Training in progress, step 500

config.json

@@ -0,0 +1,165 @@
+{
+  "_name_or_path": "microsoft/layoutxlm-base",
+  "architectures": [
+    "LayoutLMv2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "convert_sync_batchnorm": true,
+  "coordinate_size": 128,
+  "detectron2_config_args": {
+    "MODEL.ANCHOR_GENERATOR.SIZES": [
+      [
+        32
+      ],
+      [
+        64
+      ],
+      [
+        128
+      ],
+      [
+        256
+      ],
+      [
+        512
+      ]
+    ],
+    "MODEL.BACKBONE.NAME": "build_resnet_fpn_backbone",
+    "MODEL.FPN.IN_FEATURES": [
+      "res2",
+      "res3",
+      "res4",
+      "res5"
+    ],
+    "MODEL.MASK_ON": true,
+    "MODEL.PIXEL_STD": [
+      57.375,
+      57.12,
+      58.395
+    ],
+    "MODEL.POST_NMS_TOPK_TEST": 1000,
+    "MODEL.RESNETS.ASPECT_RATIOS": [
+      [
+        0.5,
+        1.0,
+        2.0
+      ]
+    ],
+    "MODEL.RESNETS.DEPTH": 101,
+    "MODEL.RESNETS.NUM_GROUPS": 32,
+    "MODEL.RESNETS.OUT_FEATURES": [
+      "res2",
+      "res3",
+      "res4",
+      "res5"
+    ],
+    "MODEL.RESNETS.SIZES": [
+      [
+        32
+      ],
+      [
+        64
+      ],
+      [
+        128
+      ],
+      [
+        256
+      ],
+      [
+        512
+      ]
+    ],
+    "MODEL.RESNETS.STRIDE_IN_1X1": false,
+    "MODEL.RESNETS.WIDTH_PER_GROUP": 8,
+    "MODEL.ROI_BOX_HEAD.NAME": "FastRCNNConvFCHead",
+    "MODEL.ROI_BOX_HEAD.NUM_FC": 2,
+    "MODEL.ROI_BOX_HEAD.POOLER_RESOLUTION": 14,
+    "MODEL.ROI_HEADS.IN_FEATURES": [
+      "p2",
+      "p3",
+      "p4",
+      "p5"
+    ],
+    "MODEL.ROI_HEADS.NAME": "StandardROIHeads",
+    "MODEL.ROI_HEADS.NUM_CLASSES": 5,
+    "MODEL.ROI_MASK_HEAD.NAME": "MaskRCNNConvUpsampleHead",
+    "MODEL.ROI_MASK_HEAD.NUM_CONV": 4,
+    "MODEL.ROI_MASK_HEAD.POOLER_RESOLUTION": 7,
+    "MODEL.RPN.IN_FEATURES": [
+      "p2",
+      "p3",
+      "p4",
+      "p5",
+      "p6"
+    ],
+    "MODEL.RPN.POST_NMS_TOPK_TRAIN": 1000,
+    "MODEL.RPN.PRE_NMS_TOPK_TEST": 1000,
+    "MODEL.RPN.PRE_NMS_TOPK_TRAIN": 2000
+  },
+  "eos_token_id": 2,
+  "fast_qkv": false,
+  "gradient_checkpointing": false,
+  "has_relative_attention_bias": false,
+  "has_spatial_attention_bias": false,
+  "has_visual_segment_embedding": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-CQ",
+    "1": "B-DT",
+    "2": "B-SO",
+    "3": "B-TI",
+    "4": "E-CQ",
+    "5": "E-DT",
+    "6": "E-SO",
+    "7": "E-TI",
+    "8": "I-CQ",
+    "9": "I-DT",
+    "10": "I-SO",
+    "11": "I-TI",
+    "12": "O"
+  },
+  "image_feature_pool_shape": [
+    7,
+    7,
+    256
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CQ": 0,
+    "B-DT": 1,
+    "B-SO": 2,
+    "B-TI": 3,
+    "E-CQ": 4,
+    "E-DT": 5,
+    "E-SO": 6,
+    "E-TI": 7,
+    "I-CQ": 8,
+    "I-DT": 9,
+    "I-SO": 10,
+    "I-TI": 11,
+    "O": 12
+  },
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "max_rel_2d_pos": 256,
+  "max_rel_pos": 128,
+  "model_type": "layoutlmv2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "shape_size": 128,
+  "tokenizer_class": "LayoutXLMTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.2",
+  "type_vocab_size": 1,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d86a578e05a9fc2f8416985102c64b05b34be6a7c35c203795b9ab2fe38fddb
+size 1476367700

runs/Jul26_00-36-27_vm-ocr-fis/events.out.tfevents.1721928994.vm-ocr-fis.1395713.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ecd221f6f5bf53d30283dd7f7ba1fe4086bf332deafa470d4a487341edcdfc
+size 7617

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ced0906ad1f456d65f4af02ffdc478ec9fb7fb01b1b625a583c54fa769dd5f
+size 5240