End of training

.gitignore

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

added_tokens.json

@@ -0,0 +1,36 @@
+{
+  "</ENTRY>": 32014,
+  "<ENTRY>": 32035,
+  "<break>": 32036,
+  "<hspace-10>": 32030,
+  "<hspace-1>": 32038,
+  "<hspace-2>": 32020,
+  "<hspace-3>": 32009,
+  "<hspace-4>": 32021,
+  "<hspace-5>": 32015,
+  "<hspace-6>": 32026,
+  "<hspace-7>": 32012,
+  "<hspace-8>": 32010,
+  "<hspace-9>": 32023,
+  "<lhspace-10>": 32024,
+  "<lhspace-1>": 32032,
+  "<lhspace-2>": 32025,
+  "<lhspace-3>": 32027,
+  "<lhspace-4>": 32028,
+  "<lhspace-5>": 32016,
+  "<lhspace-6>": 32008,
+  "<lhspace-7>": 32033,
+  "<lhspace-8>": 32007,
+  "<lhspace-9>": 32018,
+  "<rhspace-10>": 32013,
+  "<rhspace-1>": 32019,
+  "<rhspace-2>": 32017,
+  "<rhspace-3>": 32011,
+  "<rhspace-4>": 32006,
+  "<rhspace-5>": 32031,
+  "<rhspace-6>": 32037,
+  "<rhspace-7>": 32022,
+  "<rhspace-8>": 32029,
+  "<rhspace-9>": 32034,
+  "<textline>": 32005
+}

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "HueyNemud/das22-10-camembert_pretrained",
+  "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",
+    "9": "O+I-EBEGIN",
+    "10": "O+I-EEND",
+    "11": "I-LOC+I-EBEGIN",
+    "12": "I-LOC+I-EEND",
+    "13": "I-PER+I-EBEGIN",
+    "14": "I-PER+I-EEND",
+    "15": "I-CARDINAL+I-EBEGIN",
+    "16": "I-CARDINAL+I-EEND",
+    "17": "I-ACT+I-EBEGIN",
+    "18": "I-ACT+I-EEND",
+    "19": "I-TITRE+I-EBEGIN",
+    "20": "I-TITRE+I-EEND",
+    "21": "I-FT+I-EBEGIN",
+    "22": "I-FT+I-EEND"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "I-ACT": 6,
+    "I-ACT+I-EBEGIN": 17,
+    "I-ACT+I-EEND": 18,
+    "I-CARDINAL": 5,
+    "I-CARDINAL+I-EBEGIN": 15,
+    "I-CARDINAL+I-EEND": 16,
+    "I-FT": 8,
+    "I-FT+I-EBEGIN": 21,
+    "I-FT+I-EEND": 22,
+    "I-LOC": 1,
+    "I-LOC+I-EBEGIN": 11,
+    "I-LOC+I-EEND": 12,
+    "I-MISC": 3,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "I-PER+I-EBEGIN": 13,
+    "I-PER+I-EEND": 14,
+    "I-TITRE": 7,
+    "I-TITRE+I-EBEGIN": 19,
+    "I-TITRE+I-EEND": 20,
+    "O": 0,
+    "O+I-EBEGIN": 9,
+    "O+I-EEND": 10
+  },
+  "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": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32039
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d92ea622af8ef126305b04ea215b9d06712f428afafeed28a120d07a8defd2a
+size 440373357

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 +1,13 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "HueyNemud/das22-10-camembert_pretrained",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/lrde/home2/jchazalo/.cache/huggingface/transformers/fe0e213c44079a9ee091098f81fff2941484006e9ba3001a9bf1ee9f87537599.cb3ec3a6c1200d181228d8825ae9767572abca54efa1bbb37fd83d721b2ef323",
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a14576bea6a553fe82256417731c2de2e917c7fbfda4cbd4e482a033bef6a92
+size 3579