Training in progress, epoch 1

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "google/vit-large-patch16-224-in21k",
   "architectures": [
     "ViTForImageClassification"
   ],
-  "attention_probs_dropout_prob": 0.2,
+  "attention_probs_dropout_prob": 0.0,
   "encoder_stride": 16,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.2,
-  "hidden_size": 768,
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
   "id2label": {
     "0": "anger",
     "1": "contempt",
@@ -20,7 +20,7 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "anger": "0",
     "contempt": "1",
@@ -33,9 +33,9 @@
   },
   "layer_norm_eps": 1e-12,
   "model_type": "vit",
-  "num_attention_heads": 12,
+  "num_attention_heads": 16,
   "num_channels": 3,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 24,
   "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 sha256:0bd136bdcebdf6230b9b0e7ba43c9a9685396df52e49b919137c1aa2a6a12bd3
-size 343242432
+oid sha256:74b53a8f1e31e064ef3ad160eb7f4411471794a1e00e6aac283819d24e12c4f3
+size 1213285872

runs/Sep06_03-14-23_935bcd5a2a5e/events.out.tfevents.1725592477.935bcd5a2a5e.1381.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:747eaf7ee73b0428c47759a9a4c0b0213427eaf60622a73d31b0998a3cb47706
+size 5888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9305e4b81766c72e01306ccc99fa5eb8f15ed048f3c99631c3f986043416a99
+oid sha256:f76fea7d187b2734016cb05bbf8a04a379fea20a10f49a641871a7f133aeda78
 size 5240