Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/layoutlmv3-base",
+  "_name_or_path": "microsoft/layoutlm-base-uncased",
   "architectures": [
     "LayoutLMv3ForTokenClassification"
   ],
@@ -15,62 +15,64 @@
   "hidden_size": 768,
   "id2label": {
     "0": "attorneys for plaintiff",
-    "1": "attorneys for defendant",
-    "2": "attorneys for co-defendant",
-    "3": "fax",
-    "4": "attorney_name",
-    "5": "SBN",
-    "6": "lawfirm",
-    "7": "other",
-    "8": "parties",
-    "9": "attorney for defendant/cross-complainant/cross-defendant",
-    "10": "counsel for plaintiff",
-    "11": "attorneys for co-counsel",
+    "1": "SBN",
+    "2": "counsel for plaintiff",
+    "3": "lawfirm",
+    "4": "parties",
+    "5": "email",
+    "6": "co-counsel for plaintiff",
+    "7": "attorney_name",
+    "8": "attorneys for co-counsel",
+    "9": "other",
+    "10": "fax",
+    "11": "attorneys for co-defendant",
     "12": "telephone",
-    "13": "address",
-    "14": "co-counsel for plaintiff",
-    "15": "email"
+    "13": "attorney for defendant/cross-complainant/cross-defendant",
+    "14": "attorneys for defendant",
+    "15": "address"
   },
   "initializer_range": 0.02,
   "input_size": 224,
   "intermediate_size": 3072,
   "label2id": {
-    "SBN": 5,
-    "address": 13,
-    "attorney for defendant/cross-complainant/cross-defendant": 9,
-    "attorney_name": 4,
-    "attorneys for co-counsel": 11,
-    "attorneys for co-defendant": 2,
-    "attorneys for defendant": 1,
+    "SBN": 1,
+    "address": 15,
+    "attorney for defendant/cross-complainant/cross-defendant": 13,
+    "attorney_name": 7,
+    "attorneys for co-counsel": 8,
+    "attorneys for co-defendant": 11,
+    "attorneys for defendant": 14,
     "attorneys for plaintiff": 0,
-    "co-counsel for plaintiff": 14,
-    "counsel for plaintiff": 10,
-    "email": 15,
-    "fax": 3,
-    "lawfirm": 6,
-    "other": 7,
-    "parties": 8,
+    "co-counsel for plaintiff": 6,
+    "counsel for plaintiff": 2,
+    "email": 5,
+    "fax": 10,
+    "lawfirm": 3,
+    "other": 9,
+    "parties": 4,
     "telephone": 12
   },
-  "layer_norm_eps": 1e-05,
+  "layer_norm_eps": 1e-12,
   "max_2d_position_embeddings": 1024,
-  "max_position_embeddings": 514,
+  "max_position_embeddings": 512,
   "max_rel_2d_pos": 256,
   "max_rel_pos": 128,
   "model_type": "layoutlmv3",
   "num_attention_heads": 12,
   "num_channels": 3,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "output_past": true,
+  "pad_token_id": 0,
   "patch_size": 16,
+  "position_embedding_type": "absolute",
   "rel_2d_pos_bins": 64,
   "rel_pos_bins": 32,
-  "second_input_size": 112,
   "shape_size": 128,
   "text_embed": true,
   "torch_dtype": "float32",
   "transformers_version": "4.39.0.dev0",
-  "type_vocab_size": 1,
+  "type_vocab_size": 2,
+  "use_cache": true,
   "visual_embed": true,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a399559ff8695f03d8070521c03f4f400c146926ac9ab76a0496e89901701f
-size 503745816
+oid sha256:81a497fbae4db76bf633d0c6179841f4951588dfdb5cd15f671fe6e34121d89c
+size 443092232

runs/Mar13_06-11-13_bfebc32db449/events.out.tfevents.1710310274.bfebc32db449.363.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a541ff6d297e270b1f0004272fa9ef887dfed3d6fafebe327a641e77b83a5604
+size 11102

special_tokens_map.json

@@ -1,50 +1,36 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
   "cls_token": {
-    "content": "<s>",
+    "content": "[CLS]",
     "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "[PAD]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "[SEP]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -1,79 +1,56 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "apply_ocr": false,
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "cls_token_box": [
-    0,
-    0,
-    0,
-    0
-  ],
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_len": 512,
   "model_max_length": 512,
-  "only_label_first_subword": true,
-  "pad_token": "<pad>",
-  "pad_token_box": [
-    0,
-    0,
-    0,
-    0
-  ],
-  "pad_token_label": -100,
-  "processor_class": "LayoutLMv3Processor",
-  "sep_token": "</s>",
-  "sep_token_box": [
-    0,
-    0,
-    0,
-    0
-  ],
-  "tokenizer_class": "LayoutLMv3Tokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "LayoutLMTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209d58b310c62dee95c4f0c72f225b5bc4a29a9332710f52fde7a32473841dcb
+oid sha256:f6f0b84f08d7b979070db356c4d7052a12fc971f626f5fce7f6d3826c779b461
 size 4856