model data

README.md

@@ -0,0 +1,49 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: CamemBERT pretrained on french trade directories from the XIXth century
+  results: []
+---
+
+# CamemBERT trained for NER on french trade directories from the XIXth century [GOLD training set]
+
+This mdoel is part of the material of the paper
+> Abadie, N., Carlinet, E., Chazalon, J., Duménieu, B. (2022). A
+> Benchmark of Named Entity Recognition Approaches in Historical
+> Documents Application to 19𝑡ℎ Century French Directories. In: Uchida,
+> S., Barney, E., Eglin, V. (eds) Document Analysis Systems. DAS 2022.
+> Lecture Notes in Computer Science, vol 13237. Springer, Cham.
+> https://doi.org/10.1007/978-3-031-06555-2_30
+
+The source code to train this model is available on the  [GitHub repository](https://github.com/soduco/paper-ner-bench-das22) of the paper as a Jupyter notebook in  `src/ner/40_experiment_2.ipynb`.
+
+
+## Model description
+This model adapts the model [Jean-Baptiste/camembert-ner](https://huggingface.co/Jean-Baptiste/camembert-ner) for NER on 6004 manually annotated directory entries referred as the "reference dataset" in the paper.
+
+Trade directory entries are short and strongly structured texts that giving the name, activity and location of a person or business, e.g: 
+```
+Peynaud, R. de la Vieille Bouclerie, 18. Richard, Joullain et comp., (commission- —Phéâtre Français. naire, (entrepôt), au port de la Rapée-
+```
+
+## Intended uses & limitations
+This model is intended for reproducibility of the NER evaluation published in the DAS2022 paper.
+Several derived models trained for NER on trade directories are available on HuggingFace, each trained on a different dataset :
+- [das22-10-camembert_pretrained_finetuned_ref](): trained for NER on ~6000 directory entries manually corrected.
+- [das22-10-camembert_pretrained_finetuned_pero](): trained for NER on ~6000 directory entries extracted with PERO-OCR.
+- [das22-10-camembert_pretrained_finetuned_tess](): trained for NER on ~6000 directory entries extracted with Tesseract.
+
+
+
+### Training hyperparameters
+
+### Training results
+
+### Framework versions
+
+- Transformers 4.16.0.dev0
+- Pytorch 1.10.1+cu102
+- Datasets 1.17.0
+- Tokenizers 0.10.3
+

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "Jean-Baptiste/camembert-ner",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-LOC",
+    "2": "I-PER",
+    "3": "I-MISC",
+    "4": "I-ORG",
+    "5": "I-CARDINAL",
+    "6": "I-ACT",
+    "7": "I-TITRE",
+    "8": "I-FT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "I-ACT": 6,
+    "I-CARDINAL": 5,
+    "I-FT": 8,
+    "I-LOC": 1,
+    "I-MISC": 3,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "I-TITRE": 7,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c37d05b4b67c765a20a19167530cd720b44e79f8e38eb1c8f2993d3771b2c3d9
+size 880421605

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:772edbf0c9ac34190896b768916498be532e0720793fcf40175ffd001f264689
+size 440237809

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46225dc591f01a63d58b19f4a6bff66c967753d090e9698eede41c44a82a8a65
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2a41f0894d3f9924a73ab87921a32296a37ba780af39ec4b4bb5bd073c3579
+size 623

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

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": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "model_max_length": 512, "name_or_path": "Jean-Baptiste/camembert-ner", "special_tokens_map_file": "/root/.cache/huggingface/transformers/fe0e213c44079a9ee091098f81fff2941484006e9ba3001a9bf1ee9f87537599.cb3ec3a6c1200d181228d8825ae9767572abca54efa1bbb37fd83d721b2ef323", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.9654395191585274,
+  "best_model_checkpoint": "/content/drive/MyDrive/SODUCO/article_das_2022/42-experiment_2_finetuned_camembert/checkpoint-700",
+  "epoch": 1.8617021276595744,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "eval_accuracy": 0.9666871542716656,
+      "eval_f1": 0.9407993966817497,
+      "eval_loss": 0.23340629041194916,
+      "eval_precision": 0.9411542814032441,
+      "eval_recall": 0.9404447794949115,
+      "eval_runtime": 2.6624,
+      "eval_samples_per_second": 250.906,
+      "eval_steps_per_second": 15.776,
+      "step": 100
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.9729563614013522,
+      "eval_f1": 0.9542459047260402,
+      "eval_loss": 0.14227047562599182,
+      "eval_precision": 0.9533483822422875,
+      "eval_recall": 0.9551451187335093,
+      "eval_runtime": 2.474,
+      "eval_samples_per_second": 270.009,
+      "eval_steps_per_second": 16.977,
+      "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.9794714197910265,
+      "eval_f1": 0.9598046581517656,
+      "eval_loss": 0.10758526623249054,
+      "eval_precision": 0.9565705728191688,
+      "eval_recall": 0.9630606860158312,
+      "eval_runtime": 2.467,
+      "eval_samples_per_second": 270.769,
+      "eval_steps_per_second": 17.024,
+      "step": 300
+    },
+    {
+      "epoch": 1.06,
+      "eval_accuracy": 0.978119237861094,
+      "eval_f1": 0.9622393387187677,
+      "eval_loss": 0.10391023010015488,
+      "eval_precision": 0.9591760299625468,
+      "eval_recall": 0.9653222766679231,
+      "eval_runtime": 2.469,
+      "eval_samples_per_second": 270.56,
+      "eval_steps_per_second": 17.011,
+      "step": 400
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 9e-05,
+      "loss": 0.2217,
+      "step": 500
+    },
+    {
+      "epoch": 1.33,
+      "eval_accuracy": 0.9776275353411186,
+      "eval_f1": 0.9546053870785459,
+      "eval_loss": 0.0932990312576294,
+      "eval_precision": 0.954066265060241,
+      "eval_recall": 0.9551451187335093,
+      "eval_runtime": 2.5383,
+      "eval_samples_per_second": 263.164,
+      "eval_steps_per_second": 16.546,
+      "step": 500
+    },
+    {
+      "epoch": 1.6,
+      "eval_accuracy": 0.9740626920712969,
+      "eval_f1": 0.9599096555618294,
+      "eval_loss": 0.10465865582227707,
+      "eval_precision": 0.9586466165413534,
+      "eval_recall": 0.9611760271390878,
+      "eval_runtime": 2.4984,
+      "eval_samples_per_second": 267.37,
+      "eval_steps_per_second": 16.811,
+      "step": 600
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.9805777504609711,
+      "eval_f1": 0.9654395191585274,
+      "eval_loss": 0.08172685652971268,
+      "eval_precision": 0.9621864470235867,
+      "eval_recall": 0.9687146626460611,
+      "eval_runtime": 2.5163,
+      "eval_samples_per_second": 265.472,
+      "eval_steps_per_second": 16.691,
+      "step": 700
+    }
+  ],
+  "max_steps": 5000,
+  "num_train_epochs": 14,
+  "total_flos": 275154731817120.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce53345edc52d161ff77c93152d56d9996a5a3d0b7f610badc728a7974e419d
+size 3055