{"step": 1, "epoch": 0.0008090614886731392, "time": "2026-06-26 21:51:06", "logs": {"loss": 0.6913009285926819, "grad_norm": 2.5394184589385986, "learning_rate": 0.0, "epoch": 0.0008090614886731392}} {"step": 25, "epoch": 0.020226537216828478, "time": "2026-06-26 21:51:24", "logs": {"loss": 0.710881233215332, "grad_norm": 3.3882575035095215, "learning_rate": 9.716599190283402e-07, "epoch": 0.020226537216828478}} {"step": 50, "epoch": 0.040453074433656956, "time": "2026-06-26 21:51:44", "logs": {"loss": 0.6965625762939454, "grad_norm": 4.59527063369751, "learning_rate": 1.9838056680161946e-06, "epoch": 0.040453074433656956}} {"step": 75, "epoch": 0.06067961165048544, "time": "2026-06-26 21:52:04", "logs": {"loss": 0.6713954925537109, "grad_norm": 6.466946125030518, "learning_rate": 2.995951417004049e-06, "epoch": 0.06067961165048544}} {"step": 100, "epoch": 0.08090614886731391, "time": "2026-06-26 21:52:25", "logs": {"loss": 0.6306858444213868, "grad_norm": 5.92415714263916, "learning_rate": 4.008097165991903e-06, "epoch": 0.08090614886731391}} {"step": 125, "epoch": 0.1011326860841424, "time": "2026-06-26 21:52:47", "logs": {"loss": 0.5511775207519531, "grad_norm": 7.790467262268066, "learning_rate": 5.020242914979757e-06, "epoch": 0.1011326860841424}} {"step": 150, "epoch": 0.12135922330097088, "time": "2026-06-26 21:53:09", "logs": {"loss": 0.5026376342773438, "grad_norm": 5.874857425689697, "learning_rate": 6.0323886639676124e-06, "epoch": 0.12135922330097088}} {"step": 175, "epoch": 0.14158576051779936, "time": "2026-06-26 21:53:32", "logs": {"loss": 0.4295468521118164, "grad_norm": 12.701870918273926, "learning_rate": 7.044534412955466e-06, "epoch": 0.14158576051779936}} {"step": 200, "epoch": 0.16181229773462782, "time": "2026-06-26 21:53:53", "logs": {"loss": 0.3788005828857422, "grad_norm": 5.137658596038818, "learning_rate": 8.056680161943322e-06, "epoch": 0.16181229773462782}} {"step": 225, "epoch": 0.1820388349514563, "time": "2026-06-26 21:54:15", "logs": {"loss": 0.2651861381530762, "grad_norm": 5.249273300170898, "learning_rate": 9.068825910931175e-06, "epoch": 0.1820388349514563}} {"step": 250, "epoch": 0.2022653721682848, "time": "2026-06-26 21:54:38", "logs": {"loss": 0.3065790557861328, "grad_norm": 38.753013610839844, "learning_rate": 1.008097165991903e-05, "epoch": 0.2022653721682848}} {"step": 275, "epoch": 0.22249190938511326, "time": "2026-06-26 21:55:00", "logs": {"loss": 0.38094028472900393, "grad_norm": 13.836112022399902, "learning_rate": 1.1093117408906884e-05, "epoch": 0.22249190938511326}} {"step": 300, "epoch": 0.24271844660194175, "time": "2026-06-26 21:55:22", "logs": {"loss": 0.3118729019165039, "grad_norm": 6.559873580932617, "learning_rate": 1.2105263157894737e-05, "epoch": 0.24271844660194175}} {"step": 325, "epoch": 0.26294498381877024, "time": "2026-06-26 21:55:44", "logs": {"loss": 0.23761932373046876, "grad_norm": 7.356478214263916, "learning_rate": 1.3117408906882592e-05, "epoch": 0.26294498381877024}} {"step": 350, "epoch": 0.28317152103559873, "time": "2026-06-26 21:56:06", "logs": {"loss": 0.26587358474731443, "grad_norm": 4.0845184326171875, "learning_rate": 1.4129554655870446e-05, "epoch": 0.28317152103559873}} {"step": 375, "epoch": 0.30339805825242716, "time": "2026-06-26 21:56:28", "logs": {"loss": 0.3239314651489258, "grad_norm": 28.685104370117188, "learning_rate": 1.5141700404858302e-05, "epoch": 0.30339805825242716}} {"step": 400, "epoch": 0.32362459546925565, "time": "2026-06-26 21:56:51", "logs": {"loss": 0.24046634674072265, "grad_norm": 1.7896462678909302, "learning_rate": 1.6153846153846154e-05, "epoch": 0.32362459546925565}} {"step": 425, "epoch": 0.34385113268608414, "time": "2026-06-26 21:57:13", "logs": {"loss": 0.27144105911254884, "grad_norm": 6.960549831390381, "learning_rate": 1.716599190283401e-05, "epoch": 0.34385113268608414}} {"step": 450, "epoch": 0.3640776699029126, "time": "2026-06-26 21:57:35", "logs": {"loss": 0.24825719833374024, "grad_norm": 22.062820434570312, "learning_rate": 1.8178137651821864e-05, "epoch": 0.3640776699029126}} {"step": 475, "epoch": 0.3843042071197411, "time": "2026-06-26 21:57:57", "logs": {"loss": 0.22249792098999024, "grad_norm": 0.4285735785961151, "learning_rate": 1.9190283400809718e-05, "epoch": 0.3843042071197411}} {"step": 500, "epoch": 0.4045307443365696, "time": "2026-06-26 21:58:19", "logs": {"loss": 0.25503772735595703, "grad_norm": 0.26966607570648193, "learning_rate": 1.999993769982229e-05, "epoch": 0.4045307443365696}} {"step": 500, "epoch": 0.4045307443365696, "time": "2026-06-26 21:58:54", "logs": {"eval_loss": 0.1790667176246643, "eval_accuracy": 0.9550277918140475, "eval_precision": 0.9574468085106383, "eval_recall": 0.9847480106100795, "eval_f1": 0.9709055246812683, "eval_runtime": 34.5481, "eval_samples_per_second": 57.282, "eval_steps_per_second": 3.589, "epoch": 0.4045307443365696}} {"step": 525, "epoch": 0.42475728155339804, "time": "2026-06-26 21:59:29", "logs": {"loss": 0.2667963790893555, "grad_norm": 1.232269048690796, "learning_rate": 1.9997757275108847e-05, "epoch": 0.42475728155339804}} {"step": 550, "epoch": 0.4449838187702265, "time": "2026-06-26 21:59:52", "logs": {"loss": 0.2216647148132324, "grad_norm": 12.561880111694336, "learning_rate": 1.9992462617728763e-05, "epoch": 0.4449838187702265}} {"step": 575, "epoch": 0.465210355987055, "time": "2026-06-26 22:00:14", "logs": {"loss": 0.23123834609985353, "grad_norm": 0.4093881845474243, "learning_rate": 1.9984055376931414e-05, "epoch": 0.465210355987055}} {"step": 600, "epoch": 0.4854368932038835, "time": "2026-06-26 22:00:36", "logs": {"loss": 0.2226162338256836, "grad_norm": 3.573305368423462, "learning_rate": 1.9972538171514525e-05, "epoch": 0.4854368932038835}} {"step": 625, "epoch": 0.5056634304207119, "time": "2026-06-26 22:00:58", "logs": {"loss": 0.2451229476928711, "grad_norm": 12.511730194091797, "learning_rate": 1.9957914589008405e-05, "epoch": 0.5056634304207119}} {"step": 650, "epoch": 0.5258899676375405, "time": "2026-06-26 22:01:21", "logs": {"loss": 0.25127721786499024, "grad_norm": 11.676703453063965, "learning_rate": 1.9940189184558487e-05, "epoch": 0.5258899676375405}} {"step": 675, "epoch": 0.5461165048543689, "time": "2026-06-26 22:01:43", "logs": {"loss": 0.30009620666503906, "grad_norm": 5.444802284240723, "learning_rate": 1.9919367479506413e-05, "epoch": 0.5461165048543689}} {"step": 700, "epoch": 0.5663430420711975, "time": "2026-06-26 22:02:05", "logs": {"loss": 0.3415143585205078, "grad_norm": 1.9753400087356567, "learning_rate": 1.989545595967018e-05, "epoch": 0.5663430420711975}} {"step": 725, "epoch": 0.5865695792880259, "time": "2026-06-26 22:02:27", "logs": {"loss": 0.24259204864501954, "grad_norm": 0.7816814184188843, "learning_rate": 1.986846207332384e-05, "epoch": 0.5865695792880259}} {"step": 750, "epoch": 0.6067961165048543, "time": "2026-06-26 22:02:49", "logs": {"loss": 0.1343485450744629, "grad_norm": 20.42180061340332, "learning_rate": 1.9838394228877443e-05, "epoch": 0.6067961165048543}} {"step": 775, "epoch": 0.6270226537216829, "time": "2026-06-26 22:03:11", "logs": {"loss": 0.25507625579833987, "grad_norm": 21.677453994750977, "learning_rate": 1.980526179225785e-05, "epoch": 0.6270226537216829}} {"step": 800, "epoch": 0.6472491909385113, "time": "2026-06-26 22:03:33", "logs": {"loss": 0.26329845428466797, "grad_norm": 4.561895370483398, "learning_rate": 1.97690750839913e-05, "epoch": 0.6472491909385113}} {"step": 825, "epoch": 0.6674757281553398, "time": "2026-06-26 22:03:56", "logs": {"loss": 0.16668357849121093, "grad_norm": 0.17717082798480988, "learning_rate": 1.9729845375988694e-05, "epoch": 0.6674757281553398}} {"step": 850, "epoch": 0.6877022653721683, "time": "2026-06-26 22:04:18", "logs": {"loss": 0.2621467399597168, "grad_norm": 6.059898853302002, "learning_rate": 1.968758488803439e-05, "epoch": 0.6877022653721683}} {"step": 875, "epoch": 0.7079288025889967, "time": "2026-06-26 22:04:40", "logs": {"loss": 0.3152758979797363, "grad_norm": 5.8439130783081055, "learning_rate": 1.9642306783979902e-05, "epoch": 0.7079288025889967}} {"step": 900, "epoch": 0.7281553398058253, "time": "2026-06-26 22:05:02", "logs": {"loss": 0.2474656867980957, "grad_norm": 5.4012041091918945, "learning_rate": 1.959402516764339e-05, "epoch": 0.7281553398058253}} {"step": 925, "epoch": 0.7483818770226537, "time": "2026-06-26 22:05:24", "logs": {"loss": 0.22230056762695313, "grad_norm": 13.964224815368652, "learning_rate": 1.954275507841646e-05, "epoch": 0.7483818770226537}} {"step": 950, "epoch": 0.7686084142394822, "time": "2026-06-26 22:05:46", "logs": {"loss": 0.3234273910522461, "grad_norm": 8.115334510803223, "learning_rate": 1.948851248657947e-05, "epoch": 0.7686084142394822}} {"step": 975, "epoch": 0.7888349514563107, "time": "2026-06-26 22:06:08", "logs": {"loss": 0.1469671630859375, "grad_norm": 0.23621903359889984, "learning_rate": 1.9431314288326925e-05, "epoch": 0.7888349514563107}} {"step": 1000, "epoch": 0.8090614886731392, "time": "2026-06-26 22:06:30", "logs": {"loss": 0.24907604217529297, "grad_norm": 3.0084638595581055, "learning_rate": 1.9371178300504394e-05, "epoch": 0.8090614886731392}} {"step": 1000, "epoch": 0.8090614886731392, "time": "2026-06-26 22:07:05", "logs": {"eval_loss": 0.15361516177654266, "eval_accuracy": 0.9615967660434563, "eval_precision": 0.9578005115089514, "eval_recall": 0.993368700265252, "eval_f1": 0.9752604166666666, "eval_runtime": 34.2684, "eval_samples_per_second": 57.75, "eval_steps_per_second": 3.618, "epoch": 0.8090614886731392}} {"step": 1025, "epoch": 0.8292880258899676, "time": "2026-06-26 22:07:40", "logs": {"loss": 0.128564510345459, "grad_norm": 0.658998429775238, "learning_rate": 1.930812325505871e-05, "epoch": 0.8292880258899676}} {"step": 1050, "epoch": 0.8495145631067961, "time": "2026-06-26 22:08:03", "logs": {"loss": 0.28263355255126954, "grad_norm": 14.597765922546387, "learning_rate": 1.9242168793203088e-05, "epoch": 0.8495145631067961}} {"step": 1075, "epoch": 0.8697411003236246, "time": "2026-06-26 22:08:25", "logs": {"loss": 0.20550737380981446, "grad_norm": 10.520459175109863, "learning_rate": 1.9173335459299025e-05, "epoch": 0.8697411003236246}} {"step": 1100, "epoch": 0.889967637540453, "time": "2026-06-26 22:08:47", "logs": {"loss": 0.21728286743164063, "grad_norm": 8.196412086486816, "learning_rate": 1.9101644694456873e-05, "epoch": 0.889967637540453}} {"step": 1125, "epoch": 0.9101941747572816, "time": "2026-06-26 22:09:09", "logs": {"loss": 0.22805599212646485, "grad_norm": 10.451470375061035, "learning_rate": 1.902711882985708e-05, "epoch": 0.9101941747572816}} {"step": 1150, "epoch": 0.93042071197411, "time": "2026-06-26 22:09:31", "logs": {"loss": 0.19682933807373046, "grad_norm": 0.7729430794715881, "learning_rate": 1.894978107979417e-05, "epoch": 0.93042071197411}} {"step": 1175, "epoch": 0.9506472491909385, "time": "2026-06-26 22:09:53", "logs": {"loss": 0.21496267318725587, "grad_norm": 1.208465814590454, "learning_rate": 1.886965553444568e-05, "epoch": 0.9506472491909385}} {"step": 1200, "epoch": 0.970873786407767, "time": "2026-06-26 22:10:15", "logs": {"loss": 0.2545662498474121, "grad_norm": 8.930377006530762, "learning_rate": 1.8786767152368197e-05, "epoch": 0.970873786407767}} {"step": 1225, "epoch": 0.9911003236245954, "time": "2026-06-26 22:10:37", "logs": {"loss": 0.15711795806884765, "grad_norm": 8.784140586853027, "learning_rate": 1.8701141752722966e-05, "epoch": 0.9911003236245954}} {"step": 1250, "epoch": 1.0113268608414239, "time": "2026-06-26 22:10:59", "logs": {"loss": 0.18027606964111328, "grad_norm": 6.048089504241943, "learning_rate": 1.8612806007233382e-05, "epoch": 1.0113268608414239}} {"step": 1275, "epoch": 1.0315533980582525, "time": "2026-06-26 22:11:21", "logs": {"loss": 0.1467225170135498, "grad_norm": 2.1826491355895996, "learning_rate": 1.8521787431876954e-05, "epoch": 1.0315533980582525}} {"step": 1300, "epoch": 1.051779935275081, "time": "2026-06-26 22:11:43", "logs": {"loss": 0.21480131149291992, "grad_norm": 13.113622665405273, "learning_rate": 1.8428114378314237e-05, "epoch": 1.051779935275081}} {"step": 1325, "epoch": 1.0720064724919094, "time": "2026-06-26 22:12:05", "logs": {"loss": 0.22947580337524415, "grad_norm": 6.212342262268066, "learning_rate": 1.8331816025057508e-05, "epoch": 1.0720064724919094}} {"step": 1350, "epoch": 1.0922330097087378, "time": "2026-06-26 22:12:27", "logs": {"loss": 0.10173338890075684, "grad_norm": 0.22277741134166718, "learning_rate": 1.823292236838186e-05, "epoch": 1.0922330097087378}} {"step": 1375, "epoch": 1.1124595469255663, "time": "2026-06-26 22:12:49", "logs": {"loss": 0.2582175064086914, "grad_norm": 11.058046340942383, "learning_rate": 1.813146421298154e-05, "epoch": 1.1124595469255663}} {"step": 1400, "epoch": 1.132686084142395, "time": "2026-06-26 22:13:12", "logs": {"loss": 0.23467300415039063, "grad_norm": 9.502155303955078, "learning_rate": 1.802747316237454e-05, "epoch": 1.132686084142395}} {"step": 1425, "epoch": 1.1529126213592233, "time": "2026-06-26 22:13:34", "logs": {"loss": 0.18842180252075194, "grad_norm": 5.091904640197754, "learning_rate": 1.792098160905829e-05, "epoch": 1.1529126213592233}} {"step": 1450, "epoch": 1.1731391585760518, "time": "2026-06-26 22:13:56", "logs": {"loss": 0.13545321464538573, "grad_norm": 0.2650909721851349, "learning_rate": 1.7812022724419624e-05, "epoch": 1.1731391585760518}} {"step": 1475, "epoch": 1.1933656957928802, "time": "2026-06-26 22:14:18", "logs": {"loss": 0.16887168884277343, "grad_norm": 3.7782185077667236, "learning_rate": 1.7700630448402125e-05, "epoch": 1.1933656957928802}} {"step": 1500, "epoch": 1.2135922330097086, "time": "2026-06-26 22:14:40", "logs": {"loss": 0.22910015106201173, "grad_norm": 0.5704866051673889, "learning_rate": 1.758683947893406e-05, "epoch": 1.2135922330097086}} {"step": 1500, "epoch": 1.2135922330097086, "time": "2026-06-26 22:15:14", "logs": {"eval_loss": 0.14868734776973724, "eval_accuracy": 0.9605861546235472, "eval_precision": 0.9589216944801027, "eval_recall": 0.9907161803713528, "eval_f1": 0.974559686888454, "eval_runtime": 34.2705, "eval_samples_per_second": 57.746, "eval_steps_per_second": 3.618, "epoch": 1.2135922330097086}} {"step": 1525, "epoch": 1.2338187702265373, "time": "2026-06-26 22:15:50", "logs": {"loss": 0.14131352424621582, "grad_norm": 16.6047306060791, "learning_rate": 1.747068526112022e-05, "epoch": 1.2338187702265373}} {"step": 1550, "epoch": 1.2540453074433657, "time": "2026-06-26 22:16:13", "logs": {"loss": 0.15291913986206054, "grad_norm": 5.992398262023926, "learning_rate": 1.735220397620101e-05, "epoch": 1.2540453074433657}} {"step": 1575, "epoch": 1.2742718446601942, "time": "2026-06-26 22:16:35", "logs": {"loss": 0.09922373771667481, "grad_norm": 0.36782047152519226, "learning_rate": 1.7231432530282246e-05, "epoch": 1.2742718446601942}} {"step": 1600, "epoch": 1.2944983818770226, "time": "2026-06-26 22:16:57", "logs": {"loss": 0.1941922378540039, "grad_norm": 1.3172669410705566, "learning_rate": 1.7108408542839146e-05, "epoch": 1.2944983818770226}} {"step": 1625, "epoch": 1.3147249190938513, "time": "2026-06-26 22:17:19", "logs": {"loss": 0.16940629959106446, "grad_norm": 0.693942666053772, "learning_rate": 1.698317033499813e-05, "epoch": 1.3147249190938513}} {"step": 1650, "epoch": 1.3349514563106797, "time": "2026-06-26 22:17:41", "logs": {"loss": 0.12692631721496583, "grad_norm": 0.1476801335811615, "learning_rate": 1.6855756917600057e-05, "epoch": 1.3349514563106797}} {"step": 1675, "epoch": 1.3551779935275081, "time": "2026-06-26 22:18:03", "logs": {"loss": 0.25180328369140625, "grad_norm": 23.20606231689453, "learning_rate": 1.6726207979048604e-05, "epoch": 1.3551779935275081}} {"step": 1700, "epoch": 1.3754045307443366, "time": "2026-06-26 22:18:25", "logs": {"loss": 0.13337421417236328, "grad_norm": 0.3847394287586212, "learning_rate": 1.6594563872947613e-05, "epoch": 1.3754045307443366}} {"step": 1725, "epoch": 1.395631067961165, "time": "2026-06-26 22:18:48", "logs": {"loss": 0.17984333038330078, "grad_norm": 7.629310131072998, "learning_rate": 1.6460865605531214e-05, "epoch": 1.395631067961165}} {"step": 1750, "epoch": 1.4158576051779934, "time": "2026-06-26 22:19:10", "logs": {"loss": 0.15392546653747557, "grad_norm": 0.40370574593544006, "learning_rate": 1.6325154822890663e-05, "epoch": 1.4158576051779934}} {"step": 1775, "epoch": 1.436084142394822, "time": "2026-06-26 22:19:32", "logs": {"loss": 0.1560378646850586, "grad_norm": 3.1435182094573975, "learning_rate": 1.618747379800188e-05, "epoch": 1.436084142394822}} {"step": 1800, "epoch": 1.4563106796116505, "time": "2026-06-26 22:19:54", "logs": {"loss": 0.23071422576904296, "grad_norm": 6.557313919067383, "learning_rate": 1.6047865417557695e-05, "epoch": 1.4563106796116505}} {"step": 1825, "epoch": 1.476537216828479, "time": "2026-06-26 22:20:16", "logs": {"loss": 0.17919015884399414, "grad_norm": 4.851151943206787, "learning_rate": 1.5906373168608952e-05, "epoch": 1.476537216828479}} {"step": 1850, "epoch": 1.4967637540453074, "time": "2026-06-26 22:20:38", "logs": {"loss": 0.22098312377929688, "grad_norm": 6.987358093261719, "learning_rate": 1.576304112501858e-05, "epoch": 1.4967637540453074}} {"step": 1875, "epoch": 1.516990291262136, "time": "2026-06-26 22:21:00", "logs": {"loss": 0.1659644889831543, "grad_norm": 4.638033390045166, "learning_rate": 1.5617913933732892e-05, "epoch": 1.516990291262136}} {"step": 1900, "epoch": 1.5372168284789645, "time": "2026-06-26 22:21:23", "logs": {"loss": 0.18479549407958984, "grad_norm": 3.2221922874450684, "learning_rate": 1.5471036800874375e-05, "epoch": 1.5372168284789645}} {"step": 1925, "epoch": 1.557443365695793, "time": "2026-06-26 22:21:45", "logs": {"loss": 0.18851667404174804, "grad_norm": 0.3064526617527008, "learning_rate": 1.5322455477660274e-05, "epoch": 1.557443365695793}} {"step": 1950, "epoch": 1.5776699029126213, "time": "2026-06-26 22:22:07", "logs": {"loss": 0.23035451889038086, "grad_norm": 15.610395431518555, "learning_rate": 1.5172216246151426e-05, "epoch": 1.5776699029126213}} {"step": 1975, "epoch": 1.5978964401294498, "time": "2026-06-26 22:22:29", "logs": {"loss": 0.05388895988464355, "grad_norm": 8.045638084411621, "learning_rate": 1.50203659048357e-05, "epoch": 1.5978964401294498}} {"step": 2000, "epoch": 1.6181229773462782, "time": "2026-06-26 22:22:51", "logs": {"loss": 0.2584081268310547, "grad_norm": 12.035682678222656, "learning_rate": 1.4866951754050605e-05, "epoch": 1.6181229773462782}} {"step": 2000, "epoch": 1.6181229773462782, "time": "2026-06-26 22:23:26", "logs": {"eval_loss": 0.145921990275383, "eval_accuracy": 0.9621020717534108, "eval_precision": 0.9625564880568108, "eval_recall": 0.9887267904509284, "eval_f1": 0.9754661432777233, "eval_runtime": 34.2514, "eval_samples_per_second": 57.779, "eval_steps_per_second": 3.62, "epoch": 1.6181229773462782}} {"step": 2025, "epoch": 1.6383495145631068, "time": "2026-06-26 22:24:01", "logs": {"loss": 0.17600563049316406, "grad_norm": 11.77345085144043, "learning_rate": 1.4712021581249534e-05, "epoch": 1.6383495145631068}} {"step": 2050, "epoch": 1.6585760517799353, "time": "2026-06-26 22:24:24", "logs": {"loss": 0.2075064277648926, "grad_norm": 0.31589698791503906, "learning_rate": 1.4555623646116325e-05, "epoch": 1.6585760517799353}} {"step": 2075, "epoch": 1.6788025889967637, "time": "2026-06-26 22:24:47", "logs": {"loss": 0.15077384948730468, "grad_norm": 6.368648529052734, "learning_rate": 1.4397806665532693e-05, "epoch": 1.6788025889967637}} {"step": 2100, "epoch": 1.6990291262135924, "time": "2026-06-26 22:25:08", "logs": {"loss": 0.21610870361328124, "grad_norm": 0.19168436527252197, "learning_rate": 1.4238619798403266e-05, "epoch": 1.6990291262135924}} {"step": 2125, "epoch": 1.7192556634304208, "time": "2026-06-26 22:25:30", "logs": {"loss": 0.1896487808227539, "grad_norm": 3.6846413612365723, "learning_rate": 1.4078112630342891e-05, "epoch": 1.7192556634304208}} {"step": 2150, "epoch": 1.7394822006472492, "time": "2026-06-26 22:25:53", "logs": {"loss": 0.18662324905395508, "grad_norm": 6.122201919555664, "learning_rate": 1.3916335158231101e-05, "epoch": 1.7394822006472492}} {"step": 2175, "epoch": 1.7597087378640777, "time": "2026-06-26 22:26:15", "logs": {"loss": 0.14516648292541504, "grad_norm": 8.101036071777344, "learning_rate": 1.3753337774638397e-05, "epoch": 1.7597087378640777}} {"step": 2200, "epoch": 1.779935275080906, "time": "2026-06-26 22:26:37", "logs": {"loss": 0.23894359588623046, "grad_norm": 0.39058423042297363, "learning_rate": 1.3589171252129329e-05, "epoch": 1.779935275080906}} {"step": 2225, "epoch": 1.8001618122977345, "time": "2026-06-26 22:26:59", "logs": {"loss": 0.16099306106567382, "grad_norm": 20.84650993347168, "learning_rate": 1.3423886727447176e-05, "epoch": 1.8001618122977345}} {"step": 2250, "epoch": 1.820388349514563, "time": "2026-06-26 22:27:21", "logs": {"loss": 0.23093647003173828, "grad_norm": 2.713047504425049, "learning_rate": 1.325753568558521e-05, "epoch": 1.820388349514563}} {"step": 2275, "epoch": 1.8406148867313916, "time": "2026-06-26 22:27:43", "logs": {"loss": 0.14622759819030762, "grad_norm": 2.291496515274048, "learning_rate": 1.3090169943749475e-05, "epoch": 1.8406148867313916}} {"step": 2300, "epoch": 1.86084142394822, "time": "2026-06-26 22:28:05", "logs": {"loss": 0.14002437591552735, "grad_norm": 0.38880622386932373, "learning_rate": 1.2921841635218082e-05, "epoch": 1.86084142394822}} {"step": 2325, "epoch": 1.8810679611650487, "time": "2026-06-26 22:28:27", "logs": {"loss": 0.21583776473999022, "grad_norm": 0.3293047249317169, "learning_rate": 1.275260319310205e-05, "epoch": 1.8810679611650487}} {"step": 2350, "epoch": 1.9012944983818771, "time": "2026-06-26 22:28:50", "logs": {"loss": 0.17850372314453125, "grad_norm": 0.16572241485118866, "learning_rate": 1.2582507334012755e-05, "epoch": 1.9012944983818771}} {"step": 2375, "epoch": 1.9215210355987056, "time": "2026-06-26 22:29:12", "logs": {"loss": 0.16260711669921876, "grad_norm": 4.988359451293945, "learning_rate": 1.2411607041641062e-05, "epoch": 1.9215210355987056}} {"step": 2400, "epoch": 1.941747572815534, "time": "2026-06-26 22:29:34", "logs": {"loss": 0.20481142044067382, "grad_norm": 1.0162508487701416, "learning_rate": 1.2239955550253277e-05, "epoch": 1.941747572815534}} {"step": 2425, "epoch": 1.9619741100323624, "time": "2026-06-26 22:29:56", "logs": {"loss": 0.12820093154907228, "grad_norm": 0.41159898042678833, "learning_rate": 1.2067606328109038e-05, "epoch": 1.9619741100323624}} {"step": 2450, "epoch": 1.9822006472491909, "time": "2026-06-26 22:30:18", "logs": {"loss": 0.18930299758911132, "grad_norm": 6.16225528717041, "learning_rate": 1.1894613060806312e-05, "epoch": 1.9822006472491909}} {"step": 2475, "epoch": 2.0024271844660193, "time": "2026-06-26 22:30:39", "logs": {"loss": 0.11151561737060547, "grad_norm": 1.239059329032898, "learning_rate": 1.172102963455871e-05, "epoch": 2.0024271844660193}} {"step": 2500, "epoch": 2.0226537216828477, "time": "2026-06-26 22:31:02", "logs": {"loss": 0.07747174263000488, "grad_norm": 0.14050441980361938, "learning_rate": 1.1546910119410297e-05, "epoch": 2.0226537216828477}} {"step": 2500, "epoch": 2.0226537216828477, "time": "2026-06-26 22:31:36", "logs": {"eval_loss": 0.17465205490589142, "eval_accuracy": 0.966144517433047, "eval_precision": 0.9712230215827338, "eval_recall": 0.9847480106100795, "eval_f1": 0.977938755350675, "eval_runtime": 34.5204, "eval_samples_per_second": 57.328, "eval_steps_per_second": 3.592, "epoch": 2.0226537216828477}} {"step": 2525, "epoch": 2.042880258899676, "time": "2026-06-26 22:32:14", "logs": {"loss": 0.12494021415710449, "grad_norm": 0.5169682502746582, "learning_rate": 1.1372308752393144e-05, "epoch": 2.042880258899676}} {"step": 2550, "epoch": 2.063106796116505, "time": "2026-06-26 22:32:37", "logs": {"loss": 0.17911155700683593, "grad_norm": 2.469010829925537, "learning_rate": 1.1197279920632864e-05, "epoch": 2.063106796116505}} {"step": 2575, "epoch": 2.0833333333333335, "time": "2026-06-26 22:32:59", "logs": {"loss": 0.1611471939086914, "grad_norm": 0.20758801698684692, "learning_rate": 1.1021878144407408e-05, "epoch": 2.0833333333333335}} {"step": 2600, "epoch": 2.103559870550162, "time": "2026-06-26 22:33:21", "logs": {"loss": 0.09400986671447754, "grad_norm": 18.897438049316406, "learning_rate": 1.0846158060164359e-05, "epoch": 2.103559870550162}} {"step": 2625, "epoch": 2.1237864077669903, "time": "2026-06-26 22:33:43", "logs": {"loss": 0.10660056114196777, "grad_norm": 0.48710235953330994, "learning_rate": 1.0670174403502051e-05, "epoch": 2.1237864077669903}} {"step": 2650, "epoch": 2.144012944983819, "time": "2026-06-26 22:34:05", "logs": {"loss": 0.09857481956481934, "grad_norm": 5.023293972015381, "learning_rate": 1.0493981992119833e-05, "epoch": 2.144012944983819}} {"step": 2675, "epoch": 2.164239482200647, "time": "2026-06-26 22:34:27", "logs": {"loss": 0.1647811508178711, "grad_norm": 0.3322446942329407, "learning_rate": 1.03176357087427e-05, "epoch": 2.164239482200647}} {"step": 2700, "epoch": 2.1844660194174756, "time": "2026-06-26 22:34:50", "logs": {"loss": 0.21691896438598632, "grad_norm": 33.930667877197266, "learning_rate": 1.0141190484025722e-05, "epoch": 2.1844660194174756}} {"step": 2725, "epoch": 2.204692556634304, "time": "2026-06-26 22:35:12", "logs": {"loss": 0.20835105895996095, "grad_norm": 0.22541019320487976, "learning_rate": 9.964701279443509e-06, "epoch": 2.204692556634304}} {"step": 2750, "epoch": 2.2249190938511325, "time": "2026-06-26 22:35:34", "logs": {"loss": 0.1038576602935791, "grad_norm": 0.2086869329214096, "learning_rate": 9.788223070170112e-06, "epoch": 2.2249190938511325}} {"step": 2775, "epoch": 2.2451456310679614, "time": "2026-06-26 22:35:56", "logs": {"loss": 0.1402608013153076, "grad_norm": 1.6252963542938232, "learning_rate": 9.6118108279546e-06, "epoch": 2.2451456310679614}} {"step": 2800, "epoch": 2.26537216828479, "time": "2026-06-26 22:36:18", "logs": {"loss": 0.1478741455078125, "grad_norm": 1.1920742988586426, "learning_rate": 9.435519503997767e-06, "epoch": 2.26537216828479}} {"step": 2825, "epoch": 2.2855987055016183, "time": "2026-06-26 22:36:40", "logs": {"loss": 0.10929722785949707, "grad_norm": 0.6118252277374268, "learning_rate": 9.259404011835203e-06, "epoch": 2.2855987055016183}} {"step": 2850, "epoch": 2.3058252427184467, "time": "2026-06-26 22:37:03", "logs": {"loss": 0.11905492782592773, "grad_norm": 0.16680538654327393, "learning_rate": 9.083519210232096e-06, "epoch": 2.3058252427184467}} {"step": 2875, "epoch": 2.326051779935275, "time": "2026-06-26 22:37:25", "logs": {"loss": 0.08101269721984863, "grad_norm": 0.19600656628608704, "learning_rate": 8.907919886095115e-06, "epoch": 2.326051779935275}} {"step": 2900, "epoch": 2.3462783171521036, "time": "2026-06-26 22:37:47", "logs": {"loss": 0.09864620208740234, "grad_norm": 1.6680601835250854, "learning_rate": 8.732660737406663e-06, "epoch": 2.3462783171521036}} {"step": 2925, "epoch": 2.366504854368932, "time": "2026-06-26 22:38:09", "logs": {"loss": 0.16998577117919922, "grad_norm": 0.5449312925338745, "learning_rate": 8.557796356186818e-06, "epoch": 2.366504854368932}} {"step": 2950, "epoch": 2.3867313915857604, "time": "2026-06-26 22:38:31", "logs": {"loss": 0.23032936096191406, "grad_norm": 0.10003538429737091, "learning_rate": 8.383381211488321e-06, "epoch": 2.3867313915857604}} {"step": 2975, "epoch": 2.406957928802589, "time": "2026-06-26 22:38:53", "logs": {"loss": 0.08545310974121094, "grad_norm": 7.103508472442627, "learning_rate": 8.209469632429811e-06, "epoch": 2.406957928802589}} {"step": 3000, "epoch": 2.4271844660194173, "time": "2026-06-26 22:39:15", "logs": {"loss": 0.2049958038330078, "grad_norm": 6.692376136779785, "learning_rate": 8.036115791272697e-06, "epoch": 2.4271844660194173}} {"step": 3000, "epoch": 2.4271844660194173, "time": "2026-06-26 22:39:50", "logs": {"eval_loss": 0.1759410947561264, "eval_accuracy": 0.9631126831733199, "eval_precision": 0.9638009049773756, "eval_recall": 0.9887267904509284, "eval_f1": 0.9761047463175123, "eval_runtime": 34.2085, "eval_samples_per_second": 57.851, "eval_steps_per_second": 3.625, "epoch": 2.4271844660194173}} {"step": 3025, "epoch": 2.4474110032362457, "time": "2026-06-26 22:40:25", "logs": {"loss": 0.21097312927246092, "grad_norm": 11.302281379699707, "learning_rate": 7.863373686546868e-06, "epoch": 2.4474110032362457}} {"step": 3050, "epoch": 2.4676375404530746, "time": "2026-06-26 22:40:48", "logs": {"loss": 0.12400970458984376, "grad_norm": 5.9209113121032715, "learning_rate": 7.691297126230515e-06, "epoch": 2.4676375404530746}} {"step": 3075, "epoch": 2.487864077669903, "time": "2026-06-26 22:41:10", "logs": {"loss": 0.20074039459228515, "grad_norm": 15.600579261779785, "learning_rate": 7.519939710989326e-06, "epoch": 2.487864077669903}} {"step": 3100, "epoch": 2.5080906148867315, "time": "2026-06-26 22:41:32", "logs": {"loss": 0.0825264072418213, "grad_norm": 14.571202278137207, "learning_rate": 7.349354817480234e-06, "epoch": 2.5080906148867315}} {"step": 3125, "epoch": 2.52831715210356, "time": "2026-06-26 22:41:54", "logs": {"loss": 0.13173922538757324, "grad_norm": 0.2681007981300354, "learning_rate": 7.179595581724971e-06, "epoch": 2.52831715210356}} {"step": 3150, "epoch": 2.5485436893203883, "time": "2026-06-26 22:42:16", "logs": {"loss": 0.09000961303710937, "grad_norm": 0.1719094216823578, "learning_rate": 7.010714882558551e-06, "epoch": 2.5485436893203883}} {"step": 3175, "epoch": 2.5687702265372168, "time": "2026-06-26 22:42:39", "logs": {"loss": 0.13644008636474608, "grad_norm": 0.06844039261341095, "learning_rate": 6.842765325157874e-06, "epoch": 2.5687702265372168}} {"step": 3200, "epoch": 2.588996763754045, "time": "2026-06-26 22:43:01", "logs": {"loss": 0.07055030345916748, "grad_norm": 11.590834617614746, "learning_rate": 6.675799224655588e-06, "epoch": 2.588996763754045}} {"step": 3225, "epoch": 2.6092233009708736, "time": "2026-06-26 22:43:23", "logs": {"loss": 0.10780407905578614, "grad_norm": 0.16210342943668365, "learning_rate": 6.509868589844274e-06, "epoch": 2.6092233009708736}} {"step": 3250, "epoch": 2.6294498381877025, "time": "2026-06-26 22:43:45", "logs": {"loss": 0.06451849937438965, "grad_norm": 0.1514226347208023, "learning_rate": 6.34502510697607e-06, "epoch": 2.6294498381877025}} {"step": 3275, "epoch": 2.649676375404531, "time": "2026-06-26 22:44:07", "logs": {"loss": 0.13269135475158692, "grad_norm": 0.14009274542331696, "learning_rate": 6.181320123662755e-06, "epoch": 2.649676375404531}} {"step": 3300, "epoch": 2.6699029126213594, "time": "2026-06-26 22:44:29", "logs": {"loss": 0.1452858829498291, "grad_norm": 1.227739930152893, "learning_rate": 6.018804632881326e-06, "epoch": 2.6699029126213594}} {"step": 3325, "epoch": 2.690129449838188, "time": "2026-06-26 22:44:51", "logs": {"loss": 0.11763744354248047, "grad_norm": 0.12412651628255844, "learning_rate": 5.857529257090027e-06, "epoch": 2.690129449838188}} {"step": 3350, "epoch": 2.7103559870550162, "time": "2026-06-26 22:45:13", "logs": {"loss": 0.10433626174926758, "grad_norm": 9.471817016601562, "learning_rate": 5.6975442324598165e-06, "epoch": 2.7103559870550162}} {"step": 3375, "epoch": 2.7305825242718447, "time": "2026-06-26 22:45:35", "logs": {"loss": 0.14967796325683594, "grad_norm": 5.368896961212158, "learning_rate": 5.538899393226122e-06, "epoch": 2.7305825242718447}} {"step": 3400, "epoch": 2.750809061488673, "time": "2026-06-26 22:45:57", "logs": {"loss": 0.13424870491027832, "grad_norm": 0.7815220355987549, "learning_rate": 5.381644156165844e-06, "epoch": 2.750809061488673}} {"step": 3425, "epoch": 2.7710355987055015, "time": "2026-06-26 22:46:19", "logs": {"loss": 0.12580464363098146, "grad_norm": 17.132827758789062, "learning_rate": 5.225827505204355e-06, "epoch": 2.7710355987055015}} {"step": 3450, "epoch": 2.79126213592233, "time": "2026-06-26 22:46:42", "logs": {"loss": 0.18594202041625976, "grad_norm": 2.3049182891845703, "learning_rate": 5.071497976157346e-06, "epoch": 2.79126213592233}} {"step": 3475, "epoch": 2.8114886731391584, "time": "2026-06-26 22:47:04", "logs": {"loss": 0.14881797790527343, "grad_norm": 9.519274711608887, "learning_rate": 4.918703641612255e-06, "epoch": 2.8114886731391584}} {"step": 3500, "epoch": 2.831715210355987, "time": "2026-06-26 22:47:26", "logs": {"loss": 0.10424537658691406, "grad_norm": 7.568735599517822, "learning_rate": 4.767492095953985e-06, "epoch": 2.831715210355987}} {"step": 3500, "epoch": 2.831715210355987, "time": "2026-06-26 22:48:00", "logs": {"eval_loss": 0.1581990271806717, "eval_accuracy": 0.9676604345629105, "eval_precision": 0.9718954248366013, "eval_recall": 0.9860742705570292, "eval_f1": 0.9789335088874259, "eval_runtime": 34.2504, "eval_samples_per_second": 57.78, "eval_steps_per_second": 3.62, "epoch": 2.831715210355987}} {"step": 3525, "epoch": 2.8519417475728153, "time": "2026-06-26 22:48:36", "logs": {"loss": 0.17485876083374025, "grad_norm": 1.743114709854126, "learning_rate": 4.61791044053958e-06, "epoch": 2.8519417475728153}} {"step": 3550, "epoch": 2.872168284789644, "time": "2026-06-26 22:48:58", "logs": {"loss": 0.12117493629455567, "grad_norm": 0.22640278935432434, "learning_rate": 4.470005269026482e-06, "epoch": 2.872168284789644}} {"step": 3575, "epoch": 2.8923948220064726, "time": "2026-06-26 22:49:21", "logs": {"loss": 0.196475830078125, "grad_norm": 6.634481430053711, "learning_rate": 4.323822652858911e-06, "epoch": 2.8923948220064726}} {"step": 3600, "epoch": 2.912621359223301, "time": "2026-06-26 22:49:42", "logs": {"loss": 0.07209478855133057, "grad_norm": 9.53117561340332, "learning_rate": 4.179408126916946e-06, "epoch": 2.912621359223301}} {"step": 3625, "epoch": 2.9328478964401294, "time": "2026-06-26 22:50:05", "logs": {"loss": 0.10872147560119629, "grad_norm": 1.068833351135254, "learning_rate": 4.036806675332715e-06, "epoch": 2.9328478964401294}} {"step": 3650, "epoch": 2.953074433656958, "time": "2026-06-26 22:50:27", "logs": {"loss": 0.11207496643066406, "grad_norm": 12.03824520111084, "learning_rate": 3.8960627174781425e-06, "epoch": 2.953074433656958}} {"step": 3675, "epoch": 2.9733009708737863, "time": "2026-06-26 22:50:49", "logs": {"loss": 0.12596786499023438, "grad_norm": 0.6559222936630249, "learning_rate": 3.7572200941286284e-06, "epoch": 2.9733009708737863}} {"step": 3700, "epoch": 2.9935275080906147, "time": "2026-06-26 22:51:11", "logs": {"loss": 0.14922695159912108, "grad_norm": 0.2858830690383911, "learning_rate": 3.6203220538069418e-06, "epoch": 2.9935275080906147}} {"step": 3725, "epoch": 3.013754045307443, "time": "2026-06-26 22:51:32", "logs": {"loss": 0.04458343982696533, "grad_norm": 0.0661507323384285, "learning_rate": 3.4854112393116047e-06, "epoch": 3.013754045307443}} {"step": 3750, "epoch": 3.033980582524272, "time": "2026-06-26 22:51:55", "logs": {"loss": 0.08979329109191894, "grad_norm": 3.3118996620178223, "learning_rate": 3.3525296744339574e-06, "epoch": 3.033980582524272}} {"step": 3775, "epoch": 3.0542071197411005, "time": "2026-06-26 22:52:17", "logs": {"loss": 0.14806150436401366, "grad_norm": 6.178338050842285, "learning_rate": 3.2217187508680314e-06, "epoch": 3.0542071197411005}} {"step": 3800, "epoch": 3.074433656957929, "time": "2026-06-26 22:52:39", "logs": {"loss": 0.10266283988952636, "grad_norm": 0.3131246268749237, "learning_rate": 3.0930192153173233e-06, "epoch": 3.074433656957929}} {"step": 3825, "epoch": 3.0946601941747574, "time": "2026-06-26 22:53:01", "logs": {"loss": 0.05577219009399414, "grad_norm": 10.549492835998535, "learning_rate": 2.966471156802477e-06, "epoch": 3.0946601941747574}} {"step": 3850, "epoch": 3.114886731391586, "time": "2026-06-26 22:53:23", "logs": {"loss": 0.09321762084960937, "grad_norm": 0.1610606610774994, "learning_rate": 2.84211399417383e-06, "epoch": 3.114886731391586}} {"step": 3875, "epoch": 3.135113268608414, "time": "2026-06-26 22:53:45", "logs": {"loss": 0.05884582042694092, "grad_norm": 0.3851342797279358, "learning_rate": 2.719986463832708e-06, "epoch": 3.135113268608414}} {"step": 3900, "epoch": 3.1553398058252426, "time": "2026-06-26 22:54:07", "logs": {"loss": 0.13341400146484375, "grad_norm": 0.06692659109830856, "learning_rate": 2.6001266076653096e-06, "epoch": 3.1553398058252426}} {"step": 3925, "epoch": 3.175566343042071, "time": "2026-06-26 22:54:30", "logs": {"loss": 0.12380348205566406, "grad_norm": 0.03991634398698807, "learning_rate": 2.4825717611929144e-06, "epoch": 3.175566343042071}} {"step": 3950, "epoch": 3.1957928802588995, "time": "2026-06-26 22:54:52", "logs": {"loss": 0.12655723571777344, "grad_norm": 0.046412382274866104, "learning_rate": 2.3673585419421275e-06, "epoch": 3.1957928802588995}} {"step": 3975, "epoch": 3.216019417475728, "time": "2026-06-26 22:55:14", "logs": {"loss": 0.13750163078308106, "grad_norm": 0.628549337387085, "learning_rate": 2.2545228380387706e-06, "epoch": 3.216019417475728}} {"step": 4000, "epoch": 3.236245954692557, "time": "2026-06-26 22:55:36", "logs": {"loss": 0.14353644371032714, "grad_norm": 7.138247489929199, "learning_rate": 2.1440997970289744e-06, "epoch": 3.236245954692557}} {"step": 4000, "epoch": 3.236245954692557, "time": "2026-06-26 22:56:10", "logs": {"eval_loss": 0.17846979200839996, "eval_accuracy": 0.9656392117230924, "eval_precision": 0.969361147327249, "eval_recall": 0.9860742705570292, "eval_f1": 0.977646285338593, "eval_runtime": 34.2397, "eval_samples_per_second": 57.798, "eval_steps_per_second": 3.622, "epoch": 3.236245954692557}} {"step": 4025, "epoch": 3.2564724919093853, "time": "2026-06-26 22:56:45", "logs": {"loss": 0.09338082313537598, "grad_norm": 0.1521400511264801, "learning_rate": 2.036123814930967e-06, "epoch": 3.2564724919093853}} {"step": 4050, "epoch": 3.2766990291262137, "time": "2026-06-26 22:57:08", "logs": {"loss": 0.12397599220275879, "grad_norm": 0.1602470725774765, "learning_rate": 1.9306285255209467e-06, "epoch": 3.2766990291262137}} {"step": 4075, "epoch": 3.296925566343042, "time": "2026-06-26 22:57:30", "logs": {"loss": 0.016015474796295167, "grad_norm": 0.06681159883737564, "learning_rate": 1.8276467898563887e-06, "epoch": 3.296925566343042}} {"step": 4100, "epoch": 3.3171521035598706, "time": "2026-06-26 22:57:52", "logs": {"loss": 0.09872553825378418, "grad_norm": 0.13160769641399384, "learning_rate": 1.7272106860400572e-06, "epoch": 3.3171521035598706}} {"step": 4125, "epoch": 3.337378640776699, "time": "2026-06-26 22:58:14", "logs": {"loss": 0.03920928001403809, "grad_norm": 0.035521235316991806, "learning_rate": 1.6293514992278935e-06, "epoch": 3.337378640776699}} {"step": 4150, "epoch": 3.3576051779935274, "time": "2026-06-26 22:58:37", "logs": {"loss": 0.1839055061340332, "grad_norm": 0.08237211406230927, "learning_rate": 1.534099711883905e-06, "epoch": 3.3576051779935274}} {"step": 4175, "epoch": 3.377831715210356, "time": "2026-06-26 22:58:59", "logs": {"loss": 0.10226664543151856, "grad_norm": 0.20403045415878296, "learning_rate": 1.4414849942850927e-06, "epoch": 3.377831715210356}} {"step": 4200, "epoch": 3.3980582524271843, "time": "2026-06-26 22:59:21", "logs": {"loss": 0.13616151809692384, "grad_norm": 0.09233145415782928, "learning_rate": 1.3515361952793494e-06, "epoch": 3.3980582524271843}} {"step": 4225, "epoch": 3.418284789644013, "time": "2026-06-26 22:59:43", "logs": {"loss": 0.083475980758667, "grad_norm": 0.832892894744873, "learning_rate": 1.264281333299261e-06, "epoch": 3.418284789644013}} {"step": 4250, "epoch": 3.4385113268608416, "time": "2026-06-26 23:00:05", "logs": {"loss": 0.10677513122558593, "grad_norm": 0.035616640001535416, "learning_rate": 1.1797475876345431e-06, "epoch": 3.4385113268608416}} {"step": 4275, "epoch": 3.45873786407767, "time": "2026-06-26 23:00:27", "logs": {"loss": 0.07215563774108887, "grad_norm": 14.879964828491211, "learning_rate": 1.0979612899658875e-06, "epoch": 3.45873786407767}} {"step": 4300, "epoch": 3.4789644012944985, "time": "2026-06-26 23:00:49", "logs": {"loss": 0.03914974451065063, "grad_norm": 0.38712477684020996, "learning_rate": 1.018947916162817e-06, "epoch": 3.4789644012944985}} {"step": 4325, "epoch": 3.499190938511327, "time": "2026-06-26 23:01:11", "logs": {"loss": 0.11899002075195313, "grad_norm": 0.036348629742860794, "learning_rate": 9.427320783481353e-07, "epoch": 3.499190938511327}} {"step": 4350, "epoch": 3.5194174757281553, "time": "2026-06-26 23:01:34", "logs": {"loss": 0.030057404041290283, "grad_norm": 0.021908069029450417, "learning_rate": 8.693375172314133e-07, "epoch": 3.5194174757281553}} {"step": 4375, "epoch": 3.5396440129449838, "time": "2026-06-26 23:01:56", "logs": {"loss": 0.09047553062438965, "grad_norm": 0.12993556261062622, "learning_rate": 7.987870947139276e-07, "epoch": 3.5396440129449838}} {"step": 4400, "epoch": 3.559870550161812, "time": "2026-06-26 23:02:18", "logs": {"loss": 0.07117459774017335, "grad_norm": 0.4316134452819824, "learning_rate": 7.311027867673237e-07, "epoch": 3.559870550161812}} {"step": 4425, "epoch": 3.5800970873786406, "time": "2026-06-26 23:02:40", "logs": {"loss": 0.08755615234375, "grad_norm": 0.056048110127449036, "learning_rate": 6.663056765882692e-07, "epoch": 3.5800970873786406}} {"step": 4450, "epoch": 3.600323624595469, "time": "2026-06-26 23:03:02", "logs": {"loss": 0.07385186195373535, "grad_norm": 0.7098426818847656, "learning_rate": 6.044159480311673e-07, "epoch": 3.600323624595469}} {"step": 4475, "epoch": 3.6205501618122975, "time": "2026-06-26 23:03:24", "logs": {"loss": 0.11163510322570801, "grad_norm": 0.16931486129760742, "learning_rate": 5.454528793210356e-07, "epoch": 3.6205501618122975}} {"step": 4500, "epoch": 3.6407766990291264, "time": "2026-06-26 23:03:46", "logs": {"loss": 0.12371963500976563, "grad_norm": 0.12286394834518433, "learning_rate": 4.894348370484648e-07, "epoch": 3.6407766990291264}} {"step": 4500, "epoch": 3.6407766990291264, "time": "2026-06-26 23:04:21", "logs": {"eval_loss": 0.19216185808181763, "eval_accuracy": 0.9666498231430015, "eval_precision": 0.973718791064389, "eval_recall": 0.9827586206896551, "eval_f1": 0.9782178217821782, "eval_runtime": 34.5067, "eval_samples_per_second": 57.351, "eval_steps_per_second": 3.594, "epoch": 3.6407766990291264}} {"step": 4500, "epoch": 3.6407766990291264, "time": "2026-06-26 23:04:35", "logs": {"train_runtime": 4411.9439, "train_samples_per_second": 17.919, "train_steps_per_second": 1.121, "total_flos": 1.893452398792704e+16, "train_loss": 0.18470030458768208, "epoch": 3.6407766990291264}} {"step": 4500, "epoch": 3.6407766990291264, "time": "2026-06-26 23:05:10", "logs": {"eval_loss": 0.15841300785541534, "eval_accuracy": 0.9671551288529561, "eval_precision": 0.9712606139777923, "eval_recall": 0.9860742705570292, "eval_f1": 0.9786113853241197, "eval_runtime": 34.9737, "eval_samples_per_second": 56.585, "eval_steps_per_second": 3.546, "epoch": 3.6407766990291264}}