{ "batch_size": 64, "best_eval_metric_checkpoint_number": 6, "best_eval_metric_epoch": 4, "best_eval_metric_steps": 372, "best_eval_metric_value": 0.9799168109893799, "best_eval_test_metrics": { "combined": { "loss": 0.07570453733205795 }, "language": { "accuracy": 0.9817298650741577, "accuracy_micro": 0.9799426794052124, "loss": 0.07570453733205795, "roc_auc": 0.999114990234375 } }, "best_eval_train_metrics": { "combined": { "loss": 0.03008267655968666 }, "language": { "accuracy": 0.9913396835327148, "accuracy_micro": 0.9910488128662109, "loss": 0.03008267655968666, "roc_auc": 0.9997660517692566 } }, "best_eval_validation_metrics": { "combined": { "loss": 0.06920339167118073 }, "language": { "accuracy": 0.9799168109893799, "accuracy_micro": 0.9784792065620422, "loss": 0.06920339167118073, "roc_auc": 0.998852550983429 } }, "best_increase_batch_size_eval_metric": Infinity, "checkpoint_number": 10, "checkpoint_to_epoch": { "1": 1, "10": 5, "2": 1, "3": 2, "4": 2, "5": 3, "6": 3, "7": 4, "8": 4, "9": 5 }, "checkpoint_to_step": { "1": 93, "10": 465, "2": 93, "3": 186, "4": 186, "5": 279, "6": 279, "7": 372, "8": 372, "9": 465 }, "cumulative_checkpoint_token_usage": { "1": 2356558, "10": 11782790, "2": 2356558, "3": 4713116, "4": 4713116, "5": 7069674, "6": 7069674, "7": 9426232, "8": 9426232, "9": 11782790 }, "cumulative_step_token_usage": { "0": 25472, "1": 50944, "10": 280192, "100": 2560334, "101": 2585806, "102": 2611278, "103": 2636750, "104": 2662222, "105": 2687694, "106": 2713166, "107": 2738638, "108": 2764110, "109": 2789582, "11": 305664, "110": 2815054, "111": 2840526, "112": 2865998, "113": 2891470, "114": 2916942, "115": 2942414, "116": 2967886, "117": 2993358, "118": 3018830, "119": 3044302, "12": 331136, "120": 3069774, "121": 3095246, "122": 3120718, "123": 3146190, "124": 3171662, "125": 3197134, "126": 3222606, "127": 3248078, "128": 3273550, "129": 3299022, "13": 356608, "130": 3324494, "131": 3349966, "132": 3375438, "133": 3400910, "134": 3426382, "135": 3451854, "136": 3477326, "137": 3502798, "138": 3528270, "139": 3553742, "14": 382080, "140": 3579214, "141": 3604686, "142": 3630158, "143": 3655630, "144": 3681102, "145": 3706574, "146": 3732046, "147": 3757518, "148": 3782990, "149": 3808462, "15": 407552, "150": 3833934, "151": 3859406, "152": 3884878, "153": 3910350, "154": 3935822, "155": 3961294, "156": 3986766, "157": 4012238, "158": 4037710, "159": 4063182, "16": 433024, "160": 4088654, "161": 4114126, "162": 4139598, "163": 4165070, "164": 4190542, "165": 4216014, "166": 4241486, "167": 4266958, "168": 4292430, "169": 4317902, "17": 458496, "170": 4343374, "171": 4368846, "172": 4394318, "173": 4419790, "174": 4445262, "175": 4470734, "176": 4496206, "177": 4521678, "178": 4547150, "179": 4572622, "18": 483968, "180": 4598094, "181": 4623566, "182": 4649038, "183": 4674510, "184": 4699982, "185": 4713116, "186": 4738588, "187": 4764060, "188": 4789532, "189": 4815004, "19": 509440, "190": 4840476, "191": 4865948, "192": 4891420, "193": 4916892, "194": 4942364, "195": 4967836, "196": 4993308, "197": 5018780, "198": 5044252, "199": 5069724, "2": 76416, "20": 534912, "200": 5095196, "201": 5120668, "202": 5146140, "203": 5171612, "204": 5197084, "205": 5222556, "206": 5248028, "207": 5273500, "208": 5298972, "209": 5324444, "21": 560384, "210": 5349916, "211": 5375388, "212": 5400860, "213": 5426332, "214": 5451804, "215": 5477276, "216": 5502748, "217": 5528220, "218": 5553692, "219": 5579164, "22": 585856, "220": 5604636, "221": 5630108, "222": 5655580, "223": 5681052, "224": 5706524, "225": 5731996, "226": 5757468, "227": 5782940, "228": 5808412, "229": 5833884, "23": 611328, "230": 5859356, "231": 5884828, "232": 5910300, "233": 5935772, "234": 5961244, "235": 5986716, "236": 6012188, "237": 6037660, "238": 6063132, "239": 6088604, "24": 636800, "240": 6114076, "241": 6139548, "242": 6165020, "243": 6190492, "244": 6215964, "245": 6241436, "246": 6266908, "247": 6292380, "248": 6317852, "249": 6343324, "25": 662272, "250": 6368796, "251": 6394268, "252": 6419740, "253": 6445212, "254": 6470684, "255": 6496156, "256": 6521628, "257": 6547100, "258": 6572572, "259": 6598044, "26": 687744, "260": 6623516, "261": 6648988, "262": 6674460, "263": 6699932, "264": 6725404, "265": 6750876, "266": 6776348, "267": 6801820, "268": 6827292, "269": 6852764, "27": 713216, "270": 6878236, "271": 6903708, "272": 6929180, "273": 6954652, "274": 6980124, "275": 7005596, "276": 7031068, "277": 7056540, "278": 7069674, "279": 7095146, "28": 738688, "280": 7120618, "281": 7146090, "282": 7171562, "283": 7197034, "284": 7222506, "285": 7247978, "286": 7273450, "287": 7298922, "288": 7324394, "289": 7349866, "29": 764160, "290": 7375338, "291": 7400810, "292": 7426282, "293": 7451754, "294": 7477226, "295": 7502698, "296": 7528170, "297": 7553642, "298": 7579114, "299": 7604586, "3": 101888, "30": 789632, "300": 7630058, "301": 7655530, "302": 7681002, "303": 7706474, "304": 7731946, "305": 7757418, "306": 7782890, "307": 7808362, "308": 7833834, "309": 7859306, "31": 815104, "310": 7884778, "311": 7910250, "312": 7935722, "313": 7961194, "314": 7986666, "315": 8012138, "316": 8037610, "317": 8063082, "318": 8088554, "319": 8114026, "32": 840576, "320": 8139498, "321": 8164970, "322": 8190442, "323": 8215914, "324": 8241386, "325": 8266858, "326": 8292330, "327": 8317802, "328": 8343274, "329": 8368746, "33": 866048, "330": 8394218, "331": 8419690, "332": 8445162, "333": 8470634, "334": 8496106, "335": 8521578, "336": 8547050, "337": 8572522, "338": 8597994, "339": 8623466, "34": 891520, "340": 8648938, "341": 8674410, "342": 8699882, "343": 8725354, "344": 8750826, "345": 8776298, "346": 8801770, "347": 8827242, "348": 8852714, "349": 8878186, "35": 916992, "350": 8903658, "351": 8929130, "352": 8954602, "353": 8980074, "354": 9005546, "355": 9031018, "356": 9056490, "357": 9081962, "358": 9107434, "359": 9132906, "36": 942464, "360": 9158378, "361": 9183850, "362": 9209322, "363": 9234794, "364": 9260266, "365": 9285738, "366": 9311210, "367": 9336682, "368": 9362154, "369": 9387626, "37": 967936, "370": 9413098, "371": 9426232, "372": 9451704, "373": 9477176, "374": 9502648, "375": 9528120, "376": 9553592, "377": 9579064, "378": 9604536, "379": 9630008, "38": 993408, "380": 9655480, "381": 9680952, "382": 9706424, "383": 9731896, "384": 9757368, "385": 9782840, "386": 9808312, "387": 9833784, "388": 9859256, "389": 9884728, "39": 1018880, "390": 9910200, "391": 9935672, "392": 9961144, "393": 9986616, "394": 10012088, "395": 10037560, "396": 10063032, "397": 10088504, "398": 10113976, "399": 10139448, "4": 127360, "40": 1044352, "400": 10164920, "401": 10190392, "402": 10215864, "403": 10241336, "404": 10266808, "405": 10292280, "406": 10317752, "407": 10343224, "408": 10368696, "409": 10394168, "41": 1069824, "410": 10419640, "411": 10445112, "412": 10470584, "413": 10496056, "414": 10521528, "415": 10547000, "416": 10572472, "417": 10597944, "418": 10623416, "419": 10648888, "42": 1095296, "420": 10674360, "421": 10699832, "422": 10725304, "423": 10750776, "424": 10776248, "425": 10801720, "426": 10827192, "427": 10852664, "428": 10878136, "429": 10903608, "43": 1120768, "430": 10929080, "431": 10954552, "432": 10980024, "433": 11005496, "434": 11030968, "435": 11056440, "436": 11081912, "437": 11107384, "438": 11132856, "439": 11158328, "44": 1146240, "440": 11183800, "441": 11209272, "442": 11234744, "443": 11260216, "444": 11285688, "445": 11311160, "446": 11336632, "447": 11362104, "448": 11387576, "449": 11413048, "45": 1171712, "450": 11438520, "451": 11463992, "452": 11489464, "453": 11514936, "454": 11540408, "455": 11565880, "456": 11591352, "457": 11616824, "458": 11642296, "459": 11667768, "46": 1197184, "460": 11693240, "461": 11718712, "462": 11744184, "463": 11769656, "464": 11782790, "47": 1222656, "48": 1248128, "49": 1273600, "5": 152832, "50": 1299072, "51": 1324544, "52": 1350016, "53": 1375488, "54": 1400960, "55": 1426432, "56": 1451904, "57": 1477376, "58": 1502848, "59": 1528320, "6": 178304, "60": 1553792, "61": 1579264, "62": 1604736, "63": 1630208, "64": 1655680, "65": 1681152, "66": 1706624, "67": 1732096, "68": 1757568, "69": 1783040, "7": 203776, "70": 1808512, "71": 1833984, "72": 1859456, "73": 1884928, "74": 1910400, "75": 1935872, "76": 1961344, "77": 1986816, "78": 2012288, "79": 2037760, "8": 229248, "80": 2063232, "81": 2088704, "82": 2114176, "83": 2139648, "84": 2165120, "85": 2190592, "86": 2216064, "87": 2241536, "88": 2267008, "89": 2292480, "9": 254720, "90": 2317952, "91": 2343424, "92": 2356558, "93": 2382030, "94": 2407502, "95": 2432974, "96": 2458446, "97": 2483918, "98": 2509390, "99": 2534862 }, "epoch": 5, "incremental_checkpoint_token_usage": { "1": 2356558, "10": 0, "2": 0, "3": 2356558, "4": 0, "5": 2356558, "6": 0, "7": 2356558, "8": 0, "9": 2356558 }, "incremental_step_token_usage": { "0": 25472, "1": 25472, "10": 25472, "100": 25472, "101": 25472, "102": 25472, "103": 25472, "104": 25472, "105": 25472, "106": 25472, "107": 25472, "108": 25472, "109": 25472, "11": 25472, "110": 25472, "111": 25472, "112": 25472, "113": 25472, "114": 25472, "115": 25472, "116": 25472, "117": 25472, "118": 25472, "119": 25472, "12": 25472, "120": 25472, "121": 25472, "122": 25472, "123": 25472, "124": 25472, "125": 25472, "126": 25472, "127": 25472, "128": 25472, "129": 25472, "13": 25472, "130": 25472, "131": 25472, "132": 25472, "133": 25472, "134": 25472, "135": 25472, "136": 25472, "137": 25472, "138": 25472, "139": 25472, "14": 25472, "140": 25472, "141": 25472, "142": 25472, "143": 25472, "144": 25472, "145": 25472, "146": 25472, "147": 25472, "148": 25472, "149": 25472, "15": 25472, "150": 25472, "151": 25472, "152": 25472, "153": 25472, "154": 25472, "155": 25472, "156": 25472, "157": 25472, "158": 25472, "159": 25472, "16": 25472, "160": 25472, "161": 25472, "162": 25472, "163": 25472, "164": 25472, "165": 25472, "166": 25472, "167": 25472, "168": 25472, "169": 25472, "17": 25472, "170": 25472, "171": 25472, "172": 25472, "173": 25472, "174": 25472, "175": 25472, "176": 25472, "177": 25472, "178": 25472, "179": 25472, "18": 25472, "180": 25472, "181": 25472, "182": 25472, "183": 25472, "184": 25472, "185": 13134, "186": 25472, "187": 25472, "188": 25472, "189": 25472, "19": 25472, "190": 25472, "191": 25472, "192": 25472, "193": 25472, "194": 25472, "195": 25472, "196": 25472, "197": 25472, "198": 25472, "199": 25472, "2": 25472, "20": 25472, "200": 25472, "201": 25472, "202": 25472, "203": 25472, "204": 25472, "205": 25472, "206": 25472, "207": 25472, "208": 25472, "209": 25472, "21": 25472, "210": 25472, "211": 25472, "212": 25472, "213": 25472, "214": 25472, "215": 25472, "216": 25472, "217": 25472, "218": 25472, "219": 25472, "22": 25472, "220": 25472, "221": 25472, "222": 25472, "223": 25472, "224": 25472, "225": 25472, "226": 25472, "227": 25472, "228": 25472, "229": 25472, "23": 25472, "230": 25472, "231": 25472, "232": 25472, "233": 25472, "234": 25472, "235": 25472, "236": 25472, "237": 25472, "238": 25472, "239": 25472, "24": 25472, "240": 25472, "241": 25472, "242": 25472, "243": 25472, "244": 25472, "245": 25472, "246": 25472, "247": 25472, "248": 25472, "249": 25472, "25": 25472, "250": 25472, "251": 25472, "252": 25472, "253": 25472, "254": 25472, "255": 25472, "256": 25472, "257": 25472, "258": 25472, "259": 25472, "26": 25472, "260": 25472, "261": 25472, "262": 25472, "263": 25472, "264": 25472, "265": 25472, "266": 25472, "267": 25472, "268": 25472, "269": 25472, "27": 25472, "270": 25472, "271": 25472, "272": 25472, "273": 25472, "274": 25472, "275": 25472, "276": 25472, "277": 25472, "278": 13134, "279": 25472, "28": 25472, "280": 25472, "281": 25472, "282": 25472, "283": 25472, "284": 25472, "285": 25472, "286": 25472, "287": 25472, "288": 25472, "289": 25472, "29": 25472, "290": 25472, "291": 25472, "292": 25472, "293": 25472, "294": 25472, "295": 25472, "296": 25472, "297": 25472, "298": 25472, "299": 25472, "3": 25472, "30": 25472, "300": 25472, "301": 25472, "302": 25472, "303": 25472, "304": 25472, "305": 25472, "306": 25472, "307": 25472, "308": 25472, "309": 25472, "31": 25472, "310": 25472, "311": 25472, "312": 25472, "313": 25472, "314": 25472, "315": 25472, "316": 25472, "317": 25472, "318": 25472, "319": 25472, "32": 25472, "320": 25472, "321": 25472, "322": 25472, "323": 25472, "324": 25472, "325": 25472, "326": 25472, "327": 25472, "328": 25472, "329": 25472, "33": 25472, "330": 25472, "331": 25472, "332": 25472, "333": 25472, "334": 25472, "335": 25472, "336": 25472, "337": 25472, "338": 25472, "339": 25472, "34": 25472, "340": 25472, "341": 25472, "342": 25472, "343": 25472, "344": 25472, "345": 25472, "346": 25472, "347": 25472, "348": 25472, "349": 25472, "35": 25472, "350": 25472, "351": 25472, "352": 25472, "353": 25472, "354": 25472, "355": 25472, "356": 25472, "357": 25472, "358": 25472, "359": 25472, "36": 25472, "360": 25472, "361": 25472, "362": 25472, "363": 25472, "364": 25472, "365": 25472, "366": 25472, "367": 25472, "368": 25472, "369": 25472, "37": 25472, "370": 25472, "371": 13134, "372": 25472, "373": 25472, "374": 25472, "375": 25472, "376": 25472, "377": 25472, "378": 25472, "379": 25472, "38": 25472, "380": 25472, "381": 25472, "382": 25472, "383": 25472, "384": 25472, "385": 25472, "386": 25472, "387": 25472, "388": 25472, "389": 25472, "39": 25472, "390": 25472, "391": 25472, "392": 25472, "393": 25472, "394": 25472, "395": 25472, "396": 25472, "397": 25472, "398": 25472, "399": 25472, "4": 25472, "40": 25472, "400": 25472, "401": 25472, "402": 25472, "403": 25472, "404": 25472, "405": 25472, "406": 25472, "407": 25472, "408": 25472, "409": 25472, "41": 25472, "410": 25472, "411": 25472, "412": 25472, "413": 25472, "414": 25472, "415": 25472, "416": 25472, "417": 25472, "418": 25472, "419": 25472, "42": 25472, "420": 25472, "421": 25472, "422": 25472, "423": 25472, "424": 25472, "425": 25472, "426": 25472, "427": 25472, "428": 25472, "429": 25472, "43": 25472, "430": 25472, "431": 25472, "432": 25472, "433": 25472, "434": 25472, "435": 25472, "436": 25472, "437": 25472, "438": 25472, "439": 25472, "44": 25472, "440": 25472, "441": 25472, "442": 25472, "443": 25472, "444": 25472, "445": 25472, "446": 25472, "447": 25472, "448": 25472, "449": 25472, "45": 25472, "450": 25472, "451": 25472, "452": 25472, "453": 25472, "454": 25472, "455": 25472, "456": 25472, "457": 25472, "458": 25472, "459": 25472, "46": 25472, "460": 25472, "461": 25472, "462": 25472, "463": 25472, "464": 13134, "47": 25472, "48": 25472, "49": 25472, "5": 25472, "50": 25472, "51": 25472, "52": 25472, "53": 25472, "54": 25472, "55": 25472, "56": 25472, "57": 25472, "58": 25472, "59": 25472, "6": 25472, "60": 25472, "61": 25472, "62": 25472, "63": 25472, "64": 25472, "65": 25472, "66": 25472, "67": 25472, "68": 25472, "69": 25472, "7": 25472, "70": 25472, "71": 25472, "72": 25472, "73": 25472, "74": 25472, "75": 25472, "76": 25472, "77": 25472, "78": 25472, "79": 25472, "8": 25472, "80": 25472, "81": 25472, "82": 25472, "83": 25472, "84": 25472, "85": 25472, "86": 25472, "87": 25472, "88": 25472, "89": 25472, "9": 25472, "90": 25472, "91": 25472, "92": 13134, "93": 25472, "94": 25472, "95": 25472, "96": 25472, "97": 25472, "98": 25472, "99": 25472 }, "last_improvement_steps": 93, "last_increase_batch_size": 0, "last_increase_batch_size_eval_metric_improvement": 0, "last_increase_batch_size_steps": 0, "last_learning_rate_reduction": 0, "last_learning_rate_reduction_steps": 0, "learning_rate": 0.001, "llm_eval_examples": {}, "num_increases_batch_size": 0, "num_reductions_learning_rate": 0, "steps": 465, "test_metrics": { "combined": { "loss": [ [ 1, 93, 0.23742298781871796 ], [ 2, 186, 0.21031303703784943 ], [ 3, 279, 0.12192762643098831 ], [ 4, 372, 0.07570453733205795 ], [ 5, 465, 0.05710742995142937 ] ] }, "language": { "accuracy": [ [ 1, 93, 0.924312949180603 ], [ 2, 186, 0.9528379440307617 ], [ 3, 279, 0.961493730545044 ], [ 4, 372, 0.9817298650741577 ], [ 5, 465, 0.9708698987960815 ] ], "accuracy_micro": [ [ 1, 93, 0.9312320947647095 ], [ 2, 186, 0.9484240412712097 ], [ 3, 279, 0.9598853588104248 ], [ 4, 372, 0.9799426794052124 ], [ 5, 465, 0.9742120504379272 ] ], "loss": [ [ 1, 93, 0.23742298781871796 ], [ 2, 186, 0.21031303703784943 ], [ 3, 279, 0.12192762643098831 ], [ 4, 372, 0.07570453733205795 ], [ 5, 465, 0.05710742995142937 ] ], "roc_auc": [ [ 1, 93, 0.9985259175300598 ], [ 2, 186, 0.9976196885108948 ], [ 3, 279, 0.9982259273529053 ], [ 4, 372, 0.999114990234375 ], [ 5, 465, 0.9991633296012878 ] ] } }, "total_tokens_used": 11782790, "train_metrics": { "combined": { "loss": [ [ 1, 93, 2.6028196811676025 ], [ 2, 186, 0.05241914466023445 ], [ 3, 279, 0.1079530417919159 ], [ 4, 372, 0.03008267655968666 ], [ 5, 465, 0.020476186648011208 ] ] }, "language": { "accuracy": [ [ 1, 93, 0.709525465965271 ], [ 2, 186, 0.9832712411880493 ], [ 3, 279, 0.9843869209289551 ], [ 4, 372, 0.9913396835327148 ], [ 5, 465, 0.9936301708221436 ] ], "accuracy_micro": [ [ 1, 93, 0.7127174735069275 ], [ 2, 186, 0.9831109642982483 ], [ 3, 279, 0.9853065609931946 ], [ 4, 372, 0.9910488128662109 ], [ 5, 465, 0.9930754899978638 ] ], "loss": [ [ 1, 93, 2.6028196811676025 ], [ 2, 186, 0.05241914466023445 ], [ 3, 279, 0.1079530417919159 ], [ 4, 372, 0.03008267655968666 ], [ 5, 465, 0.020476186648011208 ] ], "roc_auc": [ [ 1, 93, 0.8537933826446533 ], [ 2, 186, 0.9993903636932373 ], [ 3, 279, 0.9988884925842285 ], [ 4, 372, 0.9997660517692566 ], [ 5, 465, 0.9998530745506287 ] ] } }, "tune_checkpoint_num": 0, "validation_metrics": { "combined": { "loss": [ [ 1, 93, 0.2647719979286194 ], [ 2, 186, 0.27919644117355347 ], [ 3, 279, 0.1389603614807129 ], [ 4, 372, 0.06920339167118073 ], [ 5, 465, 0.07529747486114502 ] ] }, "language": { "accuracy": [ [ 1, 93, 0.911348819732666 ], [ 2, 186, 0.9450980424880981 ], [ 3, 279, 0.9551990628242493 ], [ 4, 372, 0.9799168109893799 ], [ 5, 465, 0.9636363983154297 ] ], "accuracy_micro": [ [ 1, 93, 0.9225251078605652 ], [ 2, 186, 0.9397417306900024 ], [ 3, 279, 0.955523669719696 ], [ 4, 372, 0.9784792065620422 ], [ 5, 465, 0.9684361815452576 ] ], "loss": [ [ 1, 93, 0.2647719979286194 ], [ 2, 186, 0.27919644117355347 ], [ 3, 279, 0.1389603614807129 ], [ 4, 372, 0.06920339167118073 ], [ 5, 465, 0.07529747486114502 ] ], "roc_auc": [ [ 1, 93, 0.9981002807617188 ], [ 2, 186, 0.99806147813797 ], [ 3, 279, 0.9984046816825867 ], [ 4, 372, 0.998852550983429 ], [ 5, 465, 0.9990896582603455 ] ] } } }