End of training

README.md

@@ -15,19 +15,19 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.7170
-- eval_ANSWER: {'precision': 0.8775510204081632, 'recall': 0.8947368421052632, 'f1': 0.886060606060606, 'number': 817}
-- eval_HEADER: {'precision': 0.4644808743169399, 'recall': 0.7142857142857143, 'f1': 0.5629139072847683, 'number': 119}
-- eval_QUESTION: {'precision': 0.8934348239771646, 'recall': 0.871866295264624, 'f1': 0.8825187969924814, 'number': 1077}
-- eval_overall_precision: 0.8491
-- eval_overall_recall: 0.8718
-- eval_overall_f1: 0.8603
-- eval_overall_accuracy: 0.7983
-- eval_runtime: 59.4689
-- eval_samples_per_second: 0.841
-- eval_steps_per_second: 0.118
-- epoch: 84.2105
-- step: 1600
+- eval_loss: 1.6706
+- eval_ANSWER: {'precision': 0.875, 'recall': 0.9082007343941249, 'f1': 0.8912912912912913, 'number': 817}
+- eval_HEADER: {'precision': 0.6666666666666666, 'recall': 0.5714285714285714, 'f1': 0.6153846153846153, 'number': 119}
+- eval_QUESTION: {'precision': 0.8880931065353626, 'recall': 0.9210770659238626, 'f1': 0.9042844120328168, 'number': 1077}
+- eval_overall_precision: 0.8718
+- eval_overall_recall: 0.8952
+- eval_overall_f1: 0.8833
+- eval_overall_accuracy: 0.8026
+- eval_runtime: 50.8863
+- eval_samples_per_second: 0.983
+- eval_steps_per_second: 0.138
+- epoch: 90.8421
+- step: 1726
 
 ## Model description
 

logs/events.out.tfevents.1721227049.ACER1278.6244.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd81fc53f616f44a086375a215389a50d85231ea0da672c82d27b9d5adc0db41
-size 10950
+oid sha256:efb660c49a89ba57532a47eabd69e23f7c6c0299f3c591277200ca94735e4742
+size 11454

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "apply_ocr": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "LayoutLMv3FeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "ocr_lang": null,
+  "processor_class": "LayoutLMv3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "tesseract_config": ""
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": 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>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,78 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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>",
+  "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>"
+}