Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,82 @@
+{
+  "_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-PERSON",
+    "2": "I-PERSON",
+    "3": "L-PERSON",
+    "4": "U-PERSON",
+    "5": "B-NORP",
+    "6": "I-NORP",
+    "7": "L-NORP",
+    "8": "U-NORP",
+    "9": "B-DATE",
+    "10": "I-DATE",
+    "11": "L-DATE",
+    "12": "U-DATE",
+    "13": "B-USERID",
+    "14": "I-USERID",
+    "15": "L-USERID",
+    "16": "U-USERID",
+    "17": "B-ORG",
+    "18": "I-ORG",
+    "19": "L-ORG",
+    "20": "U-ORG",
+    "21": "B-LOCATION",
+    "22": "I-LOCATION",
+    "23": "L-LOCATION",
+    "24": "U-LOCATION"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-DATE": 9,
+    "B-LOCATION": 21,
+    "B-NORP": 5,
+    "B-ORG": 17,
+    "B-PERSON": 1,
+    "B-USERID": 13,
+    "I-DATE": 10,
+    "I-LOCATION": 22,
+    "I-NORP": 6,
+    "I-ORG": 18,
+    "I-PERSON": 2,
+    "I-USERID": 14,
+    "L-DATE": 11,
+    "L-LOCATION": 23,
+    "L-NORP": 7,
+    "L-ORG": 19,
+    "L-PERSON": 3,
+    "L-USERID": 15,
+    "O": 0,
+    "U-DATE": 12,
+    "U-LOCATION": 24,
+    "U-NORP": 8,
+    "U-ORG": 20,
+    "U-PERSON": 4,
+    "U-USERID": 16
+  },
+  "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": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff4e6866afd8d7d0cea2f186cff76315c60b59091dbb11a30a6d245c7873603
+size 1109913172

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 +1,15 @@
+{
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
+size 17082854

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "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>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce11e2619671e22aae03f31fd3517d5f0705f42580cac973eeae844a5b5c182
+size 4536