Training in progress, epoch 1

config.json

@@ -0,0 +1,88 @@
+{
+  "_name_or_path": "almanach/camembert-base",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-age",
+    "1": "I-age",
+    "2": "B-birth_date",
+    "3": "I-birth_date",
+    "4": "B-civil_status",
+    "5": "I-civil_status",
+    "6": "B-education_level",
+    "7": "I-education_level",
+    "8": "B-employer",
+    "9": "I-employer",
+    "10": "B-firstname",
+    "11": "I-firstname",
+    "12": "B-link",
+    "13": "I-link",
+    "14": "B-lob",
+    "15": "I-lob",
+    "16": "B-maiden_name",
+    "17": "I-maiden_name",
+    "18": "B-nationality",
+    "19": "I-nationality",
+    "20": "B-observation",
+    "21": "I-observation",
+    "22": "B-occupation",
+    "23": "I-occupation",
+    "24": "B-surname",
+    "25": "I-surname",
+    "26": "B-surname_household",
+    "27": "I-surname_household"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-age": 0,
+    "B-birth_date": 2,
+    "B-civil_status": 4,
+    "B-education_level": 6,
+    "B-employer": 8,
+    "B-firstname": 10,
+    "B-link": 12,
+    "B-lob": 14,
+    "B-maiden_name": 16,
+    "B-nationality": 18,
+    "B-observation": 20,
+    "B-occupation": 22,
+    "B-surname": 24,
+    "B-surname_household": 26,
+    "I-age": 1,
+    "I-birth_date": 3,
+    "I-civil_status": 5,
+    "I-education_level": 7,
+    "I-employer": 9,
+    "I-firstname": 11,
+    "I-link": 13,
+    "I-lob": 15,
+    "I-maiden_name": 17,
+    "I-nationality": 19,
+    "I-observation": 21,
+    "I-occupation": 23,
+    "I-surname": 25,
+    "I-surname_household": 27
+  },
+  "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": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732c0e6a4fc2f68fac1c65a1d62bb7157539a1f5759e5037c529abac9df10911
+size 440235496

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,83 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<unk>NOTUSED",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<unk>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcc0497671b292d291ad0923d9ee5153cdaef581a349e5c04ce3d14c36ef8da
+size 4920