Duplicate from nielsr/layoutlmv3-finetuned-funsd

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,98 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- nielsr/funsd-layoutlmv3
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: layoutlmv3-finetuned-funsd
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: nielsr/funsd-layoutlmv3
+      type: nielsr/funsd-layoutlmv3
+      args: funsd
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.9026198714780029
+    - name: Recall
+      type: recall
+      value: 0.913
+    - name: F1
+      type: f1
+      value: 0.9077802634849614
+    - name: Accuracy
+      type: accuracy
+      value: 0.8330271015158475
+duplicated_from: nielsr/layoutlmv3-finetuned-funsd
+---
+
+<!-- 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-finetuned-funsd
+
+This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the nielsr/funsd-layoutlmv3 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1164
+- Precision: 0.9026
+- Recall: 0.913
+- F1: 0.9078
+- Accuracy: 0.8330
+
+The script for training can be found here: https://github.com/huggingface/transformers/tree/main/examples/research_projects/layoutlmv3
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 10.0  | 100  | 0.5238          | 0.8366    | 0.886  | 0.8606 | 0.8410   |
+| No log        | 20.0  | 200  | 0.6930          | 0.8751    | 0.8965 | 0.8857 | 0.8322   |
+| No log        | 30.0  | 300  | 0.7784          | 0.8902    | 0.908  | 0.8990 | 0.8414   |
+| No log        | 40.0  | 400  | 0.9056          | 0.8916    | 0.905  | 0.8983 | 0.8364   |
+| 0.2429        | 50.0  | 500  | 1.0016          | 0.8954    | 0.9075 | 0.9014 | 0.8298   |
+| 0.2429        | 60.0  | 600  | 1.0097          | 0.8899    | 0.897  | 0.8934 | 0.8294   |
+| 0.2429        | 70.0  | 700  | 1.0722          | 0.9035    | 0.9085 | 0.9060 | 0.8315   |
+| 0.2429        | 80.0  | 800  | 1.0884          | 0.8905    | 0.9105 | 0.9004 | 0.8269   |
+| 0.2429        | 90.0  | 900  | 1.1292          | 0.8938    | 0.909  | 0.9013 | 0.8279   |
+| 0.0098        | 100.0 | 1000 | 1.1164          | 0.9026    | 0.913  | 0.9078 | 0.8330   |
+
+
+### Framework versions
+
+- Transformers 4.19.0.dev0
+- Pytorch 1.11.0+cu113
+- Datasets 2.0.0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 100.0,
+    "eval_accuracy": 0.8330271015158475,
+    "eval_f1": 0.9077802634849614,
+    "eval_loss": 1.1164220571517944,
+    "eval_precision": 0.9026198714780029,
+    "eval_recall": 0.913,
+    "eval_runtime": 4.5243,
+    "eval_samples": 54,
+    "eval_samples_per_second": 11.936,
+    "eval_steps_per_second": 0.884,
+    "train_loss": 0.12633917331695557,
+    "train_runtime": 1653.606,
+    "train_samples": 150,
+    "train_samples_per_second": 9.676,
+    "train_steps_per_second": 0.605
+}

config.json

@@ -0,0 +1,57 @@
+{
+  "_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": "O",
+    "1": "B-HEADER",
+    "2": "I-HEADER",
+    "3": "B-QUESTION",
+    "4": "I-QUESTION",
+    "5": "B-ANSWER",
+    "6": "I-ANSWER"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANSWER": 5,
+    "B-HEADER": 1,
+    "B-QUESTION": 3,
+    "I-ANSWER": 6,
+    "I-HEADER": 2,
+    "I-QUESTION": 4,
+    "O": 0
+  },
+  "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_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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0.dev0",
+  "type_vocab_size": 1,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2022-05-02T16:54:11,8eebd56a-eb8f-4892-9c80-7ac739a77655,codecarbon,1653.8408570289612,0.028152538025484036,0.1337565669441834,United States,USA,new york,N,,

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 100.0,
+    "eval_accuracy": 0.8330271015158475,
+    "eval_f1": 0.9077802634849614,
+    "eval_loss": 1.1164220571517944,
+    "eval_precision": 0.9026198714780029,
+    "eval_recall": 0.913,
+    "eval_runtime": 4.5243,
+    "eval_samples": 54,
+    "eval_samples_per_second": 11.936,
+    "eval_steps_per_second": 0.884
+}

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "apply_ocr": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv3FeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "ocr_lang": null,
+  "resample": 2,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab7ab7a858117bc58a9431474bb8010396a330136730dd1eed4c1ceed68e44e
+size 501405907

runs/May02_16-26-18_brutasse/1651508794.4462817/events.out.tfevents.1651508794.brutasse.9557.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7494fd0a658cd16ee6cee37961f02e3e761b1db027032e26cc2e82d2ef1a46c1
+size 5031

runs/May02_16-26-18_brutasse/events.out.tfevents.1651508794.brutasse.9557.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01c4f3993c8a55cd4b3b333bdb55a66209afd9c260cceebd171b182c0c6b3d8
+size 9489

runs/May02_16-26-18_brutasse/events.out.tfevents.1651510649.brutasse.9557.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2ed9c23e5973706e0aaa2a59ef0f1cfcfedaa1baa2552e05455bc0bebe9eaf
+size 512

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": true, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 100.0,
+    "train_loss": 0.12633917331695557,
+    "train_runtime": 1653.606,
+    "train_samples": 150,
+    "train_samples_per_second": 9.676,
+    "train_steps_per_second": 0.605
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": 0.9077802634849614,
+  "best_model_checkpoint": "layoutlmv3-test/checkpoint-1000",
+  "epoch": 100.0,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8409508497932935,
+      "eval_f1": 0.8606119475473532,
+      "eval_loss": 0.5238379240036011,
+      "eval_precision": 0.8366383380547686,
+      "eval_recall": 0.886,
+      "eval_runtime": 4.4875,
+      "eval_samples_per_second": 12.033,
+      "eval_steps_per_second": 0.891,
+      "step": 100
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.8322232429949472,
+      "eval_f1": 0.8856507779698691,
+      "eval_loss": 0.6930040717124939,
+      "eval_precision": 0.8750610053684724,
+      "eval_recall": 0.8965,
+      "eval_runtime": 4.6295,
+      "eval_samples_per_second": 11.664,
+      "eval_steps_per_second": 0.864,
+      "step": 200
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.8414101975195223,
+      "eval_f1": 0.899009900990099,
+      "eval_loss": 0.7784350514411926,
+      "eval_precision": 0.8901960784313725,
+      "eval_recall": 0.908,
+      "eval_runtime": 4.5256,
+      "eval_samples_per_second": 11.932,
+      "eval_steps_per_second": 0.884,
+      "step": 300
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy": 0.836357372531006,
+      "eval_f1": 0.8982630272952853,
+      "eval_loss": 0.9056066870689392,
+      "eval_precision": 0.8916256157635468,
+      "eval_recall": 0.905,
+      "eval_runtime": 4.5498,
+      "eval_samples_per_second": 11.869,
+      "eval_steps_per_second": 0.879,
+      "step": 400
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 5e-06,
+      "loss": 0.2429,
+      "step": 500
+    },
+    {
+      "epoch": 50.0,
+      "eval_accuracy": 0.8298116674322462,
+      "eval_f1": 0.9014154457412467,
+      "eval_loss": 1.001568078994751,
+      "eval_precision": 0.895411938825851,
+      "eval_recall": 0.9075,
+      "eval_runtime": 4.6434,
+      "eval_samples_per_second": 11.629,
+      "eval_steps_per_second": 0.861,
+      "step": 500
+    },
+    {
+      "epoch": 60.0,
+      "eval_accuracy": 0.8293523197060174,
+      "eval_f1": 0.8934262948207171,
+      "eval_loss": 1.009719967842102,
+      "eval_precision": 0.8898809523809523,
+      "eval_recall": 0.897,
+      "eval_runtime": 4.6541,
+      "eval_samples_per_second": 11.603,
+      "eval_steps_per_second": 0.859,
+      "step": 600
+    },
+    {
+      "epoch": 70.0,
+      "eval_accuracy": 0.8315342214056041,
+      "eval_f1": 0.906008476689105,
+      "eval_loss": 1.072226643562317,
+      "eval_precision": 0.9035305818000995,
+      "eval_recall": 0.9085,
+      "eval_runtime": 4.5145,
+      "eval_samples_per_second": 11.961,
+      "eval_steps_per_second": 0.886,
+      "step": 700
+    },
+    {
+      "epoch": 80.0,
+      "eval_accuracy": 0.8269407441433165,
+      "eval_f1": 0.9003708281829418,
+      "eval_loss": 1.088362693786621,
+      "eval_precision": 0.8904645476772616,
+      "eval_recall": 0.9105,
+      "eval_runtime": 4.4141,
+      "eval_samples_per_second": 12.233,
+      "eval_steps_per_second": 0.906,
+      "step": 800
+    },
+    {
+      "epoch": 90.0,
+      "eval_accuracy": 0.827859439595774,
+      "eval_f1": 0.9013386217154189,
+      "eval_loss": 1.129175066947937,
+      "eval_precision": 0.8938053097345132,
+      "eval_recall": 0.909,
+      "eval_runtime": 4.4449,
+      "eval_samples_per_second": 12.149,
+      "eval_steps_per_second": 0.9,
+      "step": 900
+    },
+    {
+      "epoch": 100.0,
+      "learning_rate": 0.0,
+      "loss": 0.0098,
+      "step": 1000
+    },
+    {
+      "epoch": 100.0,
+      "eval_accuracy": 0.8330271015158475,
+      "eval_f1": 0.9077802634849614,
+      "eval_loss": 1.1164220571517944,
+      "eval_precision": 0.9026198714780029,
+      "eval_recall": 0.913,
+      "eval_runtime": 4.533,
+      "eval_samples_per_second": 11.913,
+      "eval_steps_per_second": 0.882,
+      "step": 1000
+    },
+    {
+      "epoch": 100.0,
+      "step": 1000,
+      "total_flos": 3954080148480000.0,
+      "train_loss": 0.12633917331695557,
+      "train_runtime": 1653.606,
+      "train_samples_per_second": 9.676,
+      "train_steps_per_second": 0.605
+    }
+  ],
+  "max_steps": 1000,
+  "num_train_epochs": 100,
+  "total_flos": 3954080148480000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a236fc2f8ad0eb53ff60dc4aa91eec43e0143120b817b147b606f73d53579abe
+size 3183