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

.gitignore

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

config.json

@@ -0,0 +1,78 @@
+{
+  "_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": "AB",
+    "1": "AUX",
+    "2": "CC",
+    "3": "CD",
+    "4": "DBL",
+    "5": "DT",
+    "6": "ETC",
+    "7": "IN",
+    "8": "JJ",
+    "9": "KAN",
+    "10": "M",
+    "11": "NN",
+    "12": "PA",
+    "13": "PN",
+    "14": "PRO",
+    "15": "QT",
+    "16": "RB",
+    "17": "RPN",
+    "18": "SYM",
+    "19": "UH",
+    "20": "VB",
+    "21": "VB_JJ",
+    "22": "VCOM"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "AB": 0,
+    "AUX": 1,
+    "CC": 2,
+    "CD": 3,
+    "DBL": 4,
+    "DT": 5,
+    "ETC": 6,
+    "IN": 7,
+    "JJ": 8,
+    "KAN": 9,
+    "M": 10,
+    "NN": 11,
+    "PA": 12,
+    "PN": 13,
+    "PRO": 14,
+    "QT": 15,
+    "RB": 16,
+    "RPN": 17,
+    "SYM": 18,
+    "UH": 19,
+    "VB": 20,
+    "VB_JJ": 21,
+    "VCOM": 22
+  },
+  "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": "4.30.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d6981352255a726ed67d27bec28a89350094d84a9b1749ef48130d08a090dd8
+size 1109955693

runs/Jul12_05-28-20_9f2134707861/events.out.tfevents.1689139729.9f2134707861.1472.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8fcbc3c0e2e22b21058481196485fbc1f1fffbe7819c012365547e78766e99
+size 5266

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:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "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": 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:ade1ca0da4c01dcd5685eaea7c6f46634b8a779a1ba806add0b12665d7503c1f
+size 3963