Training in progress, step 500

config.json

@@ -1,18 +1,18 @@
 {
-  "_name_or_path": "microsoft/layoutlmv3-base",
+  "_name_or_path": "microsoft/layoutlmv3-large",
   "architectures": [
     "LayoutLMv3ForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
-  "coordinate_size": 128,
+  "coordinate_size": 171,
   "eos_token_id": 2,
   "has_relative_attention_bias": true,
   "has_spatial_attention_bias": true,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "O",
     "1": "B-MENU.NM",
@@ -78,7 +78,7 @@
   },
   "initializer_range": 0.02,
   "input_size": 224,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "B-MENU.CNT": 4,
     "B-MENU.DISCOUNTPRICE": 5,
@@ -148,15 +148,15 @@
   "max_rel_2d_pos": 256,
   "max_rel_pos": 128,
   "model_type": "layoutlmv3",
-  "num_attention_heads": 12,
+  "num_attention_heads": 16,
   "num_channels": 3,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "patch_size": 16,
   "rel_2d_pos_bins": 64,
   "rel_pos_bins": 32,
   "second_input_size": 112,
-  "shape_size": 128,
+  "shape_size": 170,
   "text_embed": true,
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa5bb30e2c01b8e4d9f45ca2d74b7936c3d110f85ba74186843cd67f975a18f
-size 503936881
+oid sha256:6a9c20dab3bc76e582c3a09b6f94c974fb6fc08e788a2393bd4050cb29f8f00c
+size 1428616177

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344ea69291879cca85f3d74189104683ae19158321a27bc1ce9d29a57d0129b7
+oid sha256:17610c46e68866ecc478db417983e07b934de761cb814bef5271b9e0b9242da5
 size 3963