End of training

README.md

@@ -0,0 +1,64 @@
+---
+license: cc-by-nc-sa-4.0
+base_model: microsoft/layoutlmv3-base
+tags:
+- generated_from_trainer
+datasets:
+- cord
+model-index:
+- name: layoutlmv3-test-2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# layoutlmv3-test-2
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the cord dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6335
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 2000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0437        | 0.47  | 500  | 0.5549          |
+| 0.0006        | 0.93  | 1000 | 0.6001          |
+| 0.0005        | 1.4   | 1500 | 0.6243          |
+| 0.0003        | 1.86  | 2000 | 0.6335          |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.2.0
+- Datasets 2.17.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.86,
+    "eval_loss": 0.6335224509239197,
+    "eval_runtime": 200.5705,
+    "eval_samples": 1400,
+    "eval_samples_per_second": 6.98,
+    "eval_steps_per_second": 0.873,
+    "train_loss": 0.01125018835812807,
+    "train_runtime": 169289.6715,
+    "train_samples": 8600,
+    "train_samples_per_second": 0.095,
+    "train_steps_per_second": 0.012
+}

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "microsoft/layoutlmv3-base",
+  "architectures": [
+    "LayoutLMv3ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "coordinate_size": 128,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "has_relative_attention_bias": true,
+  "has_spatial_attention_bias": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 8,
+    "8": 9,
+    "9": 10,
+    "10": 11,
+    "11": 12,
+    "12": 13
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "8": 7,
+    "9": 8,
+    "10": 9,
+    "11": 10,
+    "12": 11,
+    "13": 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": "layoutlmv3",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "patch_size": 16,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "second_input_size": 112,
+  "shape_size": 128,
+  "text_embed": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 1,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.86,
+    "eval_loss": 0.6335224509239197,
+    "eval_runtime": 200.5705,
+    "eval_samples": 1400,
+    "eval_samples_per_second": 6.98,
+    "eval_steps_per_second": 0.873
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f33182b22d3d901793f8a0453241a8955dafdc7dbf095731d5097ab1dfea84
+size 503736588

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "apply_ocr": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "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": "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 +1,80 @@
+{
+  "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
+    }
+  },
+  "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>",
+  "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>",
+  "use_fast": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.86,
+    "train_loss": 0.01125018835812807,
+    "train_runtime": 169289.6715,
+    "train_samples": 8600,
+    "train_samples_per_second": 0.095,
+    "train_steps_per_second": 0.012
+}

trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8604651162790697,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.0437,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 0.5549370050430298,
+      "eval_runtime": 2055.9752,
+      "eval_samples_per_second": 0.681,
+      "eval_steps_per_second": 0.085,
+      "step": 500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0006,
+      "step": 1000
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 0.6001065969467163,
+      "eval_runtime": 1468.9475,
+      "eval_samples_per_second": 0.953,
+      "eval_steps_per_second": 0.119,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.25e-05,
+      "loss": 0.0005,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.6242989301681519,
+      "eval_runtime": 199.8198,
+      "eval_samples_per_second": 7.006,
+      "eval_steps_per_second": 0.876,
+      "step": 1500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.0,
+      "loss": 0.0003,
+      "step": 2000
+    },
+    {
+      "epoch": 1.86,
+      "eval_loss": 0.6335224509239197,
+      "eval_runtime": 212.8986,
+      "eval_samples_per_second": 6.576,
+      "eval_steps_per_second": 0.822,
+      "step": 2000
+    },
+    {
+      "epoch": 1.86,
+      "step": 2000,
+      "total_flos": 4246941057024000.0,
+      "train_loss": 0.01125018835812807,
+      "train_runtime": 169289.6715,
+      "train_samples_per_second": 0.095,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 4246941057024000.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e03366e4c35374bd06e5a39a5e8bb5a85db61c7171a3712a0a5534f1dc467160
+size 4664