Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "vinai/phobert-large",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "I-UNITCALIBRATOR",
+    "2": "I-TRANSPORTATION",
+    "3": "I-ORGANIZATION",
+    "4": "I-ORGAN",
+    "5": "I-OCCUPATION",
+    "6": "I-MEDDEVICETECHNIQUE",
+    "7": "I-LOCATION",
+    "8": "I-GENDER",
+    "9": "I-DRUGCHEMICAL",
+    "10": "I-DIESEASE",
+    "11": "I-DATETIME",
+    "12": "I-AGE",
+    "13": "B-UNITCALIBRATOR",
+    "14": "B-TRANSPORTATION",
+    "15": "B-ORGANIZATION",
+    "16": "B-ORGAN",
+    "17": "B-OCCUPATION",
+    "18": "B-MEDDEVICETECHNIQUE",
+    "19": "B-LOCATION",
+    "20": "B-GENDER",
+    "21": "B-DRUGCHEMICAL",
+    "22": "B-DIESEASE",
+    "23": "B-DATETIME",
+    "24": "B-AGE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-AGE": 24,
+    "B-DATETIME": 23,
+    "B-DIESEASE": 22,
+    "B-DRUGCHEMICAL": 21,
+    "B-GENDER": 20,
+    "B-LOCATION": 19,
+    "B-MEDDEVICETECHNIQUE": 18,
+    "B-OCCUPATION": 17,
+    "B-ORGAN": 16,
+    "B-ORGANIZATION": 15,
+    "B-TRANSPORTATION": 14,
+    "B-UNITCALIBRATOR": 13,
+    "I-AGE": 12,
+    "I-DATETIME": 11,
+    "I-DIESEASE": 10,
+    "I-DRUGCHEMICAL": 9,
+    "I-GENDER": 8,
+    "I-LOCATION": 7,
+    "I-MEDDEVICETECHNIQUE": 6,
+    "I-OCCUPATION": 5,
+    "I-ORGAN": 4,
+    "I-ORGANIZATION": 3,
+    "I-TRANSPORTATION": 2,
+    "I-UNITCALIBRATOR": 1,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddaf36afc86c629ef5f653e80a9c01c573b37b4f7c33d4b55bfe9083998e75e
+size 1472692518

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "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 +1,12 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d6456673bccfa9c2a96db2d5a574135f533d1c482ab346f24742ed41f151a9f
+size 4408