{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12514377731769036,
  "eval_steps": 50,
  "global_step": 85,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014722797331492984,
      "grad_norm": 0.26644960045814514,
      "learning_rate": 7.499999999999999e-06,
      "loss": 0.296,
      "step": 1
    },
    {
      "epoch": 0.0014722797331492984,
      "eval_loss": 0.4772031009197235,
      "eval_runtime": 847.2862,
      "eval_samples_per_second": 2.7,
      "eval_steps_per_second": 1.35,
      "step": 1
    },
    {
      "epoch": 0.0029445594662985968,
      "grad_norm": 0.4351513385772705,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 0.408,
      "step": 2
    },
    {
      "epoch": 0.004416839199447895,
      "grad_norm": 0.3042258024215698,
      "learning_rate": 2.2499999999999998e-05,
      "loss": 0.393,
      "step": 3
    },
    {
      "epoch": 0.0058891189325971935,
      "grad_norm": 0.3164433538913727,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.409,
      "step": 4
    },
    {
      "epoch": 0.007361398665746492,
      "grad_norm": 0.37835752964019775,
      "learning_rate": 3.75e-05,
      "loss": 0.2635,
      "step": 5
    },
    {
      "epoch": 0.00883367839889579,
      "grad_norm": 0.22859500348567963,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 0.2615,
      "step": 6
    },
    {
      "epoch": 0.010305958132045089,
      "grad_norm": 0.37722575664520264,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 0.296,
      "step": 7
    },
    {
      "epoch": 0.011778237865194387,
      "grad_norm": 0.8506933450698853,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.2655,
      "step": 8
    },
    {
      "epoch": 0.013250517598343685,
      "grad_norm": 0.45279720425605774,
      "learning_rate": 6.75e-05,
      "loss": 0.259,
      "step": 9
    },
    {
      "epoch": 0.014722797331492983,
      "grad_norm": 0.18526464700698853,
      "learning_rate": 7.5e-05,
      "loss": 0.2053,
      "step": 10
    },
    {
      "epoch": 0.016195077064642283,
      "grad_norm": 0.20497167110443115,
      "learning_rate": 8.25e-05,
      "loss": 0.1554,
      "step": 11
    },
    {
      "epoch": 0.01766735679779158,
      "grad_norm": 0.14627239108085632,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.1306,
      "step": 12
    },
    {
      "epoch": 0.01913963653094088,
      "grad_norm": 0.240932434797287,
      "learning_rate": 9.75e-05,
      "loss": 0.1564,
      "step": 13
    },
    {
      "epoch": 0.020611916264090178,
      "grad_norm": 0.3040555715560913,
      "learning_rate": 0.00010499999999999999,
      "loss": 0.1677,
      "step": 14
    },
    {
      "epoch": 0.022084195997239476,
      "grad_norm": 0.4959651231765747,
      "learning_rate": 0.0001125,
      "loss": 0.3867,
      "step": 15
    },
    {
      "epoch": 0.023556475730388774,
      "grad_norm": 0.20291835069656372,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.2207,
      "step": 16
    },
    {
      "epoch": 0.025028755463538072,
      "grad_norm": 0.16518566012382507,
      "learning_rate": 0.00012749999999999998,
      "loss": 0.1309,
      "step": 17
    },
    {
      "epoch": 0.02650103519668737,
      "grad_norm": 0.18677189946174622,
      "learning_rate": 0.000135,
      "loss": 0.181,
      "step": 18
    },
    {
      "epoch": 0.02797331492983667,
      "grad_norm": 0.1576640009880066,
      "learning_rate": 0.0001425,
      "loss": 0.1562,
      "step": 19
    },
    {
      "epoch": 0.029445594662985967,
      "grad_norm": 0.19666102528572083,
      "learning_rate": 0.00015,
      "loss": 0.2439,
      "step": 20
    },
    {
      "epoch": 0.030917874396135265,
      "grad_norm": 0.12512515485286713,
      "learning_rate": 0.00014998857713672935,
      "loss": 0.144,
      "step": 21
    },
    {
      "epoch": 0.03239015412928457,
      "grad_norm": 0.1219751164317131,
      "learning_rate": 0.00014995431202643217,
      "loss": 0.1047,
      "step": 22
    },
    {
      "epoch": 0.033862433862433865,
      "grad_norm": 0.1390693038702011,
      "learning_rate": 0.000149897215106593,
      "loss": 0.1022,
      "step": 23
    },
    {
      "epoch": 0.03533471359558316,
      "grad_norm": 0.19809921085834503,
      "learning_rate": 0.0001498173037694868,
      "loss": 0.24,
      "step": 24
    },
    {
      "epoch": 0.03680699332873246,
      "grad_norm": 0.17452572286128998,
      "learning_rate": 0.0001497146023568809,
      "loss": 0.2497,
      "step": 25
    },
    {
      "epoch": 0.03827927306188176,
      "grad_norm": 0.10941721498966217,
      "learning_rate": 0.00014958914215262048,
      "loss": 0.0914,
      "step": 26
    },
    {
      "epoch": 0.03975155279503106,
      "grad_norm": 0.12793776392936707,
      "learning_rate": 0.00014944096137309914,
      "loss": 0.114,
      "step": 27
    },
    {
      "epoch": 0.041223832528180356,
      "grad_norm": 0.14925755560398102,
      "learning_rate": 0.00014927010515561776,
      "loss": 0.1931,
      "step": 28
    },
    {
      "epoch": 0.042696112261329654,
      "grad_norm": 0.12749770283699036,
      "learning_rate": 0.00014907662554463532,
      "loss": 0.1342,
      "step": 29
    },
    {
      "epoch": 0.04416839199447895,
      "grad_norm": 0.12666098773479462,
      "learning_rate": 0.0001488605814759156,
      "loss": 0.1404,
      "step": 30
    },
    {
      "epoch": 0.04564067172762825,
      "grad_norm": 0.12451935559511185,
      "learning_rate": 0.00014862203875857477,
      "loss": 0.1297,
      "step": 31
    },
    {
      "epoch": 0.04711295146077755,
      "grad_norm": 0.12354013323783875,
      "learning_rate": 0.0001483610700550354,
      "loss": 0.0667,
      "step": 32
    },
    {
      "epoch": 0.048585231193926846,
      "grad_norm": 0.11861127614974976,
      "learning_rate": 0.00014807775485889264,
      "loss": 0.1057,
      "step": 33
    },
    {
      "epoch": 0.050057510927076145,
      "grad_norm": 0.11489235609769821,
      "learning_rate": 0.0001477721794706997,
      "loss": 0.0717,
      "step": 34
    },
    {
      "epoch": 0.05152979066022544,
      "grad_norm": 0.15129899978637695,
      "learning_rate": 0.0001474444369716801,
      "loss": 0.1103,
      "step": 35
    },
    {
      "epoch": 0.05300207039337474,
      "grad_norm": 0.14446967840194702,
      "learning_rate": 0.0001470946271953739,
      "loss": 0.1674,
      "step": 36
    },
    {
      "epoch": 0.05447435012652404,
      "grad_norm": 0.10094312578439713,
      "learning_rate": 0.00014672285669722765,
      "loss": 0.0696,
      "step": 37
    },
    {
      "epoch": 0.05594662985967334,
      "grad_norm": 0.17120350897312164,
      "learning_rate": 0.00014632923872213652,
      "loss": 0.2139,
      "step": 38
    },
    {
      "epoch": 0.057418909592822635,
      "grad_norm": 0.14146435260772705,
      "learning_rate": 0.00014591389316994876,
      "loss": 0.0925,
      "step": 39
    },
    {
      "epoch": 0.058891189325971934,
      "grad_norm": 0.14251448214054108,
      "learning_rate": 0.0001454769465589431,
      "loss": 0.1002,
      "step": 40
    },
    {
      "epoch": 0.06036346905912123,
      "grad_norm": 0.07004090398550034,
      "learning_rate": 0.00014501853198729012,
      "loss": 0.0538,
      "step": 41
    },
    {
      "epoch": 0.06183574879227053,
      "grad_norm": 0.14318852126598358,
      "learning_rate": 0.00014453878909250904,
      "loss": 0.1316,
      "step": 42
    },
    {
      "epoch": 0.06330802852541983,
      "grad_norm": 0.10623105615377426,
      "learning_rate": 0.00014403786400893302,
      "loss": 0.0866,
      "step": 43
    },
    {
      "epoch": 0.06478030825856913,
      "grad_norm": 0.10893028974533081,
      "learning_rate": 0.00014351590932319504,
      "loss": 0.0518,
      "step": 44
    },
    {
      "epoch": 0.06625258799171843,
      "grad_norm": 0.1411529928445816,
      "learning_rate": 0.00014297308402774875,
      "loss": 0.1357,
      "step": 45
    },
    {
      "epoch": 0.06772486772486773,
      "grad_norm": 0.10105417668819427,
      "learning_rate": 0.0001424095534724375,
      "loss": 0.0654,
      "step": 46
    },
    {
      "epoch": 0.06919714745801703,
      "grad_norm": 0.14420634508132935,
      "learning_rate": 0.00014182548931412757,
      "loss": 0.0935,
      "step": 47
    },
    {
      "epoch": 0.07066942719116633,
      "grad_norm": 0.12569449841976166,
      "learning_rate": 0.0001412210694644195,
      "loss": 0.0848,
      "step": 48
    },
    {
      "epoch": 0.07214170692431562,
      "grad_norm": 0.09209802001714706,
      "learning_rate": 0.00014059647803545467,
      "loss": 0.0473,
      "step": 49
    },
    {
      "epoch": 0.07361398665746492,
      "grad_norm": 0.12560804188251495,
      "learning_rate": 0.0001399519052838329,
      "loss": 0.0785,
      "step": 50
    },
    {
      "epoch": 0.07361398665746492,
      "eval_loss": 0.08997488021850586,
      "eval_runtime": 784.5444,
      "eval_samples_per_second": 2.916,
      "eval_steps_per_second": 1.458,
      "step": 50
    },
    {
      "epoch": 0.07508626639061422,
      "grad_norm": 0.15386323630809784,
      "learning_rate": 0.00013928754755265842,
      "loss": 0.1427,
      "step": 51
    },
    {
      "epoch": 0.07655854612376352,
      "grad_norm": 0.12584620714187622,
      "learning_rate": 0.00013860360721173193,
      "loss": 0.0863,
      "step": 52
    },
    {
      "epoch": 0.07803082585691282,
      "grad_norm": 0.11394777148962021,
      "learning_rate": 0.0001379002925959068,
      "loss": 0.0691,
      "step": 53
    },
    {
      "epoch": 0.07950310559006211,
      "grad_norm": 0.10938312113285065,
      "learning_rate": 0.0001371778179416281,
      "loss": 0.0826,
      "step": 54
    },
    {
      "epoch": 0.08097538532321141,
      "grad_norm": 0.12558647990226746,
      "learning_rate": 0.00013643640332167438,
      "loss": 0.0766,
      "step": 55
    },
    {
      "epoch": 0.08244766505636071,
      "grad_norm": 0.10897130519151688,
      "learning_rate": 0.00013567627457812106,
      "loss": 0.062,
      "step": 56
    },
    {
      "epoch": 0.08391994478951001,
      "grad_norm": 0.09030541032552719,
      "learning_rate": 0.00013489766325354695,
      "loss": 0.0393,
      "step": 57
    },
    {
      "epoch": 0.08539222452265931,
      "grad_norm": 0.1143849790096283,
      "learning_rate": 0.00013410080652050412,
      "loss": 0.1219,
      "step": 58
    },
    {
      "epoch": 0.0868645042558086,
      "grad_norm": 0.1283547431230545,
      "learning_rate": 0.0001332859471092728,
      "loss": 0.1195,
      "step": 59
    },
    {
      "epoch": 0.0883367839889579,
      "grad_norm": 0.11828132718801498,
      "learning_rate": 0.00013245333323392333,
      "loss": 0.0925,
      "step": 60
    },
    {
      "epoch": 0.0898090637221072,
      "grad_norm": 0.10878538340330124,
      "learning_rate": 0.0001316032185167079,
      "loss": 0.0542,
      "step": 61
    },
    {
      "epoch": 0.0912813434552565,
      "grad_norm": 0.1320784091949463,
      "learning_rate": 0.00013073586191080457,
      "loss": 0.1005,
      "step": 62
    },
    {
      "epoch": 0.0927536231884058,
      "grad_norm": 0.10936389863491058,
      "learning_rate": 0.00012985152762143778,
      "loss": 0.0526,
      "step": 63
    },
    {
      "epoch": 0.0942259029215551,
      "grad_norm": 0.13538584113121033,
      "learning_rate": 0.00012895048502539882,
      "loss": 0.0956,
      "step": 64
    },
    {
      "epoch": 0.0956981826547044,
      "grad_norm": 0.13087764382362366,
      "learning_rate": 0.00012803300858899104,
      "loss": 0.0795,
      "step": 65
    },
    {
      "epoch": 0.09717046238785369,
      "grad_norm": 0.1554757058620453,
      "learning_rate": 0.0001270993777844248,
      "loss": 0.1455,
      "step": 66
    },
    {
      "epoch": 0.09864274212100299,
      "grad_norm": 0.12131679803133011,
      "learning_rate": 0.0001261498770046874,
      "loss": 0.0625,
      "step": 67
    },
    {
      "epoch": 0.10011502185415229,
      "grad_norm": 0.11470583826303482,
      "learning_rate": 0.00012518479547691435,
      "loss": 0.0903,
      "step": 68
    },
    {
      "epoch": 0.10158730158730159,
      "grad_norm": 0.1023801937699318,
      "learning_rate": 0.00012420442717428804,
      "loss": 0.0845,
      "step": 69
    },
    {
      "epoch": 0.10305958132045089,
      "grad_norm": 0.10249310731887817,
      "learning_rate": 0.00012320907072649044,
      "loss": 0.0539,
      "step": 70
    },
    {
      "epoch": 0.10453186105360018,
      "grad_norm": 0.10111914575099945,
      "learning_rate": 0.0001221990293287378,
      "loss": 0.0424,
      "step": 71
    },
    {
      "epoch": 0.10600414078674948,
      "grad_norm": 0.16136892139911652,
      "learning_rate": 0.00012117461064942435,
      "loss": 0.1277,
      "step": 72
    },
    {
      "epoch": 0.10747642051989878,
      "grad_norm": 0.13022761046886444,
      "learning_rate": 0.00012013612673640363,
      "loss": 0.118,
      "step": 73
    },
    {
      "epoch": 0.10894870025304808,
      "grad_norm": 0.10115568339824677,
      "learning_rate": 0.00011908389392193547,
      "loss": 0.0554,
      "step": 74
    },
    {
      "epoch": 0.11042097998619738,
      "grad_norm": 0.1352306455373764,
      "learning_rate": 0.00011801823272632844,
      "loss": 0.0683,
      "step": 75
    },
    {
      "epoch": 0.11189325971934667,
      "grad_norm": 0.11654029786586761,
      "learning_rate": 0.00011693946776030599,
      "loss": 0.0656,
      "step": 76
    },
    {
      "epoch": 0.11336553945249597,
      "grad_norm": 0.1405310332775116,
      "learning_rate": 0.00011584792762612703,
      "loss": 0.0681,
      "step": 77
    },
    {
      "epoch": 0.11483781918564527,
      "grad_norm": 0.19620081782341003,
      "learning_rate": 0.00011474394481749035,
      "loss": 0.1183,
      "step": 78
    },
    {
      "epoch": 0.11631009891879457,
      "grad_norm": 0.09413562715053558,
      "learning_rate": 0.00011362785561825406,
      "loss": 0.0377,
      "step": 79
    },
    {
      "epoch": 0.11778237865194387,
      "grad_norm": 0.10567747801542282,
      "learning_rate": 0.0001125,
      "loss": 0.0776,
      "step": 80
    },
    {
      "epoch": 0.11925465838509317,
      "grad_norm": 0.15690375864505768,
      "learning_rate": 0.00011136072151847529,
      "loss": 0.0366,
      "step": 81
    },
    {
      "epoch": 0.12072693811824246,
      "grad_norm": 0.09006724506616592,
      "learning_rate": 0.00011021036720894179,
      "loss": 0.0319,
      "step": 82
    },
    {
      "epoch": 0.12219921785139176,
      "grad_norm": 0.1135464459657669,
      "learning_rate": 0.00010904928748046599,
      "loss": 0.0482,
      "step": 83
    },
    {
      "epoch": 0.12367149758454106,
      "grad_norm": 0.09596288949251175,
      "learning_rate": 0.0001078778360091808,
      "loss": 0.0454,
      "step": 84
    },
    {
      "epoch": 0.12514377731769036,
      "grad_norm": 0.17637494206428528,
      "learning_rate": 0.00010669636963055245,
      "loss": 0.1116,
      "step": 85
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.995021026974761e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}