Training in progress, step 2500

config.json

@@ -0,0 +1,276 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-EN",
+    "2": "I-EN",
+    "3": "B-ES",
+    "4": "I-ES",
+    "5": "B-FR",
+    "6": "I-FR",
+    "7": "B-DE",
+    "8": "I-DE",
+    "9": "B-IT",
+    "10": "I-IT",
+    "11": "B-PT",
+    "12": "I-PT",
+    "13": "B-NL",
+    "14": "I-NL",
+    "15": "B-VI",
+    "16": "I-VI",
+    "17": "B-TR",
+    "18": "I-TR",
+    "19": "B-LA",
+    "20": "I-LA",
+    "21": "B-ID",
+    "22": "I-ID",
+    "23": "B-MS",
+    "24": "I-MS",
+    "25": "B-AF",
+    "26": "I-AF",
+    "27": "B-SQ",
+    "28": "I-SQ",
+    "29": "B-IS",
+    "30": "I-IS",
+    "31": "B-NO",
+    "32": "I-NO",
+    "33": "B-SV",
+    "34": "I-SV",
+    "35": "B-DA",
+    "36": "I-DA",
+    "37": "B-FI",
+    "38": "I-FI",
+    "39": "B-HU",
+    "40": "I-HU",
+    "41": "B-PL",
+    "42": "I-PL",
+    "43": "B-CS",
+    "44": "I-CS",
+    "45": "B-RO",
+    "46": "I-RO",
+    "47": "B-RU",
+    "48": "I-RU",
+    "49": "B-BG",
+    "50": "I-BG",
+    "51": "B-UK",
+    "52": "I-UK",
+    "53": "B-SR",
+    "54": "I-SR",
+    "55": "B-BE",
+    "56": "I-BE",
+    "57": "B-KK",
+    "58": "I-KK",
+    "59": "B-MK",
+    "60": "I-MK",
+    "61": "B-MN",
+    "62": "I-MN",
+    "63": "B-ZH",
+    "64": "I-ZH",
+    "65": "B-JA",
+    "66": "I-JA",
+    "67": "B-KO",
+    "68": "I-KO",
+    "69": "B-HI",
+    "70": "I-HI",
+    "71": "B-UR",
+    "72": "I-UR",
+    "73": "B-BN",
+    "74": "I-BN",
+    "75": "B-TA",
+    "76": "I-TA",
+    "77": "B-TE",
+    "78": "I-TE",
+    "79": "B-MR",
+    "80": "I-MR",
+    "81": "B-GU",
+    "82": "I-GU",
+    "83": "B-KN",
+    "84": "I-KN",
+    "85": "B-ML",
+    "86": "I-ML",
+    "87": "B-PA",
+    "88": "I-PA",
+    "89": "B-AS",
+    "90": "I-AS",
+    "91": "B-OR",
+    "92": "I-OR",
+    "93": "B-AR",
+    "94": "I-AR",
+    "95": "B-FA",
+    "96": "I-FA",
+    "97": "B-PS",
+    "98": "I-PS",
+    "99": "B-SD",
+    "100": "I-SD",
+    "101": "B-UG",
+    "102": "I-UG",
+    "103": "B-EL",
+    "104": "I-EL",
+    "105": "B-HE",
+    "106": "I-HE",
+    "107": "B-HY",
+    "108": "I-HY",
+    "109": "B-KA",
+    "110": "I-KA",
+    "111": "B-AM",
+    "112": "I-AM",
+    "113": "B-KM",
+    "114": "I-KM",
+    "115": "B-LO",
+    "116": "I-LO",
+    "117": "B-MY",
+    "118": "I-MY",
+    "119": "B-TH",
+    "120": "I-TH"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "B-AF": 25,
+    "B-AM": 111,
+    "B-AR": 93,
+    "B-AS": 89,
+    "B-BE": 55,
+    "B-BG": 49,
+    "B-BN": 73,
+    "B-CS": 43,
+    "B-DA": 35,
+    "B-DE": 7,
+    "B-EL": 103,
+    "B-EN": 1,
+    "B-ES": 3,
+    "B-FA": 95,
+    "B-FI": 37,
+    "B-FR": 5,
+    "B-GU": 81,
+    "B-HE": 105,
+    "B-HI": 69,
+    "B-HU": 39,
+    "B-HY": 107,
+    "B-ID": 21,
+    "B-IS": 29,
+    "B-IT": 9,
+    "B-JA": 65,
+    "B-KA": 109,
+    "B-KK": 57,
+    "B-KM": 113,
+    "B-KN": 83,
+    "B-KO": 67,
+    "B-LA": 19,
+    "B-LO": 115,
+    "B-MK": 59,
+    "B-ML": 85,
+    "B-MN": 61,
+    "B-MR": 79,
+    "B-MS": 23,
+    "B-MY": 117,
+    "B-NL": 13,
+    "B-NO": 31,
+    "B-OR": 91,
+    "B-PA": 87,
+    "B-PL": 41,
+    "B-PS": 97,
+    "B-PT": 11,
+    "B-RO": 45,
+    "B-RU": 47,
+    "B-SD": 99,
+    "B-SQ": 27,
+    "B-SR": 53,
+    "B-SV": 33,
+    "B-TA": 75,
+    "B-TE": 77,
+    "B-TH": 119,
+    "B-TR": 17,
+    "B-UG": 101,
+    "B-UK": 51,
+    "B-UR": 71,
+    "B-VI": 15,
+    "B-ZH": 63,
+    "I-AF": 26,
+    "I-AM": 112,
+    "I-AR": 94,
+    "I-AS": 90,
+    "I-BE": 56,
+    "I-BG": 50,
+    "I-BN": 74,
+    "I-CS": 44,
+    "I-DA": 36,
+    "I-DE": 8,
+    "I-EL": 104,
+    "I-EN": 2,
+    "I-ES": 4,
+    "I-FA": 96,
+    "I-FI": 38,
+    "I-FR": 6,
+    "I-GU": 82,
+    "I-HE": 106,
+    "I-HI": 70,
+    "I-HU": 40,
+    "I-HY": 108,
+    "I-ID": 22,
+    "I-IS": 30,
+    "I-IT": 10,
+    "I-JA": 66,
+    "I-KA": 110,
+    "I-KK": 58,
+    "I-KM": 114,
+    "I-KN": 84,
+    "I-KO": 68,
+    "I-LA": 20,
+    "I-LO": 116,
+    "I-MK": 60,
+    "I-ML": 86,
+    "I-MN": 62,
+    "I-MR": 80,
+    "I-MS": 24,
+    "I-MY": 118,
+    "I-NL": 14,
+    "I-NO": 32,
+    "I-OR": 92,
+    "I-PA": 88,
+    "I-PL": 42,
+    "I-PS": 98,
+    "I-PT": 12,
+    "I-RO": 46,
+    "I-RU": 48,
+    "I-SD": 100,
+    "I-SQ": 28,
+    "I-SR": 54,
+    "I-SV": 34,
+    "I-TA": 76,
+    "I-TE": 78,
+    "I-TH": 120,
+    "I-TR": 18,
+    "I-UG": 102,
+    "I-UK": 52,
+    "I-UR": 72,
+    "I-VI": 16,
+    "I-ZH": 64,
+    "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",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5635568371b562d79768dac086e3fec00f9287b52421686e44377b9483b618e8
+size 1110208452

runs/Apr08_21-58-34_7f354bfaa6bd/events.out.tfevents.1775685514.7f354bfaa6bd.7667.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db53f4673144228d48addbed242133f6b7978b84b4143428debafa2794083980
+size 14294

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332c79b9e42197a913e833293f90c223841d350870518d1a8bd6764806c8f19f
+size 5201