artemis13fowl's picture
Training in progress, epoch 1
1549a10 verified
{
"architectures": [
"ModernBertForSequenceClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 50281,
"classifier_activation": "gelu",
"classifier_bias": false,
"classifier_dropout": 0.0,
"classifier_pooling": "mean",
"cls_token_id": 50281,
"decoder_bias": true,
"deterministic_flash_attn": false,
"dtype": "float32",
"embedding_dropout": 0.0,
"eos_token_id": 50282,
"global_attn_every_n_layers": 3,
"global_rope_theta": 160000.0,
"gradient_checkpointing": false,
"hidden_activation": "gelu",
"hidden_size": 768,
"id2label": {
"0": 7,
"1": 17,
"10": 58,
"100": 231,
"101": 232,
"102": 233,
"103": 234,
"104": 235,
"105": 236,
"106": 237,
"107": 238,
"108": 239,
"109": 240,
"11": 64,
"110": 241,
"111": 242,
"112": 243,
"113": 244,
"114": 245,
"115": 246,
"116": 247,
"117": 248,
"118": 249,
"119": 250,
"12": 67,
"120": 251,
"121": 252,
"122": 253,
"123": 254,
"124": 255,
"125": 256,
"126": 257,
"127": 258,
"128": 259,
"129": 260,
"13": 83,
"130": 261,
"131": 262,
"132": 263,
"133": 264,
"134": 265,
"135": 266,
"136": 267,
"137": 268,
"138": 269,
"139": 270,
"14": 91,
"140": 271,
"141": 272,
"142": 273,
"143": 274,
"144": 275,
"145": 276,
"146": 277,
"147": 278,
"148": 279,
"149": 280,
"15": 100,
"150": 281,
"151": 282,
"152": 283,
"153": 284,
"154": 154,
"155": 155,
"156": 156,
"157": 157,
"158": 158,
"159": 159,
"16": 102,
"160": 160,
"161": 161,
"162": 162,
"163": 163,
"164": 164,
"165": 165,
"166": 166,
"167": 167,
"168": 168,
"169": 169,
"17": 126,
"170": 170,
"171": 171,
"172": 172,
"173": 173,
"174": 174,
"175": 175,
"176": 176,
"177": 177,
"178": 178,
"179": 179,
"18": 127,
"180": 180,
"181": 181,
"182": 182,
"183": 183,
"184": 184,
"185": 185,
"186": 186,
"187": 187,
"188": 188,
"189": 189,
"19": 128,
"190": 190,
"191": 191,
"192": 192,
"193": 193,
"194": 194,
"195": 195,
"196": 196,
"197": 197,
"198": 198,
"199": 199,
"2": 31,
"20": 131,
"200": 200,
"201": 201,
"202": 202,
"203": 203,
"204": 204,
"205": 205,
"206": 206,
"207": 207,
"208": 208,
"209": 209,
"21": 135,
"210": 210,
"211": 211,
"212": 212,
"213": 213,
"214": 214,
"215": 215,
"216": 216,
"217": 217,
"218": 218,
"219": 219,
"22": 138,
"220": 220,
"221": 221,
"222": 222,
"223": 223,
"224": 224,
"225": 225,
"226": 226,
"227": 227,
"228": 228,
"229": 229,
"23": 153,
"230": 230,
"231": 231,
"232": 232,
"233": 233,
"234": 234,
"235": 235,
"236": 236,
"237": 237,
"238": 238,
"239": 239,
"24": 154,
"240": 240,
"241": 241,
"242": 242,
"243": 243,
"244": 244,
"245": 245,
"246": 246,
"247": 247,
"248": 248,
"249": 249,
"25": 155,
"250": 250,
"251": 251,
"252": 252,
"253": 253,
"254": 254,
"255": 255,
"256": 256,
"257": 257,
"258": 258,
"259": 259,
"26": 156,
"260": 260,
"261": 261,
"262": 262,
"263": 263,
"264": 264,
"265": 265,
"266": 266,
"267": 267,
"268": 268,
"269": 269,
"27": 157,
"270": 270,
"271": 271,
"272": 272,
"273": 273,
"274": 274,
"275": 275,
"276": 276,
"277": 277,
"278": 278,
"279": 279,
"28": 158,
"280": 280,
"281": 281,
"282": 282,
"283": 283,
"284": 284,
"29": 159,
"3": 38,
"30": 160,
"31": 161,
"32": 162,
"33": 163,
"34": 164,
"35": 165,
"36": 166,
"37": 167,
"38": 168,
"39": 169,
"4": 39,
"40": 171,
"41": 172,
"42": 173,
"43": 174,
"44": 175,
"45": 176,
"46": 177,
"47": 178,
"48": 179,
"49": 180,
"5": 40,
"50": 181,
"51": 182,
"52": 183,
"53": 184,
"54": 185,
"55": 186,
"56": 187,
"57": 188,
"58": 189,
"59": 190,
"6": 43,
"60": 191,
"61": 192,
"62": 193,
"63": 194,
"64": 195,
"65": 196,
"66": 197,
"67": 198,
"68": 199,
"69": 200,
"7": 48,
"70": 201,
"71": 202,
"72": 203,
"73": 204,
"74": 205,
"75": 206,
"76": 207,
"77": 208,
"78": 209,
"79": 210,
"8": 53,
"80": 211,
"81": 212,
"82": 213,
"83": 214,
"84": 215,
"85": 216,
"86": 217,
"87": 218,
"88": 219,
"89": 220,
"9": 56,
"90": 221,
"91": 222,
"92": 223,
"93": 224,
"94": 225,
"95": 226,
"96": 227,
"97": 228,
"98": 229,
"99": 230
},
"initializer_cutoff_factor": 2.0,
"initializer_range": 0.02,
"intermediate_size": 1152,
"label2id": {
"7": "0",
"17": "1",
"31": "2",
"38": "3",
"39": "4",
"40": "5",
"43": "6",
"48": "7",
"53": "8",
"56": "9",
"58": "10",
"64": "11",
"67": "12",
"83": "13",
"91": "14",
"100": "15",
"102": "16",
"126": "17",
"127": "18",
"128": "19",
"131": "20",
"135": "21",
"138": "22",
"153": "23",
"154": "154",
"155": "155",
"156": "156",
"157": "157",
"158": "158",
"159": "159",
"160": "160",
"161": "161",
"162": "162",
"163": "163",
"164": "164",
"165": "165",
"166": "166",
"167": "167",
"168": "168",
"169": "169",
"170": "170",
"171": "171",
"172": "172",
"173": "173",
"174": "174",
"175": "175",
"176": "176",
"177": "177",
"178": "178",
"179": "179",
"180": "180",
"181": "181",
"182": "182",
"183": "183",
"184": "184",
"185": "185",
"186": "186",
"187": "187",
"188": "188",
"189": "189",
"190": "190",
"191": "191",
"192": "192",
"193": "193",
"194": "194",
"195": "195",
"196": "196",
"197": "197",
"198": "198",
"199": "199",
"200": "200",
"201": "201",
"202": "202",
"203": "203",
"204": "204",
"205": "205",
"206": "206",
"207": "207",
"208": "208",
"209": "209",
"210": "210",
"211": "211",
"212": "212",
"213": "213",
"214": "214",
"215": "215",
"216": "216",
"217": "217",
"218": "218",
"219": "219",
"220": "220",
"221": "221",
"222": "222",
"223": "223",
"224": "224",
"225": "225",
"226": "226",
"227": "227",
"228": "228",
"229": "229",
"230": "230",
"231": "231",
"232": "232",
"233": "233",
"234": "234",
"235": "235",
"236": "236",
"237": "237",
"238": "238",
"239": "239",
"240": "240",
"241": "241",
"242": "242",
"243": "243",
"244": "244",
"245": "245",
"246": "246",
"247": "247",
"248": "248",
"249": "249",
"250": "250",
"251": "251",
"252": "252",
"253": "253",
"254": "254",
"255": "255",
"256": "256",
"257": "257",
"258": "258",
"259": "259",
"260": "260",
"261": "261",
"262": "262",
"263": "263",
"264": "264",
"265": "265",
"266": "266",
"267": "267",
"268": "268",
"269": "269",
"270": "270",
"271": "271",
"272": "272",
"273": "273",
"274": "274",
"275": "275",
"276": "276",
"277": "277",
"278": "278",
"279": "279",
"280": "280",
"281": "281",
"282": "282",
"283": "283",
"284": "284"
},
"layer_norm_eps": 1e-05,
"local_attention": 128,
"local_rope_theta": 10000.0,
"max_position_embeddings": 8192,
"mlp_bias": false,
"mlp_dropout": 0.0,
"model_type": "modernbert",
"norm_bias": false,
"norm_eps": 1e-05,
"num_attention_heads": 12,
"num_hidden_layers": 22,
"pad_token_id": 50283,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"repad_logits_with_grad": false,
"sep_token_id": 50282,
"sparse_pred_ignore_index": -100,
"sparse_prediction": false,
"transformers_version": "4.57.3",
"vocab_size": 50368
}