{
  "best_metric": 1.1765553951263428,
  "best_model_checkpoint": "/root/finetuning_executions/finetuning_06_utg4java_src_fm_fc_dctx_priv/checkpoint-52644",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 87740,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 4.461702823638916,
      "learning_rate": 2.4687500000000004e-05,
      "loss": 3.4492,
      "step": 400
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.5006494522094727,
      "learning_rate": 4.96875e-05,
      "loss": 1.7497,
      "step": 800
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.1321290731430054,
      "learning_rate": 4.977283183804923e-05,
      "loss": 1.5442,
      "step": 1200
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.4736696481704712,
      "learning_rate": 4.9542788129744654e-05,
      "loss": 1.4716,
      "step": 1600
    },
    {
      "epoch": 0.11,
      "grad_norm": 1.031677484512329,
      "learning_rate": 4.931274442144008e-05,
      "loss": 1.4158,
      "step": 2000
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.6455645561218262,
      "learning_rate": 4.90827007131355e-05,
      "loss": 1.3773,
      "step": 2400
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.0821306705474854,
      "learning_rate": 4.885265700483092e-05,
      "loss": 1.3428,
      "step": 2800
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.1742956638336182,
      "learning_rate": 4.862261329652634e-05,
      "loss": 1.3228,
      "step": 3200
    },
    {
      "epoch": 0.21,
      "grad_norm": 1.0427188873291016,
      "learning_rate": 4.839256958822176e-05,
      "loss": 1.2911,
      "step": 3600
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.0644562244415283,
      "learning_rate": 4.8162525879917186e-05,
      "loss": 1.2715,
      "step": 4000
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.1774647235870361,
      "learning_rate": 4.793248217161261e-05,
      "loss": 1.2657,
      "step": 4400
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.1110398769378662,
      "learning_rate": 4.770243846330803e-05,
      "loss": 1.2418,
      "step": 4800
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.1167891025543213,
      "learning_rate": 4.7472394755003454e-05,
      "loss": 1.2388,
      "step": 5200
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9029982686042786,
      "learning_rate": 4.724235104669887e-05,
      "loss": 1.2091,
      "step": 5600
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.9677993059158325,
      "learning_rate": 4.7012307338394294e-05,
      "loss": 1.1908,
      "step": 6000
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.0969425439834595,
      "learning_rate": 4.6782263630089717e-05,
      "loss": 1.1772,
      "step": 6400
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.9977983236312866,
      "learning_rate": 4.655221992178514e-05,
      "loss": 1.1662,
      "step": 6800
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.9940459132194519,
      "learning_rate": 4.632217621348056e-05,
      "loss": 1.1755,
      "step": 7200
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.1301028728485107,
      "learning_rate": 4.6092132505175986e-05,
      "loss": 1.1427,
      "step": 7600
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.0510139465332031,
      "learning_rate": 4.586208879687141e-05,
      "loss": 1.1422,
      "step": 8000
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.0957871675491333,
      "learning_rate": 4.5632045088566825e-05,
      "loss": 1.1407,
      "step": 8400
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.0858688354492188,
      "learning_rate": 4.5402001380262254e-05,
      "loss": 1.1246,
      "step": 8800
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.1192280054092407,
      "learning_rate": 4.517195767195768e-05,
      "loss": 1.1145,
      "step": 9200
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.9741564393043518,
      "learning_rate": 4.49419139636531e-05,
      "loss": 1.1023,
      "step": 9600
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.0775293111801147,
      "learning_rate": 4.471187025534852e-05,
      "loss": 1.0946,
      "step": 10000
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.2840739488601685,
      "learning_rate": 4.448182654704394e-05,
      "loss": 1.0779,
      "step": 10400
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.0178784132003784,
      "learning_rate": 4.425178283873936e-05,
      "loss": 1.0956,
      "step": 10800
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9534255266189575,
      "learning_rate": 4.4021739130434786e-05,
      "loss": 1.0732,
      "step": 11200
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.9387480020523071,
      "learning_rate": 4.379169542213021e-05,
      "loss": 1.0697,
      "step": 11600
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.0132235288619995,
      "learning_rate": 4.356165171382563e-05,
      "loss": 1.0586,
      "step": 12000
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.8992817997932434,
      "learning_rate": 4.3332183114791814e-05,
      "loss": 1.0621,
      "step": 12400
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.9761301875114441,
      "learning_rate": 4.310213940648724e-05,
      "loss": 1.0678,
      "step": 12800
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.9724502563476562,
      "learning_rate": 4.287209569818266e-05,
      "loss": 1.0462,
      "step": 13200
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.0510269403457642,
      "learning_rate": 4.2642051989878076e-05,
      "loss": 1.0406,
      "step": 13600
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9309316277503967,
      "learning_rate": 4.24120082815735e-05,
      "loss": 1.041,
      "step": 14000
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.0321022272109985,
      "learning_rate": 4.218196457326892e-05,
      "loss": 1.0272,
      "step": 14400
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.1811890602111816,
      "learning_rate": 4.1951920864964345e-05,
      "loss": 1.033,
      "step": 14800
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.9431869983673096,
      "learning_rate": 4.172187715665977e-05,
      "loss": 1.0336,
      "step": 15200
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.8992091417312622,
      "learning_rate": 4.149183344835519e-05,
      "loss": 1.0085,
      "step": 15600
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.9057950973510742,
      "learning_rate": 4.126178974005061e-05,
      "loss": 1.0018,
      "step": 16000
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.9125655889511108,
      "learning_rate": 4.103174603174603e-05,
      "loss": 1.012,
      "step": 16400
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.9547329545021057,
      "learning_rate": 4.0801702323441453e-05,
      "loss": 1.0029,
      "step": 16800
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.8895798921585083,
      "learning_rate": 4.0571658615136876e-05,
      "loss": 0.9989,
      "step": 17200
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.2028740644454956,
      "eval_runtime": 240.0931,
      "eval_samples_per_second": 251.048,
      "eval_steps_per_second": 3.923,
      "step": 17548
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.8451918363571167,
      "learning_rate": 4.03416149068323e-05,
      "loss": 0.9939,
      "step": 17600
    },
    {
      "epoch": 1.03,
      "grad_norm": 1.025611162185669,
      "learning_rate": 4.011214630779848e-05,
      "loss": 0.9472,
      "step": 18000
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.8970223069190979,
      "learning_rate": 3.9882102599493905e-05,
      "loss": 0.9508,
      "step": 18400
    },
    {
      "epoch": 1.07,
      "grad_norm": 1.015277624130249,
      "learning_rate": 3.965205889118933e-05,
      "loss": 0.9473,
      "step": 18800
    },
    {
      "epoch": 1.09,
      "grad_norm": 1.0222784280776978,
      "learning_rate": 3.9422015182884744e-05,
      "loss": 0.938,
      "step": 19200
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.2117902040481567,
      "learning_rate": 3.9191971474580174e-05,
      "loss": 0.942,
      "step": 19600
    },
    {
      "epoch": 1.14,
      "grad_norm": 1.0239405632019043,
      "learning_rate": 3.89619277662756e-05,
      "loss": 0.9258,
      "step": 20000
    },
    {
      "epoch": 1.16,
      "grad_norm": 1.0617647171020508,
      "learning_rate": 3.873188405797102e-05,
      "loss": 0.938,
      "step": 20400
    },
    {
      "epoch": 1.19,
      "grad_norm": 1.1745421886444092,
      "learning_rate": 3.850184034966644e-05,
      "loss": 0.9389,
      "step": 20800
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.8881469964981079,
      "learning_rate": 3.827179664136186e-05,
      "loss": 0.9174,
      "step": 21200
    },
    {
      "epoch": 1.23,
      "grad_norm": 1.0169591903686523,
      "learning_rate": 3.804175293305728e-05,
      "loss": 0.9252,
      "step": 21600
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.9935150742530823,
      "learning_rate": 3.7812284334023465e-05,
      "loss": 0.917,
      "step": 22000
    },
    {
      "epoch": 1.28,
      "grad_norm": 1.0090179443359375,
      "learning_rate": 3.758224062571889e-05,
      "loss": 0.9175,
      "step": 22400
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.9346493482589722,
      "learning_rate": 3.735277202668507e-05,
      "loss": 0.9142,
      "step": 22800
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.1784305572509766,
      "learning_rate": 3.7122728318380494e-05,
      "loss": 0.9255,
      "step": 23200
    },
    {
      "epoch": 1.34,
      "grad_norm": 1.1745367050170898,
      "learning_rate": 3.689268461007592e-05,
      "loss": 0.9005,
      "step": 23600
    },
    {
      "epoch": 1.37,
      "grad_norm": 1.0601255893707275,
      "learning_rate": 3.666264090177134e-05,
      "loss": 0.9079,
      "step": 24000
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.9625568985939026,
      "learning_rate": 3.643259719346676e-05,
      "loss": 0.9069,
      "step": 24400
    },
    {
      "epoch": 1.41,
      "grad_norm": 1.1604766845703125,
      "learning_rate": 3.6202553485162186e-05,
      "loss": 0.9088,
      "step": 24800
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.964094877243042,
      "learning_rate": 3.59725097768576e-05,
      "loss": 0.8905,
      "step": 25200
    },
    {
      "epoch": 1.46,
      "grad_norm": 1.117232084274292,
      "learning_rate": 3.5742466068553025e-05,
      "loss": 0.8938,
      "step": 25600
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.895959198474884,
      "learning_rate": 3.551299746951921e-05,
      "loss": 0.9024,
      "step": 26000
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.0832242965698242,
      "learning_rate": 3.528295376121463e-05,
      "loss": 0.886,
      "step": 26400
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.8419983386993408,
      "learning_rate": 3.5052910052910054e-05,
      "loss": 0.883,
      "step": 26800
    },
    {
      "epoch": 1.55,
      "grad_norm": 1.092869758605957,
      "learning_rate": 3.482286634460548e-05,
      "loss": 0.8789,
      "step": 27200
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.8986368775367737,
      "learning_rate": 3.45928226363009e-05,
      "loss": 0.8817,
      "step": 27600
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.054891586303711,
      "learning_rate": 3.436277892799632e-05,
      "loss": 0.8864,
      "step": 28000
    },
    {
      "epoch": 1.62,
      "grad_norm": 1.1837884187698364,
      "learning_rate": 3.413273521969174e-05,
      "loss": 0.8875,
      "step": 28400
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.942943274974823,
      "learning_rate": 3.390269151138716e-05,
      "loss": 0.8891,
      "step": 28800
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.9877723455429077,
      "learning_rate": 3.3672647803082585e-05,
      "loss": 0.8839,
      "step": 29200
    },
    {
      "epoch": 1.69,
      "grad_norm": 1.034678339958191,
      "learning_rate": 3.344260409477801e-05,
      "loss": 0.8834,
      "step": 29600
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.9877994656562805,
      "learning_rate": 3.321256038647343e-05,
      "loss": 0.8774,
      "step": 30000
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.9292686581611633,
      "learning_rate": 3.2983091787439614e-05,
      "loss": 0.862,
      "step": 30400
    },
    {
      "epoch": 1.76,
      "grad_norm": 1.1605232954025269,
      "learning_rate": 3.275304807913504e-05,
      "loss": 0.8739,
      "step": 30800
    },
    {
      "epoch": 1.78,
      "grad_norm": 1.049849033355713,
      "learning_rate": 3.252300437083046e-05,
      "loss": 0.8661,
      "step": 31200
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.947123110294342,
      "learning_rate": 3.229296066252588e-05,
      "loss": 0.8785,
      "step": 31600
    },
    {
      "epoch": 1.82,
      "grad_norm": 1.2124921083450317,
      "learning_rate": 3.2062916954221306e-05,
      "loss": 0.8637,
      "step": 32000
    },
    {
      "epoch": 1.85,
      "grad_norm": 1.1220165491104126,
      "learning_rate": 3.183344835518749e-05,
      "loss": 0.8617,
      "step": 32400
    },
    {
      "epoch": 1.87,
      "grad_norm": 1.1395636796951294,
      "learning_rate": 3.160340464688291e-05,
      "loss": 0.8619,
      "step": 32800
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.9971738457679749,
      "learning_rate": 3.1373360938578334e-05,
      "loss": 0.8625,
      "step": 33200
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.9140803813934326,
      "learning_rate": 3.114331723027376e-05,
      "loss": 0.8473,
      "step": 33600
    },
    {
      "epoch": 1.94,
      "grad_norm": 1.0617098808288574,
      "learning_rate": 3.091384863123994e-05,
      "loss": 0.8567,
      "step": 34000
    },
    {
      "epoch": 1.96,
      "grad_norm": 1.0239923000335693,
      "learning_rate": 3.068380492293536e-05,
      "loss": 0.8496,
      "step": 34400
    },
    {
      "epoch": 1.98,
      "grad_norm": 1.087548851966858,
      "learning_rate": 3.0453761214630783e-05,
      "loss": 0.8597,
      "step": 34800
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.1792070865631104,
      "eval_runtime": 239.5786,
      "eval_samples_per_second": 251.588,
      "eval_steps_per_second": 3.932,
      "step": 35096
    },
    {
      "epoch": 2.01,
      "grad_norm": 1.0265460014343262,
      "learning_rate": 3.0223717506326206e-05,
      "loss": 0.8358,
      "step": 35200
    },
    {
      "epoch": 2.03,
      "grad_norm": 1.1104140281677246,
      "learning_rate": 2.9993673798021625e-05,
      "loss": 0.803,
      "step": 35600
    },
    {
      "epoch": 2.05,
      "grad_norm": 1.1498385667800903,
      "learning_rate": 2.9763630089717048e-05,
      "loss": 0.7982,
      "step": 36000
    },
    {
      "epoch": 2.07,
      "grad_norm": 1.0795114040374756,
      "learning_rate": 2.953358638141247e-05,
      "loss": 0.7994,
      "step": 36400
    },
    {
      "epoch": 2.1,
      "grad_norm": 1.099506139755249,
      "learning_rate": 2.930354267310789e-05,
      "loss": 0.7913,
      "step": 36800
    },
    {
      "epoch": 2.12,
      "grad_norm": 1.0215864181518555,
      "learning_rate": 2.9073498964803314e-05,
      "loss": 0.7922,
      "step": 37200
    },
    {
      "epoch": 2.14,
      "grad_norm": 1.0832349061965942,
      "learning_rate": 2.8843455256498737e-05,
      "loss": 0.8048,
      "step": 37600
    },
    {
      "epoch": 2.17,
      "grad_norm": 1.1585180759429932,
      "learning_rate": 2.8613411548194156e-05,
      "loss": 0.8023,
      "step": 38000
    },
    {
      "epoch": 2.19,
      "grad_norm": 1.0157803297042847,
      "learning_rate": 2.838336783988958e-05,
      "loss": 0.7967,
      "step": 38400
    },
    {
      "epoch": 2.21,
      "grad_norm": 1.0723109245300293,
      "learning_rate": 2.8153324131585002e-05,
      "loss": 0.8037,
      "step": 38800
    },
    {
      "epoch": 2.23,
      "grad_norm": 1.2227352857589722,
      "learning_rate": 2.7923280423280422e-05,
      "loss": 0.7981,
      "step": 39200
    },
    {
      "epoch": 2.26,
      "grad_norm": 1.09991455078125,
      "learning_rate": 2.7693811824246608e-05,
      "loss": 0.7913,
      "step": 39600
    },
    {
      "epoch": 2.28,
      "grad_norm": 0.9332581162452698,
      "learning_rate": 2.7463768115942028e-05,
      "loss": 0.7874,
      "step": 40000
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.9831389784812927,
      "learning_rate": 2.723372440763745e-05,
      "loss": 0.8003,
      "step": 40400
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.9457577466964722,
      "learning_rate": 2.7003680699332874e-05,
      "loss": 0.7899,
      "step": 40800
    },
    {
      "epoch": 2.35,
      "grad_norm": 1.0081899166107178,
      "learning_rate": 2.6773636991028293e-05,
      "loss": 0.7935,
      "step": 41200
    },
    {
      "epoch": 2.37,
      "grad_norm": 1.0005576610565186,
      "learning_rate": 2.6543593282723716e-05,
      "loss": 0.7812,
      "step": 41600
    },
    {
      "epoch": 2.39,
      "grad_norm": 0.9595048427581787,
      "learning_rate": 2.631354957441914e-05,
      "loss": 0.7858,
      "step": 42000
    },
    {
      "epoch": 2.42,
      "grad_norm": 1.0381603240966797,
      "learning_rate": 2.608350586611456e-05,
      "loss": 0.7904,
      "step": 42400
    },
    {
      "epoch": 2.44,
      "grad_norm": 1.0985316038131714,
      "learning_rate": 2.585346215780999e-05,
      "loss": 0.7894,
      "step": 42800
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.9309560060501099,
      "learning_rate": 2.5623418449505408e-05,
      "loss": 0.7788,
      "step": 43200
    },
    {
      "epoch": 2.48,
      "grad_norm": 1.0824271440505981,
      "learning_rate": 2.539337474120083e-05,
      "loss": 0.7945,
      "step": 43600
    },
    {
      "epoch": 2.51,
      "grad_norm": 0.9344823360443115,
      "learning_rate": 2.5163906142167014e-05,
      "loss": 0.7908,
      "step": 44000
    },
    {
      "epoch": 2.53,
      "grad_norm": 1.1404321193695068,
      "learning_rate": 2.4933862433862434e-05,
      "loss": 0.7882,
      "step": 44400
    },
    {
      "epoch": 2.55,
      "grad_norm": 1.010349154472351,
      "learning_rate": 2.4703818725557856e-05,
      "loss": 0.7857,
      "step": 44800
    },
    {
      "epoch": 2.58,
      "grad_norm": 1.0520751476287842,
      "learning_rate": 2.447377501725328e-05,
      "loss": 0.7699,
      "step": 45200
    },
    {
      "epoch": 2.6,
      "grad_norm": 1.0577901601791382,
      "learning_rate": 2.42437313089487e-05,
      "loss": 0.7803,
      "step": 45600
    },
    {
      "epoch": 2.62,
      "grad_norm": 1.153037190437317,
      "learning_rate": 2.4014262709914885e-05,
      "loss": 0.7761,
      "step": 46000
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.9152491092681885,
      "learning_rate": 2.3784219001610308e-05,
      "loss": 0.7751,
      "step": 46400
    },
    {
      "epoch": 2.67,
      "grad_norm": 1.199794888496399,
      "learning_rate": 2.355417529330573e-05,
      "loss": 0.7734,
      "step": 46800
    },
    {
      "epoch": 2.69,
      "grad_norm": 0.9831721782684326,
      "learning_rate": 2.332413158500115e-05,
      "loss": 0.7789,
      "step": 47200
    },
    {
      "epoch": 2.71,
      "grad_norm": 1.1802157163619995,
      "learning_rate": 2.3094087876696574e-05,
      "loss": 0.7707,
      "step": 47600
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.9477954506874084,
      "learning_rate": 2.2864044168391997e-05,
      "loss": 0.7804,
      "step": 48000
    },
    {
      "epoch": 2.76,
      "grad_norm": 1.1847792863845825,
      "learning_rate": 2.263457556935818e-05,
      "loss": 0.7693,
      "step": 48400
    },
    {
      "epoch": 2.78,
      "grad_norm": 1.0687909126281738,
      "learning_rate": 2.2405106970324362e-05,
      "loss": 0.7626,
      "step": 48800
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.9772168397903442,
      "learning_rate": 2.2175063262019785e-05,
      "loss": 0.7675,
      "step": 49200
    },
    {
      "epoch": 2.83,
      "grad_norm": 1.08980393409729,
      "learning_rate": 2.1945594662985968e-05,
      "loss": 0.7613,
      "step": 49600
    },
    {
      "epoch": 2.85,
      "grad_norm": 1.1358890533447266,
      "learning_rate": 2.171555095468139e-05,
      "loss": 0.7592,
      "step": 50000
    },
    {
      "epoch": 2.87,
      "grad_norm": 1.0059512853622437,
      "learning_rate": 2.1485507246376814e-05,
      "loss": 0.7773,
      "step": 50400
    },
    {
      "epoch": 2.89,
      "grad_norm": 1.0758243799209595,
      "learning_rate": 2.1255463538072234e-05,
      "loss": 0.7696,
      "step": 50800
    },
    {
      "epoch": 2.92,
      "grad_norm": 1.2823022603988647,
      "learning_rate": 2.1025419829767657e-05,
      "loss": 0.7696,
      "step": 51200
    },
    {
      "epoch": 2.94,
      "grad_norm": 1.033719539642334,
      "learning_rate": 2.079537612146308e-05,
      "loss": 0.7717,
      "step": 51600
    },
    {
      "epoch": 2.96,
      "grad_norm": 1.052535057067871,
      "learning_rate": 2.05653324131585e-05,
      "loss": 0.7688,
      "step": 52000
    },
    {
      "epoch": 2.99,
      "grad_norm": 1.2081596851348877,
      "learning_rate": 2.0335288704853922e-05,
      "loss": 0.762,
      "step": 52400
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.1765553951263428,
      "eval_runtime": 239.5578,
      "eval_samples_per_second": 251.609,
      "eval_steps_per_second": 3.932,
      "step": 52644
    },
    {
      "epoch": 3.01,
      "grad_norm": 1.319852352142334,
      "learning_rate": 2.0105244996549345e-05,
      "loss": 0.7468,
      "step": 52800
    },
    {
      "epoch": 3.03,
      "grad_norm": 1.0952869653701782,
      "learning_rate": 1.9875201288244768e-05,
      "loss": 0.7276,
      "step": 53200
    },
    {
      "epoch": 3.05,
      "grad_norm": 1.0391849279403687,
      "learning_rate": 1.964515757994019e-05,
      "loss": 0.7167,
      "step": 53600
    },
    {
      "epoch": 3.08,
      "grad_norm": 1.0109496116638184,
      "learning_rate": 1.941511387163561e-05,
      "loss": 0.7224,
      "step": 54000
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.940232515335083,
      "learning_rate": 1.9185070163331034e-05,
      "loss": 0.7269,
      "step": 54400
    },
    {
      "epoch": 3.12,
      "grad_norm": 1.1479814052581787,
      "learning_rate": 1.8955026455026457e-05,
      "loss": 0.7227,
      "step": 54800
    },
    {
      "epoch": 3.15,
      "grad_norm": 1.0427719354629517,
      "learning_rate": 1.8724982746721876e-05,
      "loss": 0.7324,
      "step": 55200
    },
    {
      "epoch": 3.17,
      "grad_norm": 1.1786882877349854,
      "learning_rate": 1.8495514147688063e-05,
      "loss": 0.7123,
      "step": 55600
    },
    {
      "epoch": 3.19,
      "grad_norm": 0.960802435874939,
      "learning_rate": 1.8265470439383482e-05,
      "loss": 0.7126,
      "step": 56000
    },
    {
      "epoch": 3.21,
      "grad_norm": 1.028399109840393,
      "learning_rate": 1.8035426731078905e-05,
      "loss": 0.7183,
      "step": 56400
    },
    {
      "epoch": 3.24,
      "grad_norm": 1.034562587738037,
      "learning_rate": 1.7805383022774328e-05,
      "loss": 0.7224,
      "step": 56800
    },
    {
      "epoch": 3.26,
      "grad_norm": 1.037462830543518,
      "learning_rate": 1.7575339314469748e-05,
      "loss": 0.7183,
      "step": 57200
    },
    {
      "epoch": 3.28,
      "grad_norm": 1.0581607818603516,
      "learning_rate": 1.734529560616517e-05,
      "loss": 0.7152,
      "step": 57600
    },
    {
      "epoch": 3.31,
      "grad_norm": 1.2400821447372437,
      "learning_rate": 1.7115827007131354e-05,
      "loss": 0.7158,
      "step": 58000
    },
    {
      "epoch": 3.33,
      "grad_norm": 1.1965630054473877,
      "learning_rate": 1.6885783298826777e-05,
      "loss": 0.7185,
      "step": 58400
    },
    {
      "epoch": 3.35,
      "grad_norm": 1.040547251701355,
      "learning_rate": 1.6655739590522203e-05,
      "loss": 0.7133,
      "step": 58800
    },
    {
      "epoch": 3.37,
      "grad_norm": 0.9884762167930603,
      "learning_rate": 1.6425695882217622e-05,
      "loss": 0.7165,
      "step": 59200
    },
    {
      "epoch": 3.4,
      "grad_norm": 1.146836757659912,
      "learning_rate": 1.6195652173913045e-05,
      "loss": 0.7239,
      "step": 59600
    },
    {
      "epoch": 3.42,
      "grad_norm": 1.0546859502792358,
      "learning_rate": 1.596560846560847e-05,
      "loss": 0.7044,
      "step": 60000
    },
    {
      "epoch": 3.44,
      "grad_norm": 1.0950185060501099,
      "learning_rate": 1.5735564757303888e-05,
      "loss": 0.7111,
      "step": 60400
    },
    {
      "epoch": 3.46,
      "grad_norm": 1.12638521194458,
      "learning_rate": 1.550552104899931e-05,
      "loss": 0.7158,
      "step": 60800
    },
    {
      "epoch": 3.49,
      "grad_norm": 0.9172453880310059,
      "learning_rate": 1.5275477340694734e-05,
      "loss": 0.7206,
      "step": 61200
    },
    {
      "epoch": 3.51,
      "grad_norm": 1.1066358089447021,
      "learning_rate": 1.5046008741660917e-05,
      "loss": 0.7141,
      "step": 61600
    },
    {
      "epoch": 3.53,
      "grad_norm": 1.1592479944229126,
      "learning_rate": 1.4815965033356338e-05,
      "loss": 0.7163,
      "step": 62000
    },
    {
      "epoch": 3.56,
      "grad_norm": 1.1727585792541504,
      "learning_rate": 1.458592132505176e-05,
      "loss": 0.7194,
      "step": 62400
    },
    {
      "epoch": 3.58,
      "grad_norm": 1.121613621711731,
      "learning_rate": 1.4355877616747182e-05,
      "loss": 0.7147,
      "step": 62800
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.0166244506835938,
      "learning_rate": 1.4125833908442604e-05,
      "loss": 0.7018,
      "step": 63200
    },
    {
      "epoch": 3.62,
      "grad_norm": 1.1400502920150757,
      "learning_rate": 1.3895790200138027e-05,
      "loss": 0.7169,
      "step": 63600
    },
    {
      "epoch": 3.65,
      "grad_norm": 0.9425780773162842,
      "learning_rate": 1.3665746491833448e-05,
      "loss": 0.7081,
      "step": 64000
    },
    {
      "epoch": 3.67,
      "grad_norm": 1.2542381286621094,
      "learning_rate": 1.343627789279963e-05,
      "loss": 0.7069,
      "step": 64400
    },
    {
      "epoch": 3.69,
      "grad_norm": 1.051892876625061,
      "learning_rate": 1.3206234184495055e-05,
      "loss": 0.7068,
      "step": 64800
    },
    {
      "epoch": 3.72,
      "grad_norm": 1.184352993965149,
      "learning_rate": 1.2976190476190478e-05,
      "loss": 0.6931,
      "step": 65200
    },
    {
      "epoch": 3.74,
      "grad_norm": 1.1641604900360107,
      "learning_rate": 1.27461467678859e-05,
      "loss": 0.7096,
      "step": 65600
    },
    {
      "epoch": 3.76,
      "grad_norm": 1.2189286947250366,
      "learning_rate": 1.2516103059581321e-05,
      "loss": 0.7089,
      "step": 66000
    },
    {
      "epoch": 3.78,
      "grad_norm": 1.1561360359191895,
      "learning_rate": 1.2286059351276744e-05,
      "loss": 0.6948,
      "step": 66400
    },
    {
      "epoch": 3.81,
      "grad_norm": 1.360732913017273,
      "learning_rate": 1.2056590752242927e-05,
      "loss": 0.7095,
      "step": 66800
    },
    {
      "epoch": 3.83,
      "grad_norm": 1.2087483406066895,
      "learning_rate": 1.182654704393835e-05,
      "loss": 0.7192,
      "step": 67200
    },
    {
      "epoch": 3.85,
      "grad_norm": 1.1215720176696777,
      "learning_rate": 1.1596503335633771e-05,
      "loss": 0.7024,
      "step": 67600
    },
    {
      "epoch": 3.88,
      "grad_norm": 1.079850196838379,
      "learning_rate": 1.1367034736599954e-05,
      "loss": 0.7035,
      "step": 68000
    },
    {
      "epoch": 3.9,
      "grad_norm": 1.039116382598877,
      "learning_rate": 1.1136991028295377e-05,
      "loss": 0.7129,
      "step": 68400
    },
    {
      "epoch": 3.92,
      "grad_norm": 0.9434814453125,
      "learning_rate": 1.0906947319990798e-05,
      "loss": 0.7059,
      "step": 68800
    },
    {
      "epoch": 3.94,
      "grad_norm": 1.4614238739013672,
      "learning_rate": 1.0676903611686221e-05,
      "loss": 0.7023,
      "step": 69200
    },
    {
      "epoch": 3.97,
      "grad_norm": 1.1363328695297241,
      "learning_rate": 1.0447435012652404e-05,
      "loss": 0.696,
      "step": 69600
    },
    {
      "epoch": 3.99,
      "grad_norm": 1.1234405040740967,
      "learning_rate": 1.0217391304347827e-05,
      "loss": 0.6965,
      "step": 70000
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.1817238330841064,
      "eval_runtime": 239.8686,
      "eval_samples_per_second": 251.283,
      "eval_steps_per_second": 3.927,
      "step": 70192
    },
    {
      "epoch": 4.01,
      "grad_norm": 0.95857834815979,
      "learning_rate": 9.98734759604325e-06,
      "loss": 0.6812,
      "step": 70400
    },
    {
      "epoch": 4.03,
      "grad_norm": 1.084378957748413,
      "learning_rate": 9.757303887738671e-06,
      "loss": 0.6713,
      "step": 70800
    },
    {
      "epoch": 4.06,
      "grad_norm": 1.1601998805999756,
      "learning_rate": 9.527260179434092e-06,
      "loss": 0.6646,
      "step": 71200
    },
    {
      "epoch": 4.08,
      "grad_norm": 1.0843966007232666,
      "learning_rate": 9.297216471129515e-06,
      "loss": 0.6807,
      "step": 71600
    },
    {
      "epoch": 4.1,
      "grad_norm": 1.002375602722168,
      "learning_rate": 9.067172762824937e-06,
      "loss": 0.6679,
      "step": 72000
    },
    {
      "epoch": 4.13,
      "grad_norm": 1.1330301761627197,
      "learning_rate": 8.837129054520358e-06,
      "loss": 0.6739,
      "step": 72400
    },
    {
      "epoch": 4.15,
      "grad_norm": 1.0197635889053345,
      "learning_rate": 8.607085346215783e-06,
      "loss": 0.6726,
      "step": 72800
    },
    {
      "epoch": 4.17,
      "grad_norm": 1.0812021493911743,
      "learning_rate": 8.377041637911204e-06,
      "loss": 0.6695,
      "step": 73200
    },
    {
      "epoch": 4.19,
      "grad_norm": 1.0424731969833374,
      "learning_rate": 8.146997929606625e-06,
      "loss": 0.664,
      "step": 73600
    },
    {
      "epoch": 4.22,
      "grad_norm": 1.256919503211975,
      "learning_rate": 7.916954221302048e-06,
      "loss": 0.6711,
      "step": 74000
    },
    {
      "epoch": 4.24,
      "grad_norm": 1.1702678203582764,
      "learning_rate": 7.68691051299747e-06,
      "loss": 0.6665,
      "step": 74400
    },
    {
      "epoch": 4.26,
      "grad_norm": 1.0422698259353638,
      "learning_rate": 7.4568668046928916e-06,
      "loss": 0.6786,
      "step": 74800
    },
    {
      "epoch": 4.29,
      "grad_norm": 1.0307954549789429,
      "learning_rate": 7.2268230963883145e-06,
      "loss": 0.6822,
      "step": 75200
    },
    {
      "epoch": 4.31,
      "grad_norm": 1.065287470817566,
      "learning_rate": 6.997354497354498e-06,
      "loss": 0.6664,
      "step": 75600
    },
    {
      "epoch": 4.33,
      "grad_norm": 1.0362813472747803,
      "learning_rate": 6.767885898320682e-06,
      "loss": 0.6676,
      "step": 76000
    },
    {
      "epoch": 4.35,
      "grad_norm": 1.0724912881851196,
      "learning_rate": 6.537842190016104e-06,
      "loss": 0.6615,
      "step": 76400
    },
    {
      "epoch": 4.38,
      "grad_norm": 1.1735118627548218,
      "learning_rate": 6.307798481711525e-06,
      "loss": 0.673,
      "step": 76800
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.0449684858322144,
      "learning_rate": 6.0777547734069475e-06,
      "loss": 0.6814,
      "step": 77200
    },
    {
      "epoch": 4.42,
      "grad_norm": 1.135045051574707,
      "learning_rate": 5.84771106510237e-06,
      "loss": 0.667,
      "step": 77600
    },
    {
      "epoch": 4.44,
      "grad_norm": 1.2403273582458496,
      "learning_rate": 5.617667356797792e-06,
      "loss": 0.671,
      "step": 78000
    },
    {
      "epoch": 4.47,
      "grad_norm": 1.1957228183746338,
      "learning_rate": 5.387623648493214e-06,
      "loss": 0.676,
      "step": 78400
    },
    {
      "epoch": 4.49,
      "grad_norm": 1.1031793355941772,
      "learning_rate": 5.157579940188636e-06,
      "loss": 0.6655,
      "step": 78800
    },
    {
      "epoch": 4.51,
      "grad_norm": 1.0661553144454956,
      "learning_rate": 4.92811134115482e-06,
      "loss": 0.6633,
      "step": 79200
    },
    {
      "epoch": 4.54,
      "grad_norm": 1.1029471158981323,
      "learning_rate": 4.698642742121003e-06,
      "loss": 0.6609,
      "step": 79600
    },
    {
      "epoch": 4.56,
      "grad_norm": 1.1163758039474487,
      "learning_rate": 4.468599033816425e-06,
      "loss": 0.6748,
      "step": 80000
    },
    {
      "epoch": 4.58,
      "grad_norm": 1.123824119567871,
      "learning_rate": 4.238555325511848e-06,
      "loss": 0.669,
      "step": 80400
    },
    {
      "epoch": 4.6,
      "grad_norm": 1.264969825744629,
      "learning_rate": 4.00851161720727e-06,
      "loss": 0.6734,
      "step": 80800
    },
    {
      "epoch": 4.63,
      "grad_norm": 1.2568612098693848,
      "learning_rate": 3.7784679089026914e-06,
      "loss": 0.6631,
      "step": 81200
    },
    {
      "epoch": 4.65,
      "grad_norm": 1.034019947052002,
      "learning_rate": 3.548424200598114e-06,
      "loss": 0.6691,
      "step": 81600
    },
    {
      "epoch": 4.67,
      "grad_norm": 1.1293307542800903,
      "learning_rate": 3.3183804922935357e-06,
      "loss": 0.658,
      "step": 82000
    },
    {
      "epoch": 4.7,
      "grad_norm": 1.0022157430648804,
      "learning_rate": 3.0883367839889582e-06,
      "loss": 0.6639,
      "step": 82400
    },
    {
      "epoch": 4.72,
      "grad_norm": 1.226061224937439,
      "learning_rate": 2.85829307568438e-06,
      "loss": 0.6803,
      "step": 82800
    },
    {
      "epoch": 4.74,
      "grad_norm": 1.0893934965133667,
      "learning_rate": 2.628249367379802e-06,
      "loss": 0.6717,
      "step": 83200
    },
    {
      "epoch": 4.76,
      "grad_norm": 1.030418872833252,
      "learning_rate": 2.3982056590752246e-06,
      "loss": 0.6643,
      "step": 83600
    },
    {
      "epoch": 4.79,
      "grad_norm": 1.0590579509735107,
      "learning_rate": 2.1681619507706463e-06,
      "loss": 0.6772,
      "step": 84000
    },
    {
      "epoch": 4.81,
      "grad_norm": 1.1410354375839233,
      "learning_rate": 1.9381182424660685e-06,
      "loss": 0.6613,
      "step": 84400
    },
    {
      "epoch": 4.83,
      "grad_norm": 1.0556975603103638,
      "learning_rate": 1.7080745341614908e-06,
      "loss": 0.6617,
      "step": 84800
    },
    {
      "epoch": 4.86,
      "grad_norm": 1.0033410787582397,
      "learning_rate": 1.478030825856913e-06,
      "loss": 0.6729,
      "step": 85200
    },
    {
      "epoch": 4.88,
      "grad_norm": 1.1760172843933105,
      "learning_rate": 1.247987117552335e-06,
      "loss": 0.66,
      "step": 85600
    },
    {
      "epoch": 4.9,
      "grad_norm": 1.1550168991088867,
      "learning_rate": 1.017943409247757e-06,
      "loss": 0.6642,
      "step": 86000
    },
    {
      "epoch": 4.92,
      "grad_norm": 1.0208549499511719,
      "learning_rate": 7.884748102139407e-07,
      "loss": 0.6628,
      "step": 86400
    },
    {
      "epoch": 4.95,
      "grad_norm": 1.189048171043396,
      "learning_rate": 5.584311019093628e-07,
      "loss": 0.6698,
      "step": 86800
    },
    {
      "epoch": 4.97,
      "grad_norm": 1.133467197418213,
      "learning_rate": 3.283873936047849e-07,
      "loss": 0.662,
      "step": 87200
    },
    {
      "epoch": 4.99,
      "grad_norm": 1.2015764713287354,
      "learning_rate": 9.834368530020704e-08,
      "loss": 0.6641,
      "step": 87600
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.1955666542053223,
      "eval_runtime": 239.5162,
      "eval_samples_per_second": 251.653,
      "eval_steps_per_second": 3.933,
      "step": 87740
    },
    {
      "epoch": 5.0,
      "step": 87740,
      "total_flos": 1.7097588901675008e+18,
      "train_loss": 0.855379424172326,
      "train_runtime": 31438.6261,
      "train_samples_per_second": 89.31,
      "train_steps_per_second": 2.791
    }
  ],
  "logging_steps": 400,
  "max_steps": 87740,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 1.7097588901675008e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}