725631127.0f6a57d125fc.1806.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df1ff098cfc3725bf892716e0ecca03f0a8242bf23af8f3254ac1bdd93b77f0
-size 16893
+oid sha256:c801716dcdb27630596c80fcd723b27087be26b661c11b04e5c668821eb44395
+size 17570

runs/Sep06_14-04-08_0f6a57d125fc/events.out.tfevents.1725631460.0f6a57d125fc.1806.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f544aa6a54f9de5e298fce6ae7db251d184f4687ba1bbb290fb7166c2e55647e
+size 4184

runs/Sep06_14-04-08_0f6a57d125fc/events.out.tfevents.1725631477.0f6a57d125fc.1806.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21207b5b1ed85f710d4f42021dd59ad652b2c970afa086016a9b0a9cde46471d
+size 6411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363ff6ffef843803e14e3bd33ebccc0f2767e0af6dd3414bbd27d1f413ecd59e
+oid sha256:5d76c9e4519b53997064d269a23ae91d298e2d2aa98bf99b46a4579565ddde4a
 size 5240