Training in progress, epoch 1

config.json

@@ -0,0 +1,55 @@
+{
+ "_name_or_path": "camembert/camembert-base",
+ "architectures": [
+ "CamembertForTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "bos_token_id": 0,
+ "classifier_dropout": null,
+ "eos_token_id": 2,
+ "eos_token_ids": 0,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "O",
+ "1": "B-PER",
+ "2": "I-PER",
+ "3": "B-ORG",
+ "4": "I-ORG",
+ "5": "B-LOC",
+ "6": "I-LOC",
+ "7": "B-MISC",
+ "8": "I-MISC",
+ "9": "B-DATE",
+ "10": "I-DATE"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "B-DATE": 9,
+ "B-LOC": 5,
+ "B-MISC": 7,
+ "B-ORG": 3,
+ "B-PER": 1,
+ "I-DATE": 10,
+ "I-LOC": 6,
+ "I-MISC": 8,
+ "I-ORG": 4,
+ "I-PER": 2,
+ "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": 0,
+ "position_embedding_type": "absolute",
+ "torch_dtype": "float32",
+ "transformers_version": "4.33.0.dev0",
+ "type_vocab_size": 1,
+ "use_cache": true,
+ "vocab_size": 32005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1629afced49b1ce282812a91e067063f3cfa6a1eccb37a89bad618a87de3ee5
+size 440227561

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 +1,19 @@
+{
+ "additional_special_tokens": [
+ "<s>NOTUSED",
+ "</s>NOTUSED"
+ ],
+ "bos_token": "<s>",
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "mask_token": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+ "additional_special_tokens": [
+ "<s>NOTUSED",
+ "</s>NOTUSED"
+ ],
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "mask_token": {
+ "__type": "AddedToken",
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "CamembertTokenizer",
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71af795e7a5d08295dbaf1964080f8475fa91701649b206c2659b6dc095c08c
+size 4027