Training in progress, step 500

config.json

@@ -1,17 +1,13 @@
 {
-  "_name_or_path": "microsoft/beit-base-patch16-224-pt22k-ft22k",
+  "_name_or_path": "google/vit-large-patch16-224-in21k",
   "architectures": [
-    "BeitForImageClassification"
+    "ViTForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "auxiliary_channels": 256,
-  "auxiliary_concat_input": false,
-  "auxiliary_loss_weight": 0.4,
-  "auxiliary_num_convs": 1,
-  "drop_path_rate": 0.1,
+  "encoder_stride": 16,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "Black-grass",
     "1": "Charlock",
@@ -28,7 +24,7 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "Black-grass": "0",
     "Charlock": "1",
@@ -44,33 +40,13 @@
     "Sugar beet": "11"
   },
   "layer_norm_eps": 1e-12,
-  "layer_scale_init_value": 0.1,
-  "model_type": "beit",
-  "num_attention_heads": 12,
+  "model_type": "vit",
+  "num_attention_heads": 16,
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "out_indices": [
-    3,
-    5,
-    7,
-    11
-  ],
+  "num_hidden_layers": 24,
   "patch_size": 16,
-  "pool_scales": [
-    1,
-    2,
-    3,
-    6
-  ],
   "problem_type": "single_label_classification",
-  "semantic_loss_ignore_index": 255,
+  "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
-  "use_absolute_position_embeddings": false,
-  "use_auxiliary_head": true,
-  "use_mask_token": false,
-  "use_mean_pooling": true,
-  "use_relative_position_bias": true,
-  "use_shared_relative_position_bias": false,
-  "vocab_size": 8192
+  "transformers_version": "4.28.1"
 }

preprocessor_config.json

@@ -1,11 +1,5 @@
 {
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
-  "do_center_crop": false,
   "do_normalize": true,
-  "do_reduce_labels": false,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
@@ -13,7 +7,7 @@
     0.5,
     0.5
   ],
-  "image_processor_type": "BeitImageProcessor",
+  "image_processor_type": "ViTFeatureExtractor",
   "image_std": [
     0.5,
     0.5,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8418d0c56ed9f7e4b6fe3c689cc21b658e06f21a66fd6098011fb66c447dfe9d
-size 346891129
+oid sha256:0841c6f80e59008c9a771a28e7311e1ac524535f873fd01b8df3fdfd48c43582
+size 1213389613

runs/Apr16_20-11-47_3b1c7990af73/1681676013.252243/events.out.tfevents.1681676013.3b1c7990af73.253.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4b9f839d9e30d9b7e336b85bb463619452dc4d622413135d09487dcacc1010
+size 5896

runs/Apr16_20-11-47_3b1c7990af73/events.out.tfevents.1681676013.3b1c7990af73.253.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abdbfb2cd3bb792681571bdd789240642a73f0d97153a5ed58c2420479e5c6ad
+size 12685

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7971b8746c70a1d903756a90707e1e63ab9243f6d542f6ff09b16e4ed989fa8
+oid sha256:43a5142eb690b726ff89529d86328472b48a979c6405ff0b373adee9e50c2c1c
 size 3579