Initial Commit

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-DATE",
+    "2": "I-DATE",
+    "3": "B-PER",
+    "4": "I-PER",
+    "5": "B-ORG",
+    "6": "I-ORG",
+    "7": "B-LOC",
+    "8": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DATE": 1,
+    "B-LOC": 7,
+    "B-ORG": 5,
+    "B-PER": 3,
+    "I-DATE": 2,
+    "I-LOC": 8,
+    "I-ORG": 6,
+    "I-PER": 4,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt

@@ -0,0 +1,15 @@
+f1 = 0.9266770670826834
+loss = 0.10732872315803924
+precision = 0.922360248447205
+recall = 0.9310344827586207
+report =               precision    recall  f1-score   support
+
+        DATE       0.90      0.94      0.92       109
+         LOC       0.94      0.95      0.94        63
+         ORG       0.76      0.82      0.79        45
+         PER       0.94      0.94      0.94       421
+
+   micro avg       0.92      0.93      0.93       638
+   macro avg       0.89      0.91      0.90       638
+weighted avg       0.92      0.93      0.93       638
+

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172227e1643d435a5f9bd18baaf4928c3d35c18ea07032a4675539a3992b2811
+size 1109924593

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

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

test_results.txt

@@ -0,0 +1,15 @@
+f1 = 0.888888888888889
+loss = 0.10679786939769352
+precision = 0.881283422459893
+recall = 0.8966267682263329
+report =               precision    recall  f1-score   support
+
+        DATE       0.91      0.93      0.92       184
+         LOC       0.86      0.88      0.87       258
+         ORG       0.82      0.82      0.82       210
+         PER       0.93      0.94      0.94       267
+
+   micro avg       0.88      0.90      0.89       919
+   macro avg       0.88      0.90      0.89       919
+weighted avg       0.88      0.90      0.89       919
+

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3577052f9cf6db4f5e475a3506be3c863f24f8a5b97b8b8977b45aba85c0bca
+size 1583