Training in progress, step 20

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "adityaprakhar/LILT_March26_with_and_without_b",
+  "_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
   "architectures": [
     "LiltForTokenClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da7073925ce6a2e3424471010caa297aff2ffc3d715cc92a1c1fbd76b7aeee88
+oid sha256:fb2c3381a079cb68be1904a6f64517a3a74afd97f7b5699126c174da1873812e
 size 520739868

preprocessor_config.json

@@ -1,22 +1,23 @@
 {
-  "_valid_processor_keys": [
-    "images",
-    "do_resize",
-    "size",
-    "resample",
-    "apply_ocr",
-    "ocr_lang",
-    "tesseract_config",
-    "return_tensors",
-    "data_format",
-    "input_data_format"
-  ],
-  "apply_ocr": true,
+  "apply_ocr": false,
+  "do_normalize": true,
+  "do_rescale": true,
   "do_resize": true,
-  "image_processor_type": "LayoutLMv2ImageProcessor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "LayoutLMv3ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
   "ocr_lang": null,
-  "processor_class": "LayoutLMv2Processor",
+  "processor_class": "LayoutLMv3Processor",
   "resample": 2,
+  "rescale_factor": 0.00392156862745098,
   "size": {
     "height": 224,
     "width": 224

runs/Mar26_01-47-29_0c95cfa99a01/events.out.tfevents.1711417650.0c95cfa99a01.305.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e50405d0c5b9f611b331955dff78de2d9546758afd3dacc9ceb95b31362b04e1
-size 6074
+oid sha256:442d868b0902d220090d3a805668d4d94e6254493d0616c49efb1b4cef9a1671
+size 6285

runs/Mar26_01-50-49_0c95cfa99a01/events.out.tfevents.1711417849.0c95cfa99a01.305.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d283be7f8009dd9674097178c22e24ffc3c78ec289a2abae1c07b0ee3545c91c
+size 6053

runs/Mar26_01-55-28_0c95cfa99a01/events.out.tfevents.1711418129.0c95cfa99a01.13991.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530867d3b0bd4b062cb90e0a812dc710584efcdd2e7478669deea2805964b633
+size 5561

special_tokens_map.json

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

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb36078885c7952ce7032f38fa42c99bd27387c69f9f4e446f2e24a5726568ac
+oid sha256:fb49058ce3265128c73e5ae2e86121a6032b5c8d8cb262dcd7aeb738f6e3a0c4
 size 4856