Update spaCy pipeline

.gitattributes

@@ -30,3 +30,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+fr_ner4archives_V3_camembert_base-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- spacy
+- token-classification
+language:
+- fr
+model-index:
+- name: fr_ner4archives_V3_camembert_base
+  results:
+  - task:
+      name: NER
+      type: token-classification
+    metrics:
+    - name: NER Precision
+      type: precision
+      value: 0.916087963
+    - name: NER Recall
+      type: recall
+      value: 0.92303207
+    - name: NER F Score
+      type: f_score
+      value: 0.9195469068
+---
+| Feature | Description |
+| --- | --- |
+| **Name** | `fr_ner4archives_V3_camembert_base` |
+| **Version** | `0.0.0` |
+| **spaCy** | `>=3.4.1,<3.5.0` |
+| **Default Pipeline** | `transformer`, `ner` |
+| **Components** | `transformer`, `ner` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | n/a |
+| **Author** | [n/a]() |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (5 labels for 1 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`ner`** | `EVENT`, `LOCATION`, `ORGANISATION`, `PERSON`, `TITLE` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `ENTS_F` | 91.95 |
+| `ENTS_P` | 91.61 |
+| `ENTS_R` | 92.30 |
+| `TRANSFORMER_LOSS` | 395487.28 |
+| `NER_LOSS` | 11238.70 |

config.cfg

@@ -0,0 +1,145 @@
+[paths]
+train = "/drive/MyDrive/spaCy/data_train/train.spacy"
+dev = "/drive/MyDrive/spaCy/data_train/dev.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = "pytorch"
+seed = 0
+
+[nlp]
+lang = "fr"
+pipeline = ["transformer","ner"]
+batch_size = 128
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+
+[components]
+
+[components.ner]
+factory = "ner"
+incorrect_spans_key = null
+moves = null
+scorer = {"@scorers":"spacy.ner_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = false
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.transformer]
+factory = "transformer"
+max_batch_items = 4096
+set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
+
+[components.transformer.model]
+@architectures = "spacy-transformers.TransformerModel.v3"
+name = "camembert-base"
+mixed_precision = false
+
+[components.transformer.model.get_spans]
+@span_getters = "spacy-transformers.strided_spans.v1"
+window = 128
+stride = 96
+
+[components.transformer.model.grad_scaler_config]
+
+[components.transformer.model.tokenizer_config]
+use_fast = true
+
+[components.transformer.model.transformer_config]
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+accumulate_gradient = 3
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_padded.v1"
+discard_oversize = true
+size = 2000
+buffer = 256
+get_length = null
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.00005
+
+[training.score_weights]
+ents_f = 1.0
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]

fr_ner4archives_V3_camembert_base-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919aca257e4b2342a3773e7dcc3442b30f2ac50c4a3466d5ecda5e0e337ea396
+size 393539880

meta.json

@@ -0,0 +1,78 @@
+{
+  "lang":"fr",
+  "name":"ner4archives_V3_camembert_base",
+  "version":"0.0.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.4.1,<3.5.0",
+  "spacy_git_version":"Unknown",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "transformer":[
+
+    ],
+    "ner":[
+      "EVENT",
+      "LOCATION",
+      "ORGANISATION",
+      "PERSON",
+      "TITLE"
+    ]
+  },
+  "pipeline":[
+    "transformer",
+    "ner"
+  ],
+  "components":[
+    "transformer",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "ents_f":0.9195469068,
+    "ents_p":0.916087963,
+    "ents_r":0.92303207,
+    "ents_per_type":{
+      "PERSON":{
+        "p":0.9466666667,
+        "r":0.9502868069,
+        "f":0.9484732824
+      },
+      "LOCATION":{
+        "p":0.9378330373,
+        "r":0.9428571429,
+        "f":0.9403383793
+      },
+      "ORGANISATION":{
+        "p":0.8839590444,
+        "r":0.8900343643,
+        "f":0.8869863014
+      },
+      "TITLE":{
+        "p":0.875,
+        "r":0.8909090909,
+        "f":0.8828828829
+      },
+      "EVENT":{
+        "p":0.4545454545,
+        "r":0.4545454545,
+        "f":0.4545454545
+      }
+    },
+    "transformer_loss":3954.8727757427,
+    "ner_loss":112.3869945505
+  },
+  "requirements":[
+    "spacy-transformers>=1.1.8,<1.2.0"
+  ]
+}

ner/cfg

@@ -0,0 +1,13 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":1,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

ner/moves

@@ -0,0 +1 @@
+��moves�
X{"0":{},"1":{"PERSON":3649,"LOCATION":3166,"TITLE":2698,"ORGANISATION":2352,"EVENT":81},"2":{"PERSON":3649,"LOCATION":3166,"TITLE":2698,"ORGANISATION":2352,"EVENT":81},"3":{"PERSON":3649,"LOCATION":3166,"TITLE":2698,"ORGANISATION":2352,"EVENT":81},"4":{"PERSON":3649,"LOCATION":3166,"TITLE":2698,"ORGANISATION":2352,"EVENT":81,"":1},"5":{"":1}}�cfg��neg_key�

transformer/cfg

@@ -0,0 +1,3 @@
+{
+  "max_batch_items":4096
+}

transformer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535d453087fd545584eb8773dfca76ebff1316b13a7bd953bb7ea428cb5637de
+size 445802618

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}