Training in progress, epoch 1

config.json

@@ -0,0 +1,245 @@
+{
+  "_name_or_path": "Buseak/spellcorrector_17_02_050_qwerty",
+  "architectures": [
+    "CanineForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 57344,
+  "downsampling_rate": 4,
+  "eos_token_id": 57345,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "1",
+    "1": "9",
+    "2": "3",
+    "3": "6",
+    "4": " ",
+    "5": "y",
+    "6": "l",
+    "7": "\u0131",
+    "8": "n",
+    "9": "d",
+    "10": "a",
+    "11": "z",
+    "12": ".",
+    "13": "\u00df",
+    "14": "NaN",
+    "15": "A",
+    "16": "e",
+    "17": "t",
+    "18": "k",
+    "19": "i",
+    "20": "m",
+    "21": "g",
+    "22": "\u015f",
+    "23": "b",
+    "24": "r",
+    "25": "h",
+    "26": "\u00e7",
+    "27": "O",
+    "28": "s",
+    "29": "u",
+    "30": "\u011f",
+    "31": "o",
+    "32": "\u00f6",
+    "33": "\u00fc",
+    "34": "v",
+    "35": "R",
+    "36": ",",
+    "37": "B",
+    "38": "'",
+    "39": "p",
+    "40": "\u00e2",
+    "41": "\u00d6",
+    "42": "S",
+    "43": "-",
+    "44": "L",
+    "45": "c",
+    "46": "T",
+    "47": "w",
+    "48": "K",
+    "49": "0",
+    "50": "P",
+    "51": "?",
+    "52": "M",
+    "53": "f",
+    "54": "Y",
+    "55": "7",
+    "56": "8",
+    "57": "U",
+    "58": "\"",
+    "59": "5",
+    "60": "N",
+    "61": "j",
+    "62": "H",
+    "63": "2",
+    "64": "\u0130",
+    "65": "D",
+    "66": "G",
+    "67": "I",
+    "68": "C",
+    "69": "F",
+    "70": "\u00c7",
+    "71": ";",
+    "72": "x",
+    "73": "E",
+    "74": "(",
+    "75": ")",
+    "76": "4",
+    "77": "\u00dc",
+    "78": "!",
+    "79": "J",
+    "80": "V",
+    "81": "\u015e",
+    "82": ":",
+    "83": "Z",
+    "84": "W",
+    "85": "*",
+    "86": "/",
+    "87": "%",
+    "88": "|",
+    "89": "\u011e",
+    "90": "q",
+    "91": "\u00fb",
+    "92": "\u201c",
+    "93": "\u25a0",
+    "94": "\u00e8",
+    "95": "\u201d",
+    "96": "\u2019",
+    "97": "Q",
+    "98": "\u00c2",
+    "99": "X",
+    "100": "+",
+    "101": "=",
+    "102": "\u00e9",
+    "103": "\u00ce",
+    "104": "\u2014",
+    "105": ">"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    " ": 4,
+    "!": 78,
+    "\"": 58,
+    "%": 87,
+    "'": 38,
+    "(": 74,
+    ")": 75,
+    "*": 85,
+    "+": 100,
+    ",": 36,
+    "-": 43,
+    ".": 12,
+    "/": 86,
+    "0": 49,
+    "1": 0,
+    "2": 63,
+    "3": 2,
+    "4": 76,
+    "5": 59,
+    "6": 3,
+    "7": 55,
+    "8": 56,
+    "9": 1,
+    ":": 82,
+    ";": 71,
+    "=": 101,
+    ">": 105,
+    "?": 51,
+    "A": 15,
+    "B": 37,
+    "C": 68,
+    "D": 65,
+    "E": 73,
+    "F": 69,
+    "G": 66,
+    "H": 62,
+    "I": 67,
+    "J": 79,
+    "K": 48,
+    "L": 44,
+    "M": 52,
+    "N": 60,
+    "NaN": 14,
+    "O": 27,
+    "P": 50,
+    "Q": 97,
+    "R": 35,
+    "S": 42,
+    "T": 46,
+    "U": 57,
+    "V": 80,
+    "W": 84,
+    "X": 99,
+    "Y": 54,
+    "Z": 83,
+    "a": 10,
+    "b": 23,
+    "c": 45,
+    "d": 9,
+    "e": 16,
+    "f": 53,
+    "g": 21,
+    "h": 25,
+    "i": 19,
+    "j": 61,
+    "k": 18,
+    "l": 6,
+    "m": 20,
+    "n": 8,
+    "o": 31,
+    "p": 39,
+    "q": 90,
+    "r": 24,
+    "s": 28,
+    "t": 17,
+    "u": 29,
+    "v": 34,
+    "w": 47,
+    "x": 72,
+    "y": 5,
+    "z": 11,
+    "|": 88,
+    "\u00c2": 98,
+    "\u00c7": 70,
+    "\u00ce": 103,
+    "\u00d6": 41,
+    "\u00dc": 77,
+    "\u00df": 13,
+    "\u00e2": 40,
+    "\u00e7": 26,
+    "\u00e8": 94,
+    "\u00e9": 102,
+    "\u00f6": 32,
+    "\u00fb": 91,
+    "\u00fc": 33,
+    "\u011e": 89,
+    "\u011f": 30,
+    "\u0130": 64,
+    "\u0131": 7,
+    "\u015e": 81,
+    "\u015f": 22,
+    "\u2014": 104,
+    "\u2019": 96,
+    "\u201c": 92,
+    "\u201d": 95,
+    "\u25a0": 93
+  },
+  "layer_norm_eps": 1e-12,
+  "local_transformer_stride": 128,
+  "max_position_embeddings": 16384,
+  "model_type": "canine",
+  "num_attention_heads": 12,
+  "num_hash_buckets": 16384,
+  "num_hash_functions": 8,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 16,
+  "upsampling_kernel_size": 4,
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f002fcc5baac32a24b16fcaff2d2432b83f1294c05e01a631dd20118a57c7c98
+size 528687832

runs/Feb18_19-26-18_a5667bb2632c/events.out.tfevents.1708284379.a5667bb2632c.2424.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1968775933888f27b7bf52e3f01e7ce6267252d605ea344233aaff22713715ac
+size 8269

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "bos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "\u0000",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "\u0000",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57344": {
+      "content": "",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57345": {
+      "content": "",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57347": {
+      "content": "",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "",
+  "eos_token": "",
+  "mask_token": "",
+  "model_max_length": 2048,
+  "pad_token": "\u0000",
+  "sep_token": "",
+  "tokenizer_class": "CanineTokenizer"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5827a1bce7941c0a0d8deab0212dd0fbac28e099b6355667c932f975f1bd02
+size 4600