Uploading model files

.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 +1,607 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66",
+    "67": "LABEL_67",
+    "68": "LABEL_68",
+    "69": "LABEL_69",
+    "70": "LABEL_70",
+    "71": "LABEL_71",
+    "72": "LABEL_72",
+    "73": "LABEL_73",
+    "74": "LABEL_74",
+    "75": "LABEL_75",
+    "76": "LABEL_76",
+    "77": "LABEL_77",
+    "78": "LABEL_78",
+    "79": "LABEL_79",
+    "80": "LABEL_80",
+    "81": "LABEL_81",
+    "82": "LABEL_82",
+    "83": "LABEL_83",
+    "84": "LABEL_84",
+    "85": "LABEL_85",
+    "86": "LABEL_86",
+    "87": "LABEL_87",
+    "88": "LABEL_88",
+    "89": "LABEL_89",
+    "90": "LABEL_90",
+    "91": "LABEL_91",
+    "92": "LABEL_92",
+    "93": "LABEL_93",
+    "94": "LABEL_94",
+    "95": "LABEL_95",
+    "96": "LABEL_96",
+    "97": "LABEL_97",
+    "98": "LABEL_98",
+    "99": "LABEL_99",
+    "100": "LABEL_100",
+    "101": "LABEL_101",
+    "102": "LABEL_102",
+    "103": "LABEL_103",
+    "104": "LABEL_104",
+    "105": "LABEL_105",
+    "106": "LABEL_106",
+    "107": "LABEL_107",
+    "108": "LABEL_108",
+    "109": "LABEL_109",
+    "110": "LABEL_110",
+    "111": "LABEL_111",
+    "112": "LABEL_112",
+    "113": "LABEL_113",
+    "114": "LABEL_114",
+    "115": "LABEL_115",
+    "116": "LABEL_116",
+    "117": "LABEL_117",
+    "118": "LABEL_118",
+    "119": "LABEL_119",
+    "120": "LABEL_120",
+    "121": "LABEL_121",
+    "122": "LABEL_122",
+    "123": "LABEL_123",
+    "124": "LABEL_124",
+    "125": "LABEL_125",
+    "126": "LABEL_126",
+    "127": "LABEL_127",
+    "128": "LABEL_128",
+    "129": "LABEL_129",
+    "130": "LABEL_130",
+    "131": "LABEL_131",
+    "132": "LABEL_132",
+    "133": "LABEL_133",
+    "134": "LABEL_134",
+    "135": "LABEL_135",
+    "136": "LABEL_136",
+    "137": "LABEL_137",
+    "138": "LABEL_138",
+    "139": "LABEL_139",
+    "140": "LABEL_140",
+    "141": "LABEL_141",
+    "142": "LABEL_142",
+    "143": "LABEL_143",
+    "144": "LABEL_144",
+    "145": "LABEL_145",
+    "146": "LABEL_146",
+    "147": "LABEL_147",
+    "148": "LABEL_148",
+    "149": "LABEL_149",
+    "150": "LABEL_150",
+    "151": "LABEL_151",
+    "152": "LABEL_152",
+    "153": "LABEL_153",
+    "154": "LABEL_154",
+    "155": "LABEL_155",
+    "156": "LABEL_156",
+    "157": "LABEL_157",
+    "158": "LABEL_158",
+    "159": "LABEL_159",
+    "160": "LABEL_160",
+    "161": "LABEL_161",
+    "162": "LABEL_162",
+    "163": "LABEL_163",
+    "164": "LABEL_164",
+    "165": "LABEL_165",
+    "166": "LABEL_166",
+    "167": "LABEL_167",
+    "168": "LABEL_168",
+    "169": "LABEL_169",
+    "170": "LABEL_170",
+    "171": "LABEL_171",
+    "172": "LABEL_172",
+    "173": "LABEL_173",
+    "174": "LABEL_174",
+    "175": "LABEL_175",
+    "176": "LABEL_176",
+    "177": "LABEL_177",
+    "178": "LABEL_178",
+    "179": "LABEL_179",
+    "180": "LABEL_180",
+    "181": "LABEL_181",
+    "182": "LABEL_182",
+    "183": "LABEL_183",
+    "184": "LABEL_184",
+    "185": "LABEL_185",
+    "186": "LABEL_186",
+    "187": "LABEL_187",
+    "188": "LABEL_188",
+    "189": "LABEL_189",
+    "190": "LABEL_190",
+    "191": "LABEL_191",
+    "192": "LABEL_192",
+    "193": "LABEL_193",
+    "194": "LABEL_194",
+    "195": "LABEL_195",
+    "196": "LABEL_196",
+    "197": "LABEL_197",
+    "198": "LABEL_198",
+    "199": "LABEL_199",
+    "200": "LABEL_200",
+    "201": "LABEL_201",
+    "202": "LABEL_202",
+    "203": "LABEL_203",
+    "204": "LABEL_204",
+    "205": "LABEL_205",
+    "206": "LABEL_206",
+    "207": "LABEL_207",
+    "208": "LABEL_208",
+    "209": "LABEL_209",
+    "210": "LABEL_210",
+    "211": "LABEL_211",
+    "212": "LABEL_212",
+    "213": "LABEL_213",
+    "214": "LABEL_214",
+    "215": "LABEL_215",
+    "216": "LABEL_216",
+    "217": "LABEL_217",
+    "218": "LABEL_218",
+    "219": "LABEL_219",
+    "220": "LABEL_220",
+    "221": "LABEL_221",
+    "222": "LABEL_222",
+    "223": "LABEL_223",
+    "224": "LABEL_224",
+    "225": "LABEL_225",
+    "226": "LABEL_226",
+    "227": "LABEL_227",
+    "228": "LABEL_228",
+    "229": "LABEL_229",
+    "230": "LABEL_230",
+    "231": "LABEL_231",
+    "232": "LABEL_232",
+    "233": "LABEL_233",
+    "234": "LABEL_234",
+    "235": "LABEL_235",
+    "236": "LABEL_236",
+    "237": "LABEL_237",
+    "238": "LABEL_238",
+    "239": "LABEL_239",
+    "240": "LABEL_240",
+    "241": "LABEL_241",
+    "242": "LABEL_242",
+    "243": "LABEL_243",
+    "244": "LABEL_244",
+    "245": "LABEL_245",
+    "246": "LABEL_246",
+    "247": "LABEL_247",
+    "248": "LABEL_248",
+    "249": "LABEL_249",
+    "250": "LABEL_250",
+    "251": "LABEL_251",
+    "252": "LABEL_252",
+    "253": "LABEL_253",
+    "254": "LABEL_254",
+    "255": "LABEL_255",
+    "256": "LABEL_256",
+    "257": "LABEL_257",
+    "258": "LABEL_258",
+    "259": "LABEL_259",
+    "260": "LABEL_260",
+    "261": "LABEL_261",
+    "262": "LABEL_262",
+    "263": "LABEL_263",
+    "264": "LABEL_264",
+    "265": "LABEL_265",
+    "266": "LABEL_266",
+    "267": "LABEL_267",
+    "268": "LABEL_268",
+    "269": "LABEL_269",
+    "270": "LABEL_270",
+    "271": "LABEL_271",
+    "272": "LABEL_272",
+    "273": "LABEL_273",
+    "274": "LABEL_274",
+    "275": "LABEL_275",
+    "276": "LABEL_276",
+    "277": "LABEL_277",
+    "278": "LABEL_278",
+    "279": "LABEL_279",
+    "280": "LABEL_280",
+    "281": "LABEL_281",
+    "282": "LABEL_282",
+    "283": "LABEL_283",
+    "284": "LABEL_284",
+    "285": "LABEL_285",
+    "286": "LABEL_286"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_100": 100,
+    "LABEL_101": 101,
+    "LABEL_102": 102,
+    "LABEL_103": 103,
+    "LABEL_104": 104,
+    "LABEL_105": 105,
+    "LABEL_106": 106,
+    "LABEL_107": 107,
+    "LABEL_108": 108,
+    "LABEL_109": 109,
+    "LABEL_11": 11,
+    "LABEL_110": 110,
+    "LABEL_111": 111,
+    "LABEL_112": 112,
+    "LABEL_113": 113,
+    "LABEL_114": 114,
+    "LABEL_115": 115,
+    "LABEL_116": 116,
+    "LABEL_117": 117,
+    "LABEL_118": 118,
+    "LABEL_119": 119,
+    "LABEL_12": 12,
+    "LABEL_120": 120,
+    "LABEL_121": 121,
+    "LABEL_122": 122,
+    "LABEL_123": 123,
+    "LABEL_124": 124,
+    "LABEL_125": 125,
+    "LABEL_126": 126,
+    "LABEL_127": 127,
+    "LABEL_128": 128,
+    "LABEL_129": 129,
+    "LABEL_13": 13,
+    "LABEL_130": 130,
+    "LABEL_131": 131,
+    "LABEL_132": 132,
+    "LABEL_133": 133,
+    "LABEL_134": 134,
+    "LABEL_135": 135,
+    "LABEL_136": 136,
+    "LABEL_137": 137,
+    "LABEL_138": 138,
+    "LABEL_139": 139,
+    "LABEL_14": 14,
+    "LABEL_140": 140,
+    "LABEL_141": 141,
+    "LABEL_142": 142,
+    "LABEL_143": 143,
+    "LABEL_144": 144,
+    "LABEL_145": 145,
+    "LABEL_146": 146,
+    "LABEL_147": 147,
+    "LABEL_148": 148,
+    "LABEL_149": 149,
+    "LABEL_15": 15,
+    "LABEL_150": 150,
+    "LABEL_151": 151,
+    "LABEL_152": 152,
+    "LABEL_153": 153,
+    "LABEL_154": 154,
+    "LABEL_155": 155,
+    "LABEL_156": 156,
+    "LABEL_157": 157,
+    "LABEL_158": 158,
+    "LABEL_159": 159,
+    "LABEL_16": 16,
+    "LABEL_160": 160,
+    "LABEL_161": 161,
+    "LABEL_162": 162,
+    "LABEL_163": 163,
+    "LABEL_164": 164,
+    "LABEL_165": 165,
+    "LABEL_166": 166,
+    "LABEL_167": 167,
+    "LABEL_168": 168,
+    "LABEL_169": 169,
+    "LABEL_17": 17,
+    "LABEL_170": 170,
+    "LABEL_171": 171,
+    "LABEL_172": 172,
+    "LABEL_173": 173,
+    "LABEL_174": 174,
+    "LABEL_175": 175,
+    "LABEL_176": 176,
+    "LABEL_177": 177,
+    "LABEL_178": 178,
+    "LABEL_179": 179,
+    "LABEL_18": 18,
+    "LABEL_180": 180,
+    "LABEL_181": 181,
+    "LABEL_182": 182,
+    "LABEL_183": 183,
+    "LABEL_184": 184,
+    "LABEL_185": 185,
+    "LABEL_186": 186,
+    "LABEL_187": 187,
+    "LABEL_188": 188,
+    "LABEL_189": 189,
+    "LABEL_19": 19,
+    "LABEL_190": 190,
+    "LABEL_191": 191,
+    "LABEL_192": 192,
+    "LABEL_193": 193,
+    "LABEL_194": 194,
+    "LABEL_195": 195,
+    "LABEL_196": 196,
+    "LABEL_197": 197,
+    "LABEL_198": 198,
+    "LABEL_199": 199,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_200": 200,
+    "LABEL_201": 201,
+    "LABEL_202": 202,
+    "LABEL_203": 203,
+    "LABEL_204": 204,
+    "LABEL_205": 205,
+    "LABEL_206": 206,
+    "LABEL_207": 207,
+    "LABEL_208": 208,
+    "LABEL_209": 209,
+    "LABEL_21": 21,
+    "LABEL_210": 210,
+    "LABEL_211": 211,
+    "LABEL_212": 212,
+    "LABEL_213": 213,
+    "LABEL_214": 214,
+    "LABEL_215": 215,
+    "LABEL_216": 216,
+    "LABEL_217": 217,
+    "LABEL_218": 218,
+    "LABEL_219": 219,
+    "LABEL_22": 22,
+    "LABEL_220": 220,
+    "LABEL_221": 221,
+    "LABEL_222": 222,
+    "LABEL_223": 223,
+    "LABEL_224": 224,
+    "LABEL_225": 225,
+    "LABEL_226": 226,
+    "LABEL_227": 227,
+    "LABEL_228": 228,
+    "LABEL_229": 229,
+    "LABEL_23": 23,
+    "LABEL_230": 230,
+    "LABEL_231": 231,
+    "LABEL_232": 232,
+    "LABEL_233": 233,
+    "LABEL_234": 234,
+    "LABEL_235": 235,
+    "LABEL_236": 236,
+    "LABEL_237": 237,
+    "LABEL_238": 238,
+    "LABEL_239": 239,
+    "LABEL_24": 24,
+    "LABEL_240": 240,
+    "LABEL_241": 241,
+    "LABEL_242": 242,
+    "LABEL_243": 243,
+    "LABEL_244": 244,
+    "LABEL_245": 245,
+    "LABEL_246": 246,
+    "LABEL_247": 247,
+    "LABEL_248": 248,
+    "LABEL_249": 249,
+    "LABEL_25": 25,
+    "LABEL_250": 250,
+    "LABEL_251": 251,
+    "LABEL_252": 252,
+    "LABEL_253": 253,
+    "LABEL_254": 254,
+    "LABEL_255": 255,
+    "LABEL_256": 256,
+    "LABEL_257": 257,
+    "LABEL_258": 258,
+    "LABEL_259": 259,
+    "LABEL_26": 26,
+    "LABEL_260": 260,
+    "LABEL_261": 261,
+    "LABEL_262": 262,
+    "LABEL_263": 263,
+    "LABEL_264": 264,
+    "LABEL_265": 265,
+    "LABEL_266": 266,
+    "LABEL_267": 267,
+    "LABEL_268": 268,
+    "LABEL_269": 269,
+    "LABEL_27": 27,
+    "LABEL_270": 270,
+    "LABEL_271": 271,
+    "LABEL_272": 272,
+    "LABEL_273": 273,
+    "LABEL_274": 274,
+    "LABEL_275": 275,
+    "LABEL_276": 276,
+    "LABEL_277": 277,
+    "LABEL_278": 278,
+    "LABEL_279": 279,
+    "LABEL_28": 28,
+    "LABEL_280": 280,
+    "LABEL_281": 281,
+    "LABEL_282": 282,
+    "LABEL_283": 283,
+    "LABEL_284": 284,
+    "LABEL_285": 285,
+    "LABEL_286": 286,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
+    "LABEL_75": 75,
+    "LABEL_76": 76,
+    "LABEL_77": 77,
+    "LABEL_78": 78,
+    "LABEL_79": 79,
+    "LABEL_8": 8,
+    "LABEL_80": 80,
+    "LABEL_81": 81,
+    "LABEL_82": 82,
+    "LABEL_83": 83,
+    "LABEL_84": 84,
+    "LABEL_85": 85,
+    "LABEL_86": 86,
+    "LABEL_87": 87,
+    "LABEL_88": 88,
+    "LABEL_89": 89,
+    "LABEL_9": 9,
+    "LABEL_90": 90,
+    "LABEL_91": 91,
+    "LABEL_92": 92,
+    "LABEL_93": 93,
+    "LABEL_94": 94,
+    "LABEL_95": 95,
+    "LABEL_96": 96,
+    "LABEL_97": 97,
+    "LABEL_98": 98,
+    "LABEL_99": 99
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0",
+  "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 sha256:7d1b8985ba44fee353b0ad4b51311a283ae3003daa480445de422012e47f592e
+size 2236679850

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 +1,21 @@
+{
+  "add_prefix_space": true,
+  "bos_token": "<s>",
+  "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,
+  "name_or_path": "xlm-roberta-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,295 @@
+{
+  "best_metric": 0.9710087370929309,
+  "best_model_checkpoint": ".//debugged_en_ewt_ses_udpipe_16_0.1_0.00002_15_04-23-24_01-15/checkpoint-10803",
+  "epoch": 14.999398677089598,
+  "global_step": 12465,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.985832550994282e-05,
+      "loss": 0.8748,
+      "step": 831
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9727829995913363,
+      "eval_f1": 0.9206887946094336,
+      "eval_loss": 0.11471811681985855,
+      "eval_precision": 0.9245188452285485,
+      "eval_recall": 0.9168903469529774,
+      "eval_runtime": 8.5451,
+      "eval_samples_per_second": 194.614,
+      "eval_steps_per_second": 24.341,
+      "step": 831
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.8439873687804047e-05,
+      "loss": 0.074,
+      "step": 1662
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9862280343277483,
+      "eval_f1": 0.9563490092863883,
+      "eval_loss": 0.06378430128097534,
+      "eval_precision": 0.9554475094264735,
+      "eval_recall": 0.9572522119494979,
+      "eval_runtime": 9.0509,
+      "eval_samples_per_second": 183.738,
+      "eval_steps_per_second": 22.981,
+      "step": 1662
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.7021421865665273e-05,
+      "loss": 0.0375,
+      "step": 2493
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9880261544748672,
+      "eval_f1": 0.961840405445692,
+      "eval_loss": 0.054762206971645355,
+      "eval_precision": 0.9614582298599385,
+      "eval_recall": 0.9622228849786261,
+      "eval_runtime": 8.6908,
+      "eval_samples_per_second": 191.352,
+      "eval_steps_per_second": 23.933,
+      "step": 2493
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.5602970043526503e-05,
+      "loss": 0.0236,
+      "step": 3324
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9895790764201062,
+      "eval_f1": 0.9648930880159124,
+      "eval_loss": 0.054631613194942474,
+      "eval_precision": 0.9652770868570292,
+      "eval_recall": 0.964509394572025,
+      "eval_runtime": 8.7121,
+      "eval_samples_per_second": 190.884,
+      "eval_steps_per_second": 23.875,
+      "step": 3324
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.4184518221387728e-05,
+      "loss": 0.0155,
+      "step": 4155
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.989865140988966,
+      "eval_f1": 0.9674321916452189,
+      "eval_loss": 0.0665346086025238,
+      "eval_precision": 0.9633316904879251,
+      "eval_recall": 0.971567750273387,
+      "eval_runtime": 8.672,
+      "eval_samples_per_second": 191.767,
+      "eval_steps_per_second": 23.985,
+      "step": 4155
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.2766066399248956e-05,
+      "loss": 0.0102,
+      "step": 4986
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.989865140988966,
+      "eval_f1": 0.9660317302431989,
+      "eval_loss": 0.06522596627473831,
+      "eval_precision": 0.9665605095541401,
+      "eval_recall": 0.9655035291778507,
+      "eval_runtime": 9.1046,
+      "eval_samples_per_second": 182.656,
+      "eval_steps_per_second": 22.846,
+      "step": 4986
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.1347614577110182e-05,
+      "loss": 0.0067,
+      "step": 5817
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9908868001634654,
+      "eval_f1": 0.9694357754990836,
+      "eval_loss": 0.06391981989145279,
+      "eval_precision": 0.9661334913112164,
+      "eval_recall": 0.9727607118003778,
+      "eval_runtime": 9.6275,
+      "eval_samples_per_second": 172.735,
+      "eval_steps_per_second": 21.605,
+      "step": 5817
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 9.92916275497141e-06,
+      "loss": 0.005,
+      "step": 6648
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9906007355946056,
+      "eval_f1": 0.9695436507936508,
+      "eval_loss": 0.06800998747348785,
+      "eval_precision": 0.9675279675279675,
+      "eval_recall": 0.971567750273387,
+      "eval_runtime": 8.544,
+      "eval_samples_per_second": 194.64,
+      "eval_steps_per_second": 24.345,
+      "step": 6648
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 8.510710932832637e-06,
+      "loss": 0.0033,
+      "step": 7479
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9906824683285655,
+      "eval_f1": 0.9697029899672196,
+      "eval_loss": 0.07487699389457703,
+      "eval_precision": 0.9689330024813896,
+      "eval_recall": 0.9704742022069788,
+      "eval_runtime": 8.5275,
+      "eval_samples_per_second": 195.016,
+      "eval_steps_per_second": 24.392,
+      "step": 7479
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 7.092259110693864e-06,
+      "loss": 0.0027,
+      "step": 8310
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9906824683285655,
+      "eval_f1": 0.9683280381254964,
+      "eval_loss": 0.0723545178771019,
+      "eval_precision": 0.9670798215171046,
+      "eval_recall": 0.9695794810617357,
+      "eval_runtime": 8.98,
+      "eval_samples_per_second": 185.189,
+      "eval_steps_per_second": 23.163,
+      "step": 8310
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 5.673807288555091e-06,
+      "loss": 0.0018,
+      "step": 9141
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.9910911319983653,
+      "eval_f1": 0.969461852183428,
+      "eval_loss": 0.07421588897705078,
+      "eval_precision": 0.9700408082014532,
+      "eval_recall": 0.9688835868376579,
+      "eval_runtime": 9.1698,
+      "eval_samples_per_second": 181.357,
+      "eval_steps_per_second": 22.683,
+      "step": 9141
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 4.255355466416318e-06,
+      "loss": 0.0018,
+      "step": 9972
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.9909276665304454,
+      "eval_f1": 0.9694831013916502,
+      "eval_loss": 0.07263504713773727,
+      "eval_precision": 0.9693867408806282,
+      "eval_recall": 0.9695794810617357,
+      "eval_runtime": 8.7552,
+      "eval_samples_per_second": 189.945,
+      "eval_steps_per_second": 23.757,
+      "step": 9972
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 2.8369036442775456e-06,
+      "loss": 0.001,
+      "step": 10803
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.9913363302002453,
+      "eval_f1": 0.9710087370929309,
+      "eval_loss": 0.07499531656503677,
+      "eval_precision": 0.9697570649479424,
+      "eval_recall": 0.9722636444974649,
+      "eval_runtime": 8.5127,
+      "eval_samples_per_second": 195.356,
+      "eval_steps_per_second": 24.434,
+      "step": 10803
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 1.4184518221387728e-06,
+      "loss": 0.0008,
+      "step": 11634
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.9908868001634654,
+      "eval_f1": 0.969507350019865,
+      "eval_loss": 0.07384610921144485,
+      "eval_precision": 0.968641460752208,
+      "eval_recall": 0.9703747887463963,
+      "eval_runtime": 8.7778,
+      "eval_samples_per_second": 189.456,
+      "eval_steps_per_second": 23.696,
+      "step": 11634
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.0,
+      "loss": 0.0007,
+      "step": 12465
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.9910093992644053,
+      "eval_f1": 0.969751154820444,
+      "eval_loss": 0.07460830360651016,
+      "eval_precision": 0.9690291840381179,
+      "eval_recall": 0.9704742022069788,
+      "eval_runtime": 8.9902,
+      "eval_samples_per_second": 184.979,
+      "eval_steps_per_second": 23.136,
+      "step": 12465
+    },
+    {
+      "epoch": 15.0,
+      "step": 12465,
+      "total_flos": 1.722226508123076e+16,
+      "train_loss": 0.07061179929405056,
+      "train_runtime": 5194.8123,
+      "train_samples_per_second": 38.398,
+      "train_steps_per_second": 2.4
+    }
+  ],
+  "max_steps": 12465,
+  "num_train_epochs": 15,
+  "total_flos": 1.722226508123076e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa98f2d4bfc73ad56508e9f98a753769d3751ea5bb42e9460a56956694ab2da9
+size 3832