{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 70,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 1.5370203256607056,
      "learning_rate": 0.0,
      "loss": 1.71875,
      "step": 1
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 1.2635160684585571,
      "learning_rate": 5.555555555555556e-06,
      "loss": 1.62890625,
      "step": 2
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 1.1691744327545166,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 1.5576171875,
      "step": 3
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 1.0796048641204834,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.366455078125,
      "step": 4
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.9845981001853943,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.4541015625,
      "step": 5
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8848991394042969,
      "learning_rate": 2.777777777777778e-05,
      "loss": 1.4345703125,
      "step": 6
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.6667224764823914,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.3564453125,
      "step": 7
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.5166143178939819,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.3291015625,
      "step": 8
    },
    {
      "epoch": 0.12857142857142856,
      "grad_norm": 0.22515398263931274,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.10791015625,
      "step": 9
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.19087187945842743,
      "learning_rate": 5e-05,
      "loss": 1.0686798095703125,
      "step": 10
    },
    {
      "epoch": 0.15714285714285714,
      "grad_norm": 0.2104729264974594,
      "learning_rate": 5.555555555555556e-05,
      "loss": 1.2060546875,
      "step": 11
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.14718303084373474,
      "learning_rate": 6.111111111111112e-05,
      "loss": 1.00634765625,
      "step": 12
    },
    {
      "epoch": 0.18571428571428572,
      "grad_norm": 0.16706810891628265,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.2275390625,
      "step": 13
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.16205047070980072,
      "learning_rate": 7.222222222222222e-05,
      "loss": 1.1552734375,
      "step": 14
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.14002586901187897,
      "learning_rate": 7.777777777777778e-05,
      "loss": 1.11474609375,
      "step": 15
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.11632716655731201,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.2568359375,
      "step": 16
    },
    {
      "epoch": 0.24285714285714285,
      "grad_norm": 0.07913663238286972,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.09521484375,
      "step": 17
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.0647306740283966,
      "learning_rate": 9.444444444444444e-05,
      "loss": 1.08740234375,
      "step": 18
    },
    {
      "epoch": 0.2714285714285714,
      "grad_norm": 0.08836376667022705,
      "learning_rate": 0.0001,
      "loss": 1.134765625,
      "step": 19
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.09614553302526474,
      "learning_rate": 9.999798533493594e-05,
      "loss": 1.1533203125,
      "step": 20
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.11298302561044693,
      "learning_rate": 9.99919415201382e-05,
      "loss": 1.16845703125,
      "step": 21
    },
    {
      "epoch": 0.3142857142857143,
      "grad_norm": 0.07566612213850021,
      "learning_rate": 9.998186909677402e-05,
      "loss": 1.06201171875,
      "step": 22
    },
    {
      "epoch": 0.32857142857142857,
      "grad_norm": 0.07081552594900131,
      "learning_rate": 9.996776896673492e-05,
      "loss": 1.1025390625,
      "step": 23
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.052225261926651,
      "learning_rate": 9.994964239255598e-05,
      "loss": 1.0576171875,
      "step": 24
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.051157619804143906,
      "learning_rate": 9.992749099730281e-05,
      "loss": 0.99609375,
      "step": 25
    },
    {
      "epoch": 0.37142857142857144,
      "grad_norm": 0.04909141734242439,
      "learning_rate": 9.990131676442615e-05,
      "loss": 1.10009765625,
      "step": 26
    },
    {
      "epoch": 0.38571428571428573,
      "grad_norm": 0.051664452999830246,
      "learning_rate": 9.987112203758434e-05,
      "loss": 1.0869140625,
      "step": 27
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.05382264778017998,
      "learning_rate": 9.983690952043345e-05,
      "loss": 1.07763671875,
      "step": 28
    },
    {
      "epoch": 0.4142857142857143,
      "grad_norm": 0.04685552790760994,
      "learning_rate": 9.979868227638516e-05,
      "loss": 1.08203125,
      "step": 29
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.044112514704465866,
      "learning_rate": 9.975644372833249e-05,
      "loss": 1.08544921875,
      "step": 30
    },
    {
      "epoch": 0.44285714285714284,
      "grad_norm": 0.04807021841406822,
      "learning_rate": 9.971019765834333e-05,
      "loss": 1.044921875,
      "step": 31
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.044932372868061066,
      "learning_rate": 9.965994820732173e-05,
      "loss": 1.0576171875,
      "step": 32
    },
    {
      "epoch": 0.4714285714285714,
      "grad_norm": 0.04348684847354889,
      "learning_rate": 9.960569987463719e-05,
      "loss": 1.0517578125,
      "step": 33
    },
    {
      "epoch": 0.4857142857142857,
      "grad_norm": 0.042379334568977356,
      "learning_rate": 9.954745751772172e-05,
      "loss": 1.103515625,
      "step": 34
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.03986199572682381,
      "learning_rate": 9.948522635163499e-05,
      "loss": 1.076171875,
      "step": 35
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.03914280980825424,
      "learning_rate": 9.941901194859725e-05,
      "loss": 1.0654296875,
      "step": 36
    },
    {
      "epoch": 0.5285714285714286,
      "grad_norm": 0.037639349699020386,
      "learning_rate": 9.934882023749048e-05,
      "loss": 1.05126953125,
      "step": 37
    },
    {
      "epoch": 0.5428571428571428,
      "grad_norm": 0.03912171721458435,
      "learning_rate": 9.927465750332747e-05,
      "loss": 1.0205078125,
      "step": 38
    },
    {
      "epoch": 0.5571428571428572,
      "grad_norm": 0.03608435392379761,
      "learning_rate": 9.919653038668912e-05,
      "loss": 1.04150390625,
      "step": 39
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.0371897928416729,
      "learning_rate": 9.911444588312976e-05,
      "loss": 1.01953125,
      "step": 40
    },
    {
      "epoch": 0.5857142857142857,
      "grad_norm": 0.03903960809111595,
      "learning_rate": 9.902841134255077e-05,
      "loss": 1.0936279296875,
      "step": 41
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.038740161806344986,
      "learning_rate": 9.893843446854254e-05,
      "loss": 1.06005859375,
      "step": 42
    },
    {
      "epoch": 0.6142857142857143,
      "grad_norm": 0.039114199578762054,
      "learning_rate": 9.88445233176946e-05,
      "loss": 1.05810546875,
      "step": 43
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 0.03906146436929703,
      "learning_rate": 9.874668629887426e-05,
      "loss": 0.96630859375,
      "step": 44
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 0.037451352924108505,
      "learning_rate": 9.864493217247373e-05,
      "loss": 1.02734375,
      "step": 45
    },
    {
      "epoch": 0.6571428571428571,
      "grad_norm": 0.03710811585187912,
      "learning_rate": 9.853927004962556e-05,
      "loss": 1.06591796875,
      "step": 46
    },
    {
      "epoch": 0.6714285714285714,
      "grad_norm": 0.0455041341483593,
      "learning_rate": 9.8429709391387e-05,
      "loss": 0.9853515625,
      "step": 47
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.035515446215867996,
      "learning_rate": 9.831626000789274e-05,
      "loss": 1.0263671875,
      "step": 48
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.03612297400832176,
      "learning_rate": 9.819893205747654e-05,
      "loss": 1.0361328125,
      "step": 49
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.036578841507434845,
      "learning_rate": 9.807773604576159e-05,
      "loss": 0.96533203125,
      "step": 50
    },
    {
      "epoch": 0.7285714285714285,
      "grad_norm": 0.03498220071196556,
      "learning_rate": 9.795268282471998e-05,
      "loss": 1.015625,
      "step": 51
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 0.03724769502878189,
      "learning_rate": 9.782378359170082e-05,
      "loss": 1.041015625,
      "step": 52
    },
    {
      "epoch": 0.7571428571428571,
      "grad_norm": 0.03416800871491432,
      "learning_rate": 9.769104988842775e-05,
      "loss": 0.838134765625,
      "step": 53
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.03408706933259964,
      "learning_rate": 9.75544935999654e-05,
      "loss": 0.81109619140625,
      "step": 54
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 0.04380936920642853,
      "learning_rate": 9.741412695365528e-05,
      "loss": 1.02587890625,
      "step": 55
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.03615158423781395,
      "learning_rate": 9.726996251802087e-05,
      "loss": 1.0185546875,
      "step": 56
    },
    {
      "epoch": 0.8142857142857143,
      "grad_norm": 0.0350247323513031,
      "learning_rate": 9.712201320164228e-05,
      "loss": 1.02197265625,
      "step": 57
    },
    {
      "epoch": 0.8285714285714286,
      "grad_norm": 0.03687237203121185,
      "learning_rate": 9.697029225200033e-05,
      "loss": 1.0048828125,
      "step": 58
    },
    {
      "epoch": 0.8428571428571429,
      "grad_norm": 0.04002695530653,
      "learning_rate": 9.681481325429045e-05,
      "loss": 1.05322265625,
      "step": 59
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.036546625196933746,
      "learning_rate": 9.665559013020615e-05,
      "loss": 1.064453125,
      "step": 60
    },
    {
      "epoch": 0.8714285714285714,
      "grad_norm": 0.036987561732530594,
      "learning_rate": 9.64926371366926e-05,
      "loss": 0.98095703125,
      "step": 61
    },
    {
      "epoch": 0.8857142857142857,
      "grad_norm": 0.03506046533584595,
      "learning_rate": 9.632596886466994e-05,
      "loss": 1.0126953125,
      "step": 62
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.035204075276851654,
      "learning_rate": 9.615560023772684e-05,
      "loss": 0.96533203125,
      "step": 63
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.03650631383061409,
      "learning_rate": 9.598154651078418e-05,
      "loss": 1.0244140625,
      "step": 64
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 0.03606770932674408,
      "learning_rate": 9.580382326872922e-05,
      "loss": 1.00244140625,
      "step": 65
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.034475889056921005,
      "learning_rate": 9.562244642502007e-05,
      "loss": 0.99755859375,
      "step": 66
    },
    {
      "epoch": 0.9571428571428572,
      "grad_norm": 0.03869969770312309,
      "learning_rate": 9.543743222026071e-05,
      "loss": 0.9990234375,
      "step": 67
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 0.035299014300107956,
      "learning_rate": 9.524879722074692e-05,
      "loss": 1.01953125,
      "step": 68
    },
    {
      "epoch": 0.9857142857142858,
      "grad_norm": 0.0372522734105587,
      "learning_rate": 9.505655831698286e-05,
      "loss": 1.04296875,
      "step": 69
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.037406694144010544,
      "learning_rate": 9.486073272216866e-05,
      "loss": 1.0478515625,
      "step": 70
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.93798828125,
      "eval_runtime": 2.2138,
      "eval_samples_per_second": 2.71,
      "eval_steps_per_second": 0.452,
      "step": 70
    },
    {
      "epoch": 1.0142857142857142,
      "grad_norm": 0.036507610231637955,
      "learning_rate": 9.46613379706592e-05,
      "loss": 1.0615234375,
      "step": 71
    },
    {
      "epoch": 1.0285714285714285,
      "grad_norm": 0.03933257237076759,
      "learning_rate": 9.445839191639403e-05,
      "loss": 1.06298828125,
      "step": 72
    },
    {
      "epoch": 1.042857142857143,
      "grad_norm": 0.03883332386612892,
      "learning_rate": 9.425191273129873e-05,
      "loss": 1.05224609375,
      "step": 73
    },
    {
      "epoch": 1.0571428571428572,
      "grad_norm": 0.03544116020202637,
      "learning_rate": 9.404191890365774e-05,
      "loss": 0.891998291015625,
      "step": 74
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 0.03692076727747917,
      "learning_rate": 9.382842923645904e-05,
      "loss": 1.01220703125,
      "step": 75
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.04064275696873665,
      "learning_rate": 9.361146284571031e-05,
      "loss": 0.99951171875,
      "step": 76
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.03858662769198418,
      "learning_rate": 9.339103915872745e-05,
      "loss": 0.9892578125,
      "step": 77
    },
    {
      "epoch": 1.1142857142857143,
      "grad_norm": 0.036362070590257645,
      "learning_rate": 9.316717791239499e-05,
      "loss": 1.0126953125,
      "step": 78
    },
    {
      "epoch": 1.1285714285714286,
      "grad_norm": 0.042795922607183456,
      "learning_rate": 9.29398991513988e-05,
      "loss": 0.904296875,
      "step": 79
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.03503147140145302,
      "learning_rate": 9.27092232264313e-05,
      "loss": 0.84356689453125,
      "step": 80
    },
    {
      "epoch": 1.157142857142857,
      "grad_norm": 0.042715106159448624,
      "learning_rate": 9.247517079236926e-05,
      "loss": 0.95849609375,
      "step": 81
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.035005152225494385,
      "learning_rate": 9.223776280642429e-05,
      "loss": 0.840576171875,
      "step": 82
    },
    {
      "epoch": 1.1857142857142857,
      "grad_norm": 0.03969377279281616,
      "learning_rate": 9.199702052626646e-05,
      "loss": 1.00927734375,
      "step": 83
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.040097057819366455,
      "learning_rate": 9.175296550812066e-05,
      "loss": 0.96484375,
      "step": 84
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 0.03844078630208969,
      "learning_rate": 9.150561960483666e-05,
      "loss": 0.94482421875,
      "step": 85
    },
    {
      "epoch": 1.2285714285714286,
      "grad_norm": 0.04095899313688278,
      "learning_rate": 9.125500496393221e-05,
      "loss": 1.07275390625,
      "step": 86
    },
    {
      "epoch": 1.2428571428571429,
      "grad_norm": 0.0425279326736927,
      "learning_rate": 9.100114402561006e-05,
      "loss": 0.92626953125,
      "step": 87
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.03975928947329521,
      "learning_rate": 9.074405952074858e-05,
      "loss": 0.95458984375,
      "step": 88
    },
    {
      "epoch": 1.2714285714285714,
      "grad_norm": 0.047119978815317154,
      "learning_rate": 9.048377446886647e-05,
      "loss": 0.9716796875,
      "step": 89
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.046727199107408524,
      "learning_rate": 9.022031217606153e-05,
      "loss": 0.98095703125,
      "step": 90
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.040927693247795105,
      "learning_rate": 8.995369623292385e-05,
      "loss": 1.03173828125,
      "step": 91
    },
    {
      "epoch": 1.3142857142857143,
      "grad_norm": 0.04770605266094208,
      "learning_rate": 8.968395051242349e-05,
      "loss": 0.92578125,
      "step": 92
    },
    {
      "epoch": 1.3285714285714285,
      "grad_norm": 0.04084092751145363,
      "learning_rate": 8.941109916777286e-05,
      "loss": 0.9873046875,
      "step": 93
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.04231275990605354,
      "learning_rate": 8.913516663026404e-05,
      "loss": 0.94287109375,
      "step": 94
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 0.04177459329366684,
      "learning_rate": 8.885617760708116e-05,
      "loss": 0.8828125,
      "step": 95
    },
    {
      "epoch": 1.3714285714285714,
      "grad_norm": 0.04704070836305618,
      "learning_rate": 8.857415707908818e-05,
      "loss": 0.9853515625,
      "step": 96
    },
    {
      "epoch": 1.3857142857142857,
      "grad_norm": 0.042378682643175125,
      "learning_rate": 8.828913029859194e-05,
      "loss": 0.96533203125,
      "step": 97
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.04612474888563156,
      "learning_rate": 8.800112278708123e-05,
      "loss": 0.95556640625,
      "step": 98
    },
    {
      "epoch": 1.4142857142857144,
      "grad_norm": 0.04554460942745209,
      "learning_rate": 8.771016033294148e-05,
      "loss": 0.9765625,
      "step": 99
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.043107710778713226,
      "learning_rate": 8.741626898914558e-05,
      "loss": 0.97412109375,
      "step": 100
    },
    {
      "epoch": 1.4428571428571428,
      "grad_norm": 0.045618608593940735,
      "learning_rate": 8.711947507092126e-05,
      "loss": 0.93359375,
      "step": 101
    },
    {
      "epoch": 1.457142857142857,
      "grad_norm": 0.04153142496943474,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.9541015625,
      "step": 102
    },
    {
      "epoch": 1.4714285714285715,
      "grad_norm": 0.04040868580341339,
      "learning_rate": 8.651728606921079e-05,
      "loss": 0.9599609375,
      "step": 103
    },
    {
      "epoch": 1.4857142857142858,
      "grad_norm": 0.05096150189638138,
      "learning_rate": 8.621194490613103e-05,
      "loss": 1.009765625,
      "step": 104
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.04161123186349869,
      "learning_rate": 8.590380900460755e-05,
      "loss": 0.9833984375,
      "step": 105
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.04169192537665367,
      "learning_rate": 8.559290595533526e-05,
      "loss": 0.9697265625,
      "step": 106
    },
    {
      "epoch": 1.5285714285714285,
      "grad_norm": 0.04692216217517853,
      "learning_rate": 8.527926359678135e-05,
      "loss": 0.9560546875,
      "step": 107
    },
    {
      "epoch": 1.5428571428571427,
      "grad_norm": 0.044088274240493774,
      "learning_rate": 8.496291001269259e-05,
      "loss": 0.9375,
      "step": 108
    },
    {
      "epoch": 1.5571428571428572,
      "grad_norm": 0.041295040398836136,
      "learning_rate": 8.464387352958074e-05,
      "loss": 0.95361328125,
      "step": 109
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.04311827942728996,
      "learning_rate": 8.432218271418601e-05,
      "loss": 0.9287109375,
      "step": 110
    },
    {
      "epoch": 1.5857142857142859,
      "grad_norm": 0.04645412787795067,
      "learning_rate": 8.399786637091947e-05,
      "loss": 1.008544921875,
      "step": 111
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.04281448572874069,
      "learning_rate": 8.36709535392836e-05,
      "loss": 0.97119140625,
      "step": 112
    },
    {
      "epoch": 1.6142857142857143,
      "grad_norm": 0.039966315031051636,
      "learning_rate": 8.334147349127222e-05,
      "loss": 0.98046875,
      "step": 113
    },
    {
      "epoch": 1.6285714285714286,
      "grad_norm": 0.047403622418642044,
      "learning_rate": 8.300945572874939e-05,
      "loss": 0.88720703125,
      "step": 114
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 0.04420870169997215,
      "learning_rate": 8.267492998080791e-05,
      "loss": 0.9580078125,
      "step": 115
    },
    {
      "epoch": 1.657142857142857,
      "grad_norm": 0.04278175160288811,
      "learning_rate": 8.233792620110719e-05,
      "loss": 0.99267578125,
      "step": 116
    },
    {
      "epoch": 1.6714285714285713,
      "grad_norm": 0.04950513318181038,
      "learning_rate": 8.19984745651913e-05,
      "loss": 0.9140625,
      "step": 117
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.04335412010550499,
      "learning_rate": 8.1656605467787e-05,
      "loss": 0.95068359375,
      "step": 118
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.04472755640745163,
      "learning_rate": 8.131234952008212e-05,
      "loss": 0.96240234375,
      "step": 119
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.043206386268138885,
      "learning_rate": 8.096573754698473e-05,
      "loss": 0.89599609375,
      "step": 120
    },
    {
      "epoch": 1.7285714285714286,
      "grad_norm": 0.04570404067635536,
      "learning_rate": 8.061680058436298e-05,
      "loss": 0.9423828125,
      "step": 121
    },
    {
      "epoch": 1.7428571428571429,
      "grad_norm": 0.04255395382642746,
      "learning_rate": 8.026556987626607e-05,
      "loss": 0.96875,
      "step": 122
    },
    {
      "epoch": 1.7571428571428571,
      "grad_norm": 0.039799995720386505,
      "learning_rate": 7.99120768721268e-05,
      "loss": 0.78369140625,
      "step": 123
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.04574437811970711,
      "learning_rate": 7.955635322394542e-05,
      "loss": 0.746826171875,
      "step": 124
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 0.04676768183708191,
      "learning_rate": 7.919843078345555e-05,
      "loss": 0.96826171875,
      "step": 125
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.045920632779598236,
      "learning_rate": 7.883834159927212e-05,
      "loss": 0.9521484375,
      "step": 126
    },
    {
      "epoch": 1.8142857142857143,
      "grad_norm": 0.047574810683727264,
      "learning_rate": 7.847611791402181e-05,
      "loss": 0.9560546875,
      "step": 127
    },
    {
      "epoch": 1.8285714285714287,
      "grad_norm": 0.04646388068795204,
      "learning_rate": 7.811179216145588e-05,
      "loss": 0.94482421875,
      "step": 128
    },
    {
      "epoch": 1.842857142857143,
      "grad_norm": 0.04814613610506058,
      "learning_rate": 7.774539696354615e-05,
      "loss": 0.9873046875,
      "step": 129
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.05017926171422005,
      "learning_rate": 7.737696512756394e-05,
      "loss": 1.005859375,
      "step": 130
    },
    {
      "epoch": 1.8714285714285714,
      "grad_norm": 0.043628886342048645,
      "learning_rate": 7.70065296431425e-05,
      "loss": 0.91650390625,
      "step": 131
    },
    {
      "epoch": 1.8857142857142857,
      "grad_norm": 0.0455118864774704,
      "learning_rate": 7.663412367932314e-05,
      "loss": 0.95263671875,
      "step": 132
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.04489551857113838,
      "learning_rate": 7.62597805815852e-05,
      "loss": 0.90283203125,
      "step": 133
    },
    {
      "epoch": 1.9142857142857141,
      "grad_norm": 0.0432695671916008,
      "learning_rate": 7.588353386886026e-05,
      "loss": 0.96630859375,
      "step": 134
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 0.04645658656954765,
      "learning_rate": 7.550541723053088e-05,
      "loss": 0.9375,
      "step": 135
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.04398561641573906,
      "learning_rate": 7.512546452341401e-05,
      "loss": 0.93994140625,
      "step": 136
    },
    {
      "epoch": 1.9571428571428573,
      "grad_norm": 0.043043263256549835,
      "learning_rate": 7.474370976872944e-05,
      "loss": 0.93896484375,
      "step": 137
    },
    {
      "epoch": 1.9714285714285715,
      "grad_norm": 0.04508152976632118,
      "learning_rate": 7.436018714905347e-05,
      "loss": 0.9638671875,
      "step": 138
    },
    {
      "epoch": 1.9857142857142858,
      "grad_norm": 0.043544020503759384,
      "learning_rate": 7.397493100525829e-05,
      "loss": 0.98095703125,
      "step": 139
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.04602934047579765,
      "learning_rate": 7.358797583343691e-05,
      "loss": 0.97900390625,
      "step": 140
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.89306640625,
      "eval_runtime": 2.1996,
      "eval_samples_per_second": 2.728,
      "eval_steps_per_second": 0.455,
      "step": 140
    },
    {
      "epoch": 2.0142857142857142,
      "grad_norm": 0.046280667185783386,
      "learning_rate": 7.319935628181446e-05,
      "loss": 0.99365234375,
      "step": 141
    },
    {
      "epoch": 2.0285714285714285,
      "grad_norm": 0.046611592173576355,
      "learning_rate": 7.280910714764585e-05,
      "loss": 1.0029296875,
      "step": 142
    },
    {
      "epoch": 2.0428571428571427,
      "grad_norm": 0.04613683372735977,
      "learning_rate": 7.241726337409979e-05,
      "loss": 0.99951171875,
      "step": 143
    },
    {
      "epoch": 2.057142857142857,
      "grad_norm": 0.040014706552028656,
      "learning_rate": 7.202386004713008e-05,
      "loss": 0.845367431640625,
      "step": 144
    },
    {
      "epoch": 2.0714285714285716,
      "grad_norm": 0.04537486657500267,
      "learning_rate": 7.162893239233408e-05,
      "loss": 0.9560546875,
      "step": 145
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.050085388123989105,
      "learning_rate": 7.123251577179833e-05,
      "loss": 0.9423828125,
      "step": 146
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.04427152872085571,
      "learning_rate": 7.083464568093249e-05,
      "loss": 0.93212890625,
      "step": 147
    },
    {
      "epoch": 2.1142857142857143,
      "grad_norm": 0.050130926072597504,
      "learning_rate": 7.043535774529087e-05,
      "loss": 0.9580078125,
      "step": 148
    },
    {
      "epoch": 2.1285714285714286,
      "grad_norm": 0.05082038417458534,
      "learning_rate": 7.003468771738255e-05,
      "loss": 0.85888671875,
      "step": 149
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.04404108598828316,
      "learning_rate": 6.963267147347007e-05,
      "loss": 0.7931671142578125,
      "step": 150
    },
    {
      "epoch": 2.157142857142857,
      "grad_norm": 0.048873648047447205,
      "learning_rate": 6.922934501035709e-05,
      "loss": 0.9072265625,
      "step": 151
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.03908224776387215,
      "learning_rate": 6.882474444216513e-05,
      "loss": 0.8017578125,
      "step": 152
    },
    {
      "epoch": 2.185714285714286,
      "grad_norm": 0.04746107757091522,
      "learning_rate": 6.841890599709994e-05,
      "loss": 0.95703125,
      "step": 153
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.04566887393593788,
      "learning_rate": 6.801186601420766e-05,
      "loss": 0.916015625,
      "step": 154
    },
    {
      "epoch": 2.2142857142857144,
      "grad_norm": 0.04792994260787964,
      "learning_rate": 6.760366094012083e-05,
      "loss": 0.89794921875,
      "step": 155
    },
    {
      "epoch": 2.2285714285714286,
      "grad_norm": 0.04765713959932327,
      "learning_rate": 6.719432732579508e-05,
      "loss": 1.01904296875,
      "step": 156
    },
    {
      "epoch": 2.242857142857143,
      "grad_norm": 0.04851759225130081,
      "learning_rate": 6.67839018232363e-05,
      "loss": 0.875,
      "step": 157
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.04878833889961243,
      "learning_rate": 6.63724211822188e-05,
      "loss": 0.90869140625,
      "step": 158
    },
    {
      "epoch": 2.2714285714285714,
      "grad_norm": 0.05301643908023834,
      "learning_rate": 6.595992224699463e-05,
      "loss": 0.91796875,
      "step": 159
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.051798202097415924,
      "learning_rate": 6.554644195299467e-05,
      "loss": 0.92529296875,
      "step": 160
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.04964352399110794,
      "learning_rate": 6.513201732352124e-05,
      "loss": 0.98388671875,
      "step": 161
    },
    {
      "epoch": 2.314285714285714,
      "grad_norm": 0.048345692455768585,
      "learning_rate": 6.471668546643312e-05,
      "loss": 0.87939453125,
      "step": 162
    },
    {
      "epoch": 2.3285714285714287,
      "grad_norm": 0.04840334132313728,
      "learning_rate": 6.430048357082287e-05,
      "loss": 0.94287109375,
      "step": 163
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.04917162284255028,
      "learning_rate": 6.388344890368693e-05,
      "loss": 0.89990234375,
      "step": 164
    },
    {
      "epoch": 2.357142857142857,
      "grad_norm": 0.04613529145717621,
      "learning_rate": 6.346561880658852e-05,
      "loss": 0.83447265625,
      "step": 165
    },
    {
      "epoch": 2.3714285714285714,
      "grad_norm": 0.04937538877129555,
      "learning_rate": 6.304703069231434e-05,
      "loss": 0.94091796875,
      "step": 166
    },
    {
      "epoch": 2.3857142857142857,
      "grad_norm": 0.04908490553498268,
      "learning_rate": 6.262772204152436e-05,
      "loss": 0.91748046875,
      "step": 167
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.05064590647816658,
      "learning_rate": 6.220773039939592e-05,
      "loss": 0.90869140625,
      "step": 168
    },
    {
      "epoch": 2.414285714285714,
      "grad_norm": 0.0501258559525013,
      "learning_rate": 6.178709337226182e-05,
      "loss": 0.93115234375,
      "step": 169
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.04868542030453682,
      "learning_rate": 6.136584862424312e-05,
      "loss": 0.92724609375,
      "step": 170
    },
    {
      "epoch": 2.442857142857143,
      "grad_norm": 0.05527665466070175,
      "learning_rate": 6.0944033873876616e-05,
      "loss": 0.8837890625,
      "step": 171
    },
    {
      "epoch": 2.4571428571428573,
      "grad_norm": 0.04786409065127373,
      "learning_rate": 6.0521686890737396e-05,
      "loss": 0.91015625,
      "step": 172
    },
    {
      "epoch": 2.4714285714285715,
      "grad_norm": 0.044612202793359756,
      "learning_rate": 6.009884549205715e-05,
      "loss": 0.91796875,
      "step": 173
    },
    {
      "epoch": 2.4857142857142858,
      "grad_norm": 0.04983896762132645,
      "learning_rate": 5.96755475393378e-05,
      "loss": 0.966796875,
      "step": 174
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.04861399903893471,
      "learning_rate": 5.9251830934961414e-05,
      "loss": 0.94189453125,
      "step": 175
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.048787105828523636,
      "learning_rate": 5.882773361879645e-05,
      "loss": 0.9267578125,
      "step": 176
    },
    {
      "epoch": 2.5285714285714285,
      "grad_norm": 0.05140867829322815,
      "learning_rate": 5.8403293564800564e-05,
      "loss": 0.9140625,
      "step": 177
    },
    {
      "epoch": 2.5428571428571427,
      "grad_norm": 0.05104586109519005,
      "learning_rate": 5.7978548777620303e-05,
      "loss": 0.8974609375,
      "step": 178
    },
    {
      "epoch": 2.557142857142857,
      "grad_norm": 0.051857445389032364,
      "learning_rate": 5.755353728918834e-05,
      "loss": 0.90966796875,
      "step": 179
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.04690718650817871,
      "learning_rate": 5.712829715531787e-05,
      "loss": 0.88916015625,
      "step": 180
    },
    {
      "epoch": 2.585714285714286,
      "grad_norm": 0.05306775122880936,
      "learning_rate": 5.670286645229518e-05,
      "loss": 0.9661865234375,
      "step": 181
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.05184696242213249,
      "learning_rate": 5.627728327347025e-05,
      "loss": 0.9296875,
      "step": 182
    },
    {
      "epoch": 2.6142857142857143,
      "grad_norm": 0.046935904771089554,
      "learning_rate": 5.5851585725845854e-05,
      "loss": 0.93896484375,
      "step": 183
    },
    {
      "epoch": 2.6285714285714286,
      "grad_norm": 0.053297340869903564,
      "learning_rate": 5.5425811926665426e-05,
      "loss": 0.84423828125,
      "step": 184
    },
    {
      "epoch": 2.642857142857143,
      "grad_norm": 0.05101242661476135,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.92041015625,
      "step": 185
    },
    {
      "epoch": 2.657142857142857,
      "grad_norm": 0.047452762722969055,
      "learning_rate": 5.457418807333458e-05,
      "loss": 0.95556640625,
      "step": 186
    },
    {
      "epoch": 2.6714285714285713,
      "grad_norm": 0.05259615555405617,
      "learning_rate": 5.4148414274154156e-05,
      "loss": 0.87646484375,
      "step": 187
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.051185209304094315,
      "learning_rate": 5.3722716726529775e-05,
      "loss": 0.91455078125,
      "step": 188
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.05002773553133011,
      "learning_rate": 5.3297133547704845e-05,
      "loss": 0.92431640625,
      "step": 189
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.047548212110996246,
      "learning_rate": 5.2871702844682156e-05,
      "loss": 0.8603515625,
      "step": 190
    },
    {
      "epoch": 2.7285714285714286,
      "grad_norm": 0.04842185601592064,
      "learning_rate": 5.2446462710811675e-05,
      "loss": 0.90234375,
      "step": 191
    },
    {
      "epoch": 2.742857142857143,
      "grad_norm": 0.05007163807749748,
      "learning_rate": 5.20214512223797e-05,
      "loss": 0.9326171875,
      "step": 192
    },
    {
      "epoch": 2.757142857142857,
      "grad_norm": 0.04509156197309494,
      "learning_rate": 5.159670643519946e-05,
      "loss": 0.752685546875,
      "step": 193
    },
    {
      "epoch": 2.7714285714285714,
      "grad_norm": 0.04984093829989433,
      "learning_rate": 5.117226638120356e-05,
      "loss": 0.7127685546875,
      "step": 194
    },
    {
      "epoch": 2.7857142857142856,
      "grad_norm": 0.05356363207101822,
      "learning_rate": 5.0748169065038596e-05,
      "loss": 0.93603515625,
      "step": 195
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.049684904515743256,
      "learning_rate": 5.032445246066223e-05,
      "loss": 0.9169921875,
      "step": 196
    },
    {
      "epoch": 2.814285714285714,
      "grad_norm": 0.0515378974378109,
      "learning_rate": 4.990115450794286e-05,
      "loss": 0.91943359375,
      "step": 197
    },
    {
      "epoch": 2.8285714285714287,
      "grad_norm": 0.05335700139403343,
      "learning_rate": 4.947831310926261e-05,
      "loss": 0.90869140625,
      "step": 198
    },
    {
      "epoch": 2.842857142857143,
      "grad_norm": 0.049173396080732346,
      "learning_rate": 4.905596612612341e-05,
      "loss": 0.95166015625,
      "step": 199
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.05383915826678276,
      "learning_rate": 4.8634151375756875e-05,
      "loss": 0.97216796875,
      "step": 200
    },
    {
      "epoch": 2.8714285714285714,
      "grad_norm": 0.04927995428442955,
      "learning_rate": 4.821290662773819e-05,
      "loss": 0.88037109375,
      "step": 201
    },
    {
      "epoch": 2.8857142857142857,
      "grad_norm": 0.04969802498817444,
      "learning_rate": 4.779226960060411e-05,
      "loss": 0.91943359375,
      "step": 202
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.04692715033888817,
      "learning_rate": 4.737227795847565e-05,
      "loss": 0.86865234375,
      "step": 203
    },
    {
      "epoch": 2.914285714285714,
      "grad_norm": 0.04850691184401512,
      "learning_rate": 4.695296930768567e-05,
      "loss": 0.9326171875,
      "step": 204
    },
    {
      "epoch": 2.928571428571429,
      "grad_norm": 0.04940219596028328,
      "learning_rate": 4.653438119341149e-05,
      "loss": 0.90283203125,
      "step": 205
    },
    {
      "epoch": 2.942857142857143,
      "grad_norm": 0.04640163481235504,
      "learning_rate": 4.6116551096313085e-05,
      "loss": 0.90625,
      "step": 206
    },
    {
      "epoch": 2.9571428571428573,
      "grad_norm": 0.05001261085271835,
      "learning_rate": 4.5699516429177116e-05,
      "loss": 0.90673828125,
      "step": 207
    },
    {
      "epoch": 2.9714285714285715,
      "grad_norm": 0.04668058827519417,
      "learning_rate": 4.528331453356689e-05,
      "loss": 0.93115234375,
      "step": 208
    },
    {
      "epoch": 2.9857142857142858,
      "grad_norm": 0.04703083634376526,
      "learning_rate": 4.486798267647877e-05,
      "loss": 0.95068359375,
      "step": 209
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.049874696880578995,
      "learning_rate": 4.445355804700533e-05,
      "loss": 0.93505859375,
      "step": 210
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.876953125,
      "eval_runtime": 2.2107,
      "eval_samples_per_second": 2.714,
      "eval_steps_per_second": 0.452,
      "step": 210
    },
    {
      "epoch": 3.0142857142857142,
      "grad_norm": 0.04854424297809601,
      "learning_rate": 4.4040077753005374e-05,
      "loss": 0.953125,
      "step": 211
    },
    {
      "epoch": 3.0285714285714285,
      "grad_norm": 0.049803610891103745,
      "learning_rate": 4.362757881778121e-05,
      "loss": 0.97314453125,
      "step": 212
    },
    {
      "epoch": 3.0428571428571427,
      "grad_norm": 0.05409076437354088,
      "learning_rate": 4.3216098176763696e-05,
      "loss": 0.966796875,
      "step": 213
    },
    {
      "epoch": 3.057142857142857,
      "grad_norm": 0.0482853464782238,
      "learning_rate": 4.2805672674204933e-05,
      "loss": 0.81683349609375,
      "step": 214
    },
    {
      "epoch": 3.0714285714285716,
      "grad_norm": 0.048197198659181595,
      "learning_rate": 4.2396339059879184e-05,
      "loss": 0.92333984375,
      "step": 215
    },
    {
      "epoch": 3.085714285714286,
      "grad_norm": 0.05081643909215927,
      "learning_rate": 4.1988133985792356e-05,
      "loss": 0.91162109375,
      "step": 216
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.05412709712982178,
      "learning_rate": 4.158109400290007e-05,
      "loss": 0.89990234375,
      "step": 217
    },
    {
      "epoch": 3.1142857142857143,
      "grad_norm": 0.046897511929273605,
      "learning_rate": 4.117525555783489e-05,
      "loss": 0.92724609375,
      "step": 218
    },
    {
      "epoch": 3.1285714285714286,
      "grad_norm": 0.0496889092028141,
      "learning_rate": 4.077065498964292e-05,
      "loss": 0.8310546875,
      "step": 219
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 0.05350854992866516,
      "learning_rate": 4.036732852652994e-05,
      "loss": 0.7672271728515625,
      "step": 220
    },
    {
      "epoch": 3.157142857142857,
      "grad_norm": 0.05670761317014694,
      "learning_rate": 3.9965312282617464e-05,
      "loss": 0.87841796875,
      "step": 221
    },
    {
      "epoch": 3.1714285714285713,
      "grad_norm": 0.041794054210186005,
      "learning_rate": 3.956464225470914e-05,
      "loss": 0.7783203125,
      "step": 222
    },
    {
      "epoch": 3.185714285714286,
      "grad_norm": 0.0495549812912941,
      "learning_rate": 3.9165354319067516e-05,
      "loss": 0.927734375,
      "step": 223
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.05281737074255943,
      "learning_rate": 3.876748422820168e-05,
      "loss": 0.88720703125,
      "step": 224
    },
    {
      "epoch": 3.2142857142857144,
      "grad_norm": 0.0501176193356514,
      "learning_rate": 3.837106760766594e-05,
      "loss": 0.8701171875,
      "step": 225
    },
    {
      "epoch": 3.2285714285714286,
      "grad_norm": 0.051232192665338516,
      "learning_rate": 3.797613995286993e-05,
      "loss": 0.9892578125,
      "step": 226
    },
    {
      "epoch": 3.242857142857143,
      "grad_norm": 0.05132833123207092,
      "learning_rate": 3.7582736625900224e-05,
      "loss": 0.8447265625,
      "step": 227
    },
    {
      "epoch": 3.257142857142857,
      "grad_norm": 0.05618225038051605,
      "learning_rate": 3.719089285235417e-05,
      "loss": 0.88134765625,
      "step": 228
    },
    {
      "epoch": 3.2714285714285714,
      "grad_norm": 0.0628756508231163,
      "learning_rate": 3.680064371818555e-05,
      "loss": 0.8896484375,
      "step": 229
    },
    {
      "epoch": 3.2857142857142856,
      "grad_norm": 0.056082308292388916,
      "learning_rate": 3.641202416656311e-05,
      "loss": 0.89404296875,
      "step": 230
    },
    {
      "epoch": 3.3,
      "grad_norm": 0.05168178305029869,
      "learning_rate": 3.602506899474173e-05,
      "loss": 0.95556640625,
      "step": 231
    },
    {
      "epoch": 3.314285714285714,
      "grad_norm": 0.051914263516664505,
      "learning_rate": 3.563981285094654e-05,
      "loss": 0.85400390625,
      "step": 232
    },
    {
      "epoch": 3.3285714285714287,
      "grad_norm": 0.051675330847501755,
      "learning_rate": 3.525629023127057e-05,
      "loss": 0.91552734375,
      "step": 233
    },
    {
      "epoch": 3.342857142857143,
      "grad_norm": 0.048695966601371765,
      "learning_rate": 3.487453547658601e-05,
      "loss": 0.875,
      "step": 234
    },
    {
      "epoch": 3.357142857142857,
      "grad_norm": 0.05254810303449631,
      "learning_rate": 3.449458276946914e-05,
      "loss": 0.80712890625,
      "step": 235
    },
    {
      "epoch": 3.3714285714285714,
      "grad_norm": 0.052136149257421494,
      "learning_rate": 3.411646613113976e-05,
      "loss": 0.9140625,
      "step": 236
    },
    {
      "epoch": 3.3857142857142857,
      "grad_norm": 0.05295842885971069,
      "learning_rate": 3.374021941841482e-05,
      "loss": 0.89111328125,
      "step": 237
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.053937479853630066,
      "learning_rate": 3.336587632067686e-05,
      "loss": 0.8779296875,
      "step": 238
    },
    {
      "epoch": 3.414285714285714,
      "grad_norm": 0.0523514524102211,
      "learning_rate": 3.299347035685751e-05,
      "loss": 0.90673828125,
      "step": 239
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 0.05106062814593315,
      "learning_rate": 3.2623034872436084e-05,
      "loss": 0.9013671875,
      "step": 240
    },
    {
      "epoch": 3.442857142857143,
      "grad_norm": 0.054687730967998505,
      "learning_rate": 3.225460303645388e-05,
      "loss": 0.857421875,
      "step": 241
    },
    {
      "epoch": 3.4571428571428573,
      "grad_norm": 0.053257834166288376,
      "learning_rate": 3.188820783854413e-05,
      "loss": 0.8837890625,
      "step": 242
    },
    {
      "epoch": 3.4714285714285715,
      "grad_norm": 0.04854962229728699,
      "learning_rate": 3.1523882085978204e-05,
      "loss": 0.8935546875,
      "step": 243
    },
    {
      "epoch": 3.4857142857142858,
      "grad_norm": 0.0504307858645916,
      "learning_rate": 3.116165840072789e-05,
      "loss": 0.9423828125,
      "step": 244
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.05123041197657585,
      "learning_rate": 3.0801569216544456e-05,
      "loss": 0.91650390625,
      "step": 245
    },
    {
      "epoch": 3.5142857142857142,
      "grad_norm": 0.050109054893255234,
      "learning_rate": 3.0443646776054602e-05,
      "loss": 0.90234375,
      "step": 246
    },
    {
      "epoch": 3.5285714285714285,
      "grad_norm": 0.0505213625729084,
      "learning_rate": 3.0087923127873196e-05,
      "loss": 0.88916015625,
      "step": 247
    },
    {
      "epoch": 3.5428571428571427,
      "grad_norm": 0.04955083131790161,
      "learning_rate": 2.9734430123733936e-05,
      "loss": 0.87353515625,
      "step": 248
    },
    {
      "epoch": 3.557142857142857,
      "grad_norm": 0.050369661301374435,
      "learning_rate": 2.9383199415637042e-05,
      "loss": 0.8837890625,
      "step": 249
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 0.055560868233442307,
      "learning_rate": 2.903426245301526e-05,
      "loss": 0.86474609375,
      "step": 250
    },
    {
      "epoch": 3.585714285714286,
      "grad_norm": 0.054119765758514404,
      "learning_rate": 2.8687650479917883e-05,
      "loss": 0.941162109375,
      "step": 251
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.049803949892520905,
      "learning_rate": 2.8343394532213017e-05,
      "loss": 0.90380859375,
      "step": 252
    },
    {
      "epoch": 3.6142857142857143,
      "grad_norm": 0.05511877313256264,
      "learning_rate": 2.8001525434808705e-05,
      "loss": 0.9169921875,
      "step": 253
    },
    {
      "epoch": 3.6285714285714286,
      "grad_norm": 0.0531773567199707,
      "learning_rate": 2.7662073798892806e-05,
      "loss": 0.8193359375,
      "step": 254
    },
    {
      "epoch": 3.642857142857143,
      "grad_norm": 0.053087010979652405,
      "learning_rate": 2.732507001919209e-05,
      "loss": 0.8994140625,
      "step": 255
    },
    {
      "epoch": 3.657142857142857,
      "grad_norm": 0.051729291677474976,
      "learning_rate": 2.6990544271250608e-05,
      "loss": 0.93310546875,
      "step": 256
    },
    {
      "epoch": 3.6714285714285713,
      "grad_norm": 0.049172382801771164,
      "learning_rate": 2.665852650872779e-05,
      "loss": 0.85498046875,
      "step": 257
    },
    {
      "epoch": 3.685714285714286,
      "grad_norm": 0.051789790391922,
      "learning_rate": 2.6329046460716423e-05,
      "loss": 0.89404296875,
      "step": 258
    },
    {
      "epoch": 3.7,
      "grad_norm": 0.052890848368406296,
      "learning_rate": 2.6002133629080538e-05,
      "loss": 0.904296875,
      "step": 259
    },
    {
      "epoch": 3.7142857142857144,
      "grad_norm": 0.04675760492682457,
      "learning_rate": 2.5677817285813992e-05,
      "loss": 0.83984375,
      "step": 260
    },
    {
      "epoch": 3.7285714285714286,
      "grad_norm": 0.052761152386665344,
      "learning_rate": 2.535612647041929e-05,
      "loss": 0.8828125,
      "step": 261
    },
    {
      "epoch": 3.742857142857143,
      "grad_norm": 0.05000728741288185,
      "learning_rate": 2.5037089987307405e-05,
      "loss": 0.91162109375,
      "step": 262
    },
    {
      "epoch": 3.757142857142857,
      "grad_norm": 0.04449896141886711,
      "learning_rate": 2.4720736403218654e-05,
      "loss": 0.737060546875,
      "step": 263
    },
    {
      "epoch": 3.7714285714285714,
      "grad_norm": 0.04890809580683708,
      "learning_rate": 2.4407094044664748e-05,
      "loss": 0.6920166015625,
      "step": 264
    },
    {
      "epoch": 3.7857142857142856,
      "grad_norm": 0.04929943382740021,
      "learning_rate": 2.4096190995392466e-05,
      "loss": 0.916015625,
      "step": 265
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.04906542971730232,
      "learning_rate": 2.3788055093868964e-05,
      "loss": 0.8955078125,
      "step": 266
    },
    {
      "epoch": 3.814285714285714,
      "grad_norm": 0.05111577361822128,
      "learning_rate": 2.3482713930789225e-05,
      "loss": 0.900390625,
      "step": 267
    },
    {
      "epoch": 3.8285714285714287,
      "grad_norm": 0.048875000327825546,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.888671875,
      "step": 268
    },
    {
      "epoch": 3.842857142857143,
      "grad_norm": 0.049121737480163574,
      "learning_rate": 2.2880524929078745e-05,
      "loss": 0.92919921875,
      "step": 269
    },
    {
      "epoch": 3.857142857142857,
      "grad_norm": 0.04929174482822418,
      "learning_rate": 2.2583731010854436e-05,
      "loss": 0.9521484375,
      "step": 270
    },
    {
      "epoch": 3.8714285714285714,
      "grad_norm": 0.04900052025914192,
      "learning_rate": 2.2289839667058532e-05,
      "loss": 0.85986328125,
      "step": 271
    },
    {
      "epoch": 3.8857142857142857,
      "grad_norm": 0.0492103286087513,
      "learning_rate": 2.199887721291877e-05,
      "loss": 0.8994140625,
      "step": 272
    },
    {
      "epoch": 3.9,
      "grad_norm": 0.04784834012389183,
      "learning_rate": 2.1710869701408073e-05,
      "loss": 0.8486328125,
      "step": 273
    },
    {
      "epoch": 3.914285714285714,
      "grad_norm": 0.049870528280735016,
      "learning_rate": 2.1425842920911848e-05,
      "loss": 0.91357421875,
      "step": 274
    },
    {
      "epoch": 3.928571428571429,
      "grad_norm": 0.050932083278894424,
      "learning_rate": 2.1143822392918844e-05,
      "loss": 0.88330078125,
      "step": 275
    },
    {
      "epoch": 3.942857142857143,
      "grad_norm": 0.04739019647240639,
      "learning_rate": 2.0864833369735974e-05,
      "loss": 0.88720703125,
      "step": 276
    },
    {
      "epoch": 3.9571428571428573,
      "grad_norm": 0.048358820378780365,
      "learning_rate": 2.058890083222715e-05,
      "loss": 0.8876953125,
      "step": 277
    },
    {
      "epoch": 3.9714285714285715,
      "grad_norm": 0.04822513833642006,
      "learning_rate": 2.0316049487576505e-05,
      "loss": 0.91552734375,
      "step": 278
    },
    {
      "epoch": 3.9857142857142858,
      "grad_norm": 0.05123396962881088,
      "learning_rate": 2.004630376707616e-05,
      "loss": 0.92919921875,
      "step": 279
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0550776869058609,
      "learning_rate": 1.977968782393848e-05,
      "loss": 0.90869140625,
      "step": 280
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.87109375,
      "eval_runtime": 2.2051,
      "eval_samples_per_second": 2.721,
      "eval_steps_per_second": 0.453,
      "step": 280
    },
    {
      "epoch": 4.014285714285714,
      "grad_norm": 0.05216512829065323,
      "learning_rate": 1.951622553113354e-05,
      "loss": 0.927734375,
      "step": 281
    },
    {
      "epoch": 4.0285714285714285,
      "grad_norm": 0.05291033536195755,
      "learning_rate": 1.9255940479251434e-05,
      "loss": 0.955078125,
      "step": 282
    },
    {
      "epoch": 4.042857142857143,
      "grad_norm": 0.05907987058162689,
      "learning_rate": 1.899885597438995e-05,
      "loss": 0.94873046875,
      "step": 283
    },
    {
      "epoch": 4.057142857142857,
      "grad_norm": 0.05320875719189644,
      "learning_rate": 1.87449950360678e-05,
      "loss": 0.8026275634765625,
      "step": 284
    },
    {
      "epoch": 4.071428571428571,
      "grad_norm": 0.050279874354600906,
      "learning_rate": 1.8494380395163352e-05,
      "loss": 0.904296875,
      "step": 285
    },
    {
      "epoch": 4.085714285714285,
      "grad_norm": 0.05075318366289139,
      "learning_rate": 1.8247034491879344e-05,
      "loss": 0.8955078125,
      "step": 286
    },
    {
      "epoch": 4.1,
      "grad_norm": 0.05274856835603714,
      "learning_rate": 1.800297947373355e-05,
      "loss": 0.8828125,
      "step": 287
    },
    {
      "epoch": 4.114285714285714,
      "grad_norm": 0.05150414630770683,
      "learning_rate": 1.7762237193575708e-05,
      "loss": 0.9111328125,
      "step": 288
    },
    {
      "epoch": 4.128571428571428,
      "grad_norm": 0.05325537174940109,
      "learning_rate": 1.7524829207630762e-05,
      "loss": 0.81640625,
      "step": 289
    },
    {
      "epoch": 4.142857142857143,
      "grad_norm": 0.0480109266936779,
      "learning_rate": 1.72907767735687e-05,
      "loss": 0.7505950927734375,
      "step": 290
    },
    {
      "epoch": 4.1571428571428575,
      "grad_norm": 0.05344746261835098,
      "learning_rate": 1.706010084860121e-05,
      "loss": 0.86474609375,
      "step": 291
    },
    {
      "epoch": 4.171428571428572,
      "grad_norm": 0.04495096951723099,
      "learning_rate": 1.683282208760501e-05,
      "loss": 0.765625,
      "step": 292
    },
    {
      "epoch": 4.185714285714286,
      "grad_norm": 0.055278196930885315,
      "learning_rate": 1.6608960841272554e-05,
      "loss": 0.91015625,
      "step": 293
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.051233768463134766,
      "learning_rate": 1.6388537154289706e-05,
      "loss": 0.87109375,
      "step": 294
    },
    {
      "epoch": 4.214285714285714,
      "grad_norm": 0.050882738083601,
      "learning_rate": 1.617157076354097e-05,
      "loss": 0.8564453125,
      "step": 295
    },
    {
      "epoch": 4.228571428571429,
      "grad_norm": 0.05535581707954407,
      "learning_rate": 1.5958081096342256e-05,
      "loss": 0.9716796875,
      "step": 296
    },
    {
      "epoch": 4.242857142857143,
      "grad_norm": 0.05219915881752968,
      "learning_rate": 1.5748087268701284e-05,
      "loss": 0.82763671875,
      "step": 297
    },
    {
      "epoch": 4.257142857142857,
      "grad_norm": 0.04867938905954361,
      "learning_rate": 1.554160808360598e-05,
      "loss": 0.86669921875,
      "step": 298
    },
    {
      "epoch": 4.271428571428571,
      "grad_norm": 0.052604760974645615,
      "learning_rate": 1.5338662029340803e-05,
      "loss": 0.87255859375,
      "step": 299
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 0.05216054245829582,
      "learning_rate": 1.5139267277831347e-05,
      "loss": 0.87744140625,
      "step": 300
    },
    {
      "epoch": 4.3,
      "grad_norm": 0.0504562072455883,
      "learning_rate": 1.4943441683017157e-05,
      "loss": 0.943359375,
      "step": 301
    },
    {
      "epoch": 4.314285714285714,
      "grad_norm": 0.048031508922576904,
      "learning_rate": 1.4751202779253084e-05,
      "loss": 0.841796875,
      "step": 302
    },
    {
      "epoch": 4.328571428571428,
      "grad_norm": 0.05019447207450867,
      "learning_rate": 1.4562567779739312e-05,
      "loss": 0.9013671875,
      "step": 303
    },
    {
      "epoch": 4.3428571428571425,
      "grad_norm": 0.04919208586215973,
      "learning_rate": 1.4377553574979947e-05,
      "loss": 0.86328125,
      "step": 304
    },
    {
      "epoch": 4.357142857142857,
      "grad_norm": 0.0508447140455246,
      "learning_rate": 1.4196176731270785e-05,
      "loss": 0.79052734375,
      "step": 305
    },
    {
      "epoch": 4.371428571428572,
      "grad_norm": 0.05003906786441803,
      "learning_rate": 1.4018453489215835e-05,
      "loss": 0.90087890625,
      "step": 306
    },
    {
      "epoch": 4.385714285714286,
      "grad_norm": 0.0615018755197525,
      "learning_rate": 1.3844399762273175e-05,
      "loss": 0.876953125,
      "step": 307
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.05253160372376442,
      "learning_rate": 1.3674031135330054e-05,
      "loss": 0.86376953125,
      "step": 308
    },
    {
      "epoch": 4.414285714285715,
      "grad_norm": 0.0486416257917881,
      "learning_rate": 1.3507362863307391e-05,
      "loss": 0.89453125,
      "step": 309
    },
    {
      "epoch": 4.428571428571429,
      "grad_norm": 0.0522824265062809,
      "learning_rate": 1.3344409869793851e-05,
      "loss": 0.88671875,
      "step": 310
    },
    {
      "epoch": 4.442857142857143,
      "grad_norm": 0.055019911378622055,
      "learning_rate": 1.318518674570957e-05,
      "loss": 0.84228515625,
      "step": 311
    },
    {
      "epoch": 4.457142857142857,
      "grad_norm": 0.053540315479040146,
      "learning_rate": 1.302970774799968e-05,
      "loss": 0.87109375,
      "step": 312
    },
    {
      "epoch": 4.4714285714285715,
      "grad_norm": 0.049618784338235855,
      "learning_rate": 1.2877986798357727e-05,
      "loss": 0.88037109375,
      "step": 313
    },
    {
      "epoch": 4.485714285714286,
      "grad_norm": 0.04931506887078285,
      "learning_rate": 1.2730037481979131e-05,
      "loss": 0.927734375,
      "step": 314
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.050537627190351486,
      "learning_rate": 1.2585873046344732e-05,
      "loss": 0.904296875,
      "step": 315
    },
    {
      "epoch": 4.514285714285714,
      "grad_norm": 0.05481034889817238,
      "learning_rate": 1.2445506400034607e-05,
      "loss": 0.88916015625,
      "step": 316
    },
    {
      "epoch": 4.5285714285714285,
      "grad_norm": 0.05597779527306557,
      "learning_rate": 1.2308950111572266e-05,
      "loss": 0.87841796875,
      "step": 317
    },
    {
      "epoch": 4.542857142857143,
      "grad_norm": 0.05157225951552391,
      "learning_rate": 1.2176216408299179e-05,
      "loss": 0.86083984375,
      "step": 318
    },
    {
      "epoch": 4.557142857142857,
      "grad_norm": 0.04958087578415871,
      "learning_rate": 1.2047317175280021e-05,
      "loss": 0.8701171875,
      "step": 319
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 0.053986869752407074,
      "learning_rate": 1.1922263954238409e-05,
      "loss": 0.85400390625,
      "step": 320
    },
    {
      "epoch": 4.585714285714285,
      "grad_norm": 0.0558587945997715,
      "learning_rate": 1.1801067942523477e-05,
      "loss": 0.9287109375,
      "step": 321
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.05723806843161583,
      "learning_rate": 1.1683739992107266e-05,
      "loss": 0.89111328125,
      "step": 322
    },
    {
      "epoch": 4.614285714285714,
      "grad_norm": 0.04987065866589546,
      "learning_rate": 1.1570290608613003e-05,
      "loss": 0.90625,
      "step": 323
    },
    {
      "epoch": 4.628571428571428,
      "grad_norm": 0.051388390362262726,
      "learning_rate": 1.1460729950374444e-05,
      "loss": 0.806640625,
      "step": 324
    },
    {
      "epoch": 4.642857142857143,
      "grad_norm": 0.050233837217092514,
      "learning_rate": 1.1355067827526275e-05,
      "loss": 0.88916015625,
      "step": 325
    },
    {
      "epoch": 4.6571428571428575,
      "grad_norm": 0.049414992332458496,
      "learning_rate": 1.1253313701125727e-05,
      "loss": 0.9228515625,
      "step": 326
    },
    {
      "epoch": 4.671428571428572,
      "grad_norm": 0.04873225465416908,
      "learning_rate": 1.1155476682305401e-05,
      "loss": 0.84423828125,
      "step": 327
    },
    {
      "epoch": 4.685714285714286,
      "grad_norm": 0.04912515729665756,
      "learning_rate": 1.1061565531457457e-05,
      "loss": 0.88232421875,
      "step": 328
    },
    {
      "epoch": 4.7,
      "grad_norm": 0.049595706164836884,
      "learning_rate": 1.0971588657449234e-05,
      "loss": 0.89306640625,
      "step": 329
    },
    {
      "epoch": 4.714285714285714,
      "grad_norm": 0.04815579950809479,
      "learning_rate": 1.0885554116870247e-05,
      "loss": 0.830078125,
      "step": 330
    },
    {
      "epoch": 4.728571428571429,
      "grad_norm": 0.04959326609969139,
      "learning_rate": 1.0803469613310885e-05,
      "loss": 0.87158203125,
      "step": 331
    },
    {
      "epoch": 4.742857142857143,
      "grad_norm": 0.05295655131340027,
      "learning_rate": 1.0725342496672538e-05,
      "loss": 0.900390625,
      "step": 332
    },
    {
      "epoch": 4.757142857142857,
      "grad_norm": 0.04444817081093788,
      "learning_rate": 1.0651179762509537e-05,
      "loss": 0.7275390625,
      "step": 333
    },
    {
      "epoch": 4.771428571428571,
      "grad_norm": 0.04879536107182503,
      "learning_rate": 1.0580988051402763e-05,
      "loss": 0.68359375,
      "step": 334
    },
    {
      "epoch": 4.785714285714286,
      "grad_norm": 0.05020657181739807,
      "learning_rate": 1.0514773648365018e-05,
      "loss": 0.908203125,
      "step": 335
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.050407882779836655,
      "learning_rate": 1.0452542482278278e-05,
      "loss": 0.88623046875,
      "step": 336
    },
    {
      "epoch": 4.814285714285714,
      "grad_norm": 0.04872056096792221,
      "learning_rate": 1.039430012536282e-05,
      "loss": 0.88916015625,
      "step": 337
    },
    {
      "epoch": 4.828571428571428,
      "grad_norm": 0.05090424790978432,
      "learning_rate": 1.0340051792678276e-05,
      "loss": 0.87890625,
      "step": 338
    },
    {
      "epoch": 4.8428571428571425,
      "grad_norm": 0.05038944259285927,
      "learning_rate": 1.0289802341656678e-05,
      "loss": 0.92138671875,
      "step": 339
    },
    {
      "epoch": 4.857142857142857,
      "grad_norm": 0.05104154720902443,
      "learning_rate": 1.0243556271667513e-05,
      "loss": 0.94140625,
      "step": 340
    },
    {
      "epoch": 4.871428571428572,
      "grad_norm": 0.05096552520990372,
      "learning_rate": 1.0201317723614851e-05,
      "loss": 0.8505859375,
      "step": 341
    },
    {
      "epoch": 4.885714285714286,
      "grad_norm": 0.051582347601652145,
      "learning_rate": 1.0163090479566553e-05,
      "loss": 0.8916015625,
      "step": 342
    },
    {
      "epoch": 4.9,
      "grad_norm": 0.05110916122794151,
      "learning_rate": 1.012887796241566e-05,
      "loss": 0.84033203125,
      "step": 343
    },
    {
      "epoch": 4.914285714285715,
      "grad_norm": 0.051592547446489334,
      "learning_rate": 1.0098683235573854e-05,
      "loss": 0.90380859375,
      "step": 344
    },
    {
      "epoch": 4.928571428571429,
      "grad_norm": 0.052361734211444855,
      "learning_rate": 1.0072509002697195e-05,
      "loss": 0.8759765625,
      "step": 345
    },
    {
      "epoch": 4.942857142857143,
      "grad_norm": 0.04869278147816658,
      "learning_rate": 1.0050357607444017e-05,
      "loss": 0.87939453125,
      "step": 346
    },
    {
      "epoch": 4.957142857142857,
      "grad_norm": 0.04847113788127899,
      "learning_rate": 1.0032231033265086e-05,
      "loss": 0.8798828125,
      "step": 347
    },
    {
      "epoch": 4.9714285714285715,
      "grad_norm": 0.049888331443071365,
      "learning_rate": 1.0018130903225987e-05,
      "loss": 0.90673828125,
      "step": 348
    },
    {
      "epoch": 4.985714285714286,
      "grad_norm": 0.05218585208058357,
      "learning_rate": 1.0008058479861802e-05,
      "loss": 0.923828125,
      "step": 349
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.05943594127893448,
      "learning_rate": 1.0002014665064068e-05,
      "loss": 0.89599609375,
      "step": 350
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.869140625,
      "eval_runtime": 2.2185,
      "eval_samples_per_second": 2.705,
      "eval_steps_per_second": 0.451,
      "step": 350
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.562900871360807e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}