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 +1,126 @@
+{
+  "_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": "ADVI",
+    "1": "ADVN",
+    "2": "ADVP",
+    "3": "ADVS",
+    "4": "CFQC",
+    "5": "CLTV",
+    "6": "CMTR",
+    "7": "CMTR@PUNC",
+    "8": "CNIT",
+    "9": "CVBL",
+    "10": "DCNM",
+    "11": "DDAC",
+    "12": "DDAN",
+    "13": "DDAQ",
+    "14": "DDBQ",
+    "15": "DIAC",
+    "16": "DIAQ",
+    "17": "DIBQ",
+    "18": "DONM",
+    "19": "EAFF",
+    "20": "EITT",
+    "21": "FIXN",
+    "22": "FIXV",
+    "23": "JCMP",
+    "24": "JCRG",
+    "25": "JSBR",
+    "26": "NCMN",
+    "27": "NCNM",
+    "28": "NEG",
+    "29": "NLBL",
+    "30": "NONM",
+    "31": "NPRP",
+    "32": "NTTL",
+    "33": "PDMN",
+    "34": "PNTR",
+    "35": "PPRS",
+    "36": "PREL",
+    "37": "PUNC",
+    "38": "RPRE",
+    "39": "VACT",
+    "40": "VATT",
+    "41": "VSTA",
+    "42": "XVAE",
+    "43": "XVAM",
+    "44": "XVBB",
+    "45": "XVBM",
+    "46": "XVMM"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADVI": 0,
+    "ADVN": 1,
+    "ADVP": 2,
+    "ADVS": 3,
+    "CFQC": 4,
+    "CLTV": 5,
+    "CMTR": 6,
+    "CMTR@PUNC": 7,
+    "CNIT": 8,
+    "CVBL": 9,
+    "DCNM": 10,
+    "DDAC": 11,
+    "DDAN": 12,
+    "DDAQ": 13,
+    "DDBQ": 14,
+    "DIAC": 15,
+    "DIAQ": 16,
+    "DIBQ": 17,
+    "DONM": 18,
+    "EAFF": 19,
+    "EITT": 20,
+    "FIXN": 21,
+    "FIXV": 22,
+    "JCMP": 23,
+    "JCRG": 24,
+    "JSBR": 25,
+    "NCMN": 26,
+    "NCNM": 27,
+    "NEG": 28,
+    "NLBL": 29,
+    "NONM": 30,
+    "NPRP": 31,
+    "NTTL": 32,
+    "PDMN": 33,
+    "PNTR": 34,
+    "PPRS": 35,
+    "PREL": 36,
+    "PUNC": 37,
+    "RPRE": 38,
+    "VACT": 39,
+    "VATT": 40,
+    "VSTA": 41,
+    "XVAE": 42,
+    "XVAM": 43,
+    "XVBB": 44,
+    "XVBM": 45,
+    "XVMM": 46
+  },
+  "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": "4.47.1",
+  "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 sha256:57af2a061694f2d2c9a30bbe6086c4f193545bef84a0e313cc25d40d3dda30ae
+size 1109980852

runs/Jan21_16-20-54_5202292f931c/events.out.tfevents.1737476456.5202292f931c.2249.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581b97b9dc032f214160b622339353a21519fe184c5e62a4a65800bdf86b898e
+size 7378

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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 416,
+  "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 sha256:328b2330ae8387de06e14b9dfecfead6851fa5f5e2795a029131ec864be0e47b
+size 5304