{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005,
      "grad_norm": 68.2828140258789,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 3.547993850708008,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 381.42022705078125,
      "learning_rate": 7.2e-05,
      "loss": 3.2959220886230467,
      "step": 10
    },
    {
      "epoch": 0.015,
      "grad_norm": 19640.955078125,
      "learning_rate": 0.00011200000000000001,
      "loss": 3.369282531738281,
      "step": 15
    },
    {
      "epoch": 0.02,
      "grad_norm": 205.24681091308594,
      "learning_rate": 0.000152,
      "loss": 3.256881332397461,
      "step": 20
    },
    {
      "epoch": 0.025,
      "grad_norm": 259.6229248046875,
      "learning_rate": 0.000192,
      "loss": 3.3879322052001952,
      "step": 25
    },
    {
      "epoch": 0.03,
      "grad_norm": 2096.502685546875,
      "learning_rate": 0.0001999916943334945,
      "loss": 3.4791305541992186,
      "step": 30
    },
    {
      "epoch": 0.035,
      "grad_norm": 29.51216697692871,
      "learning_rate": 0.0001999579549278937,
      "loss": 3.5544124603271485,
      "step": 35
    },
    {
      "epoch": 0.04,
      "grad_norm": 2868.5859375,
      "learning_rate": 0.00019989827142936862,
      "loss": 3.4086448669433596,
      "step": 40
    },
    {
      "epoch": 0.045,
      "grad_norm": 116.66321563720703,
      "learning_rate": 0.00019981265932877488,
      "loss": 3.26219482421875,
      "step": 45
    },
    {
      "epoch": 0.05,
      "grad_norm": 1199.3328857421875,
      "learning_rate": 0.00019970114084673796,
      "loss": 3.556040954589844,
      "step": 50
    },
    {
      "epoch": 0.05,
      "eval_loss": 3.7243571281433105,
      "eval_runtime": 200.7945,
      "eval_samples_per_second": 1.484,
      "eval_steps_per_second": 0.299,
      "step": 50
    },
    {
      "epoch": 0.055,
      "grad_norm": 1653.0960693359375,
      "learning_rate": 0.0001995637449278864,
      "loss": 3.860651397705078,
      "step": 55
    },
    {
      "epoch": 0.06,
      "grad_norm": 411.4178466796875,
      "learning_rate": 0.00019940050723333866,
      "loss": 3.699799728393555,
      "step": 60
    },
    {
      "epoch": 0.065,
      "grad_norm": 2424.376708984375,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.703348159790039,
      "step": 65
    },
    {
      "epoch": 0.07,
      "grad_norm": 23206.84375,
      "learning_rate": 0.0001989966826868044,
      "loss": 3.6570384979248045,
      "step": 70
    },
    {
      "epoch": 0.075,
      "grad_norm": 395.9013977050781,
      "learning_rate": 0.00019875620064750202,
      "loss": 3.622447204589844,
      "step": 75
    },
    {
      "epoch": 0.08,
      "grad_norm": 228293.453125,
      "learning_rate": 0.00019849008643066772,
      "loss": 3.773283767700195,
      "step": 80
    },
    {
      "epoch": 0.085,
      "grad_norm": 52893.1875,
      "learning_rate": 0.00019819840910626174,
      "loss": 3.650778961181641,
      "step": 85
    },
    {
      "epoch": 0.09,
      "grad_norm": 12679.291015625,
      "learning_rate": 0.0001978812443791503,
      "loss": 3.9305484771728514,
      "step": 90
    },
    {
      "epoch": 0.095,
      "grad_norm": 439037.4375,
      "learning_rate": 0.0001975386745694565,
      "loss": 3.8479537963867188,
      "step": 95
    },
    {
      "epoch": 0.1,
      "grad_norm": 878.3585815429688,
      "learning_rate": 0.0001971707885911941,
      "loss": 3.90667724609375,
      "step": 100
    },
    {
      "epoch": 0.1,
      "eval_loss": 4.1160054206848145,
      "eval_runtime": 201.0129,
      "eval_samples_per_second": 1.482,
      "eval_steps_per_second": 0.298,
      "step": 100
    },
    {
      "epoch": 0.105,
      "grad_norm": 2385.37744140625,
      "learning_rate": 0.00019677768192918971,
      "loss": 3.805155944824219,
      "step": 105
    },
    {
      "epoch": 0.11,
      "grad_norm": 10.20463752746582,
      "learning_rate": 0.00019635945661430006,
      "loss": 3.822935104370117,
      "step": 110
    },
    {
      "epoch": 0.115,
      "grad_norm": 7.702394962310791,
      "learning_rate": 0.0001959162211969295,
      "loss": 3.702631378173828,
      "step": 115
    },
    {
      "epoch": 0.12,
      "grad_norm": 2.8037490844726562,
      "learning_rate": 0.00019544809071885604,
      "loss": 3.6845611572265624,
      "step": 120
    },
    {
      "epoch": 0.125,
      "grad_norm": 3.6743063926696777,
      "learning_rate": 0.00019495518668337201,
      "loss": 3.644290542602539,
      "step": 125
    },
    {
      "epoch": 0.13,
      "grad_norm": 5.9780964851379395,
      "learning_rate": 0.00019443763702374812,
      "loss": 3.5586227416992187,
      "step": 130
    },
    {
      "epoch": 0.135,
      "grad_norm": 2.230492353439331,
      "learning_rate": 0.00019389557607002805,
      "loss": 3.4619365692138673,
      "step": 135
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.7121639251708984,
      "learning_rate": 0.00019332914451416347,
      "loss": 3.531117248535156,
      "step": 140
    },
    {
      "epoch": 0.145,
      "grad_norm": 4.843437194824219,
      "learning_rate": 0.0001927384893734971,
      "loss": 3.5250553131103515,
      "step": 145
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.5022116899490356,
      "learning_rate": 0.00019212376395260448,
      "loss": 3.252106475830078,
      "step": 150
    },
    {
      "epoch": 0.15,
      "eval_loss": 3.604867935180664,
      "eval_runtime": 200.7401,
      "eval_samples_per_second": 1.485,
      "eval_steps_per_second": 0.299,
      "step": 150
    },
    {
      "epoch": 0.155,
      "grad_norm": 2.400775909423828,
      "learning_rate": 0.00019148512780350384,
      "loss": 3.291422653198242,
      "step": 155
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.1534276008605957,
      "learning_rate": 0.00019082274668424422,
      "loss": 3.4382129669189454,
      "step": 160
    },
    {
      "epoch": 0.165,
      "grad_norm": 5.130342960357666,
      "learning_rate": 0.00019013679251588303,
      "loss": 3.4447181701660154,
      "step": 165
    },
    {
      "epoch": 0.17,
      "grad_norm": 125.57601928710938,
      "learning_rate": 0.00018942744333786397,
      "loss": 3.4935020446777343,
      "step": 170
    },
    {
      "epoch": 0.175,
      "grad_norm": 7.2148356437683105,
      "learning_rate": 0.00018869488326180679,
      "loss": 3.4430862426757813,
      "step": 175
    },
    {
      "epoch": 0.18,
      "grad_norm": 47.17856979370117,
      "learning_rate": 0.0001879393024237212,
      "loss": 3.4849868774414063,
      "step": 180
    },
    {
      "epoch": 0.185,
      "grad_norm": 3.984619140625,
      "learning_rate": 0.00018716089693465696,
      "loss": 3.467825698852539,
      "step": 185
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.7979289293289185,
      "learning_rate": 0.00018635986882980325,
      "loss": 3.2273773193359374,
      "step": 190
    },
    {
      "epoch": 0.195,
      "grad_norm": 49.847412109375,
      "learning_rate": 0.00018553642601605068,
      "loss": 3.51593017578125,
      "step": 195
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.552674412727356,
      "learning_rate": 0.0001846907822180286,
      "loss": 3.5006553649902346,
      "step": 200
    },
    {
      "epoch": 0.2,
      "eval_loss": 3.619206190109253,
      "eval_runtime": 201.0123,
      "eval_samples_per_second": 1.482,
      "eval_steps_per_second": 0.298,
      "step": 200
    },
    {
      "epoch": 0.205,
      "grad_norm": 5811.900390625,
      "learning_rate": 0.00018382315692263323,
      "loss": 3.4652740478515627,
      "step": 205
    },
    {
      "epoch": 0.21,
      "grad_norm": 1784.0272216796875,
      "learning_rate": 0.00018293377532205968,
      "loss": 3.136703681945801,
      "step": 210
    },
    {
      "epoch": 0.215,
      "grad_norm": 8352.1416015625,
      "learning_rate": 0.0001820228682553533,
      "loss": 3.3410572052001952,
      "step": 215
    },
    {
      "epoch": 0.22,
      "grad_norm": 9626.669921875,
      "learning_rate": 0.00018109067214849538,
      "loss": 3.3538772583007814,
      "step": 220
    },
    {
      "epoch": 0.225,
      "grad_norm": 5929.7529296875,
      "learning_rate": 0.00018013742895303883,
      "loss": 3.598949432373047,
      "step": 225
    },
    {
      "epoch": 0.23,
      "grad_norm": 280.86492919921875,
      "learning_rate": 0.0001791633860833096,
      "loss": 3.4480300903320313,
      "step": 230
    },
    {
      "epoch": 0.235,
      "grad_norm": 19.305431365966797,
      "learning_rate": 0.00017816879635219028,
      "loss": 3.521527099609375,
      "step": 235
    },
    {
      "epoch": 0.24,
      "grad_norm": 11.262675285339355,
      "learning_rate": 0.00017715391790550252,
      "loss": 3.543391799926758,
      "step": 240
    },
    {
      "epoch": 0.245,
      "grad_norm": 107.26178741455078,
      "learning_rate": 0.00017611901415500535,
      "loss": 3.380891799926758,
      "step": 245
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.6105318069458008,
      "learning_rate": 0.00017506435371002633,
      "loss": 3.2983978271484373,
      "step": 250
    },
    {
      "epoch": 0.25,
      "eval_loss": 3.6096248626708984,
      "eval_runtime": 200.7485,
      "eval_samples_per_second": 1.484,
      "eval_steps_per_second": 0.299,
      "step": 250
    },
    {
      "epoch": 0.255,
      "grad_norm": 1.168889045715332,
      "learning_rate": 0.00017399021030774442,
      "loss": 3.5202346801757813,
      "step": 255
    },
    {
      "epoch": 0.26,
      "grad_norm": 4.2245283126831055,
      "learning_rate": 0.00017289686274214118,
      "loss": 3.2942405700683595,
      "step": 260
    },
    {
      "epoch": 0.265,
      "grad_norm": 0.3621503710746765,
      "learning_rate": 0.00017178459479163976,
      "loss": 3.4601863861083983,
      "step": 265
    },
    {
      "epoch": 0.27,
      "grad_norm": 35.780120849609375,
      "learning_rate": 0.00017065369514545053,
      "loss": 3.2967288970947264,
      "step": 270
    },
    {
      "epoch": 0.275,
      "grad_norm": 474.76861572265625,
      "learning_rate": 0.00016950445732864127,
      "loss": 3.4325428009033203,
      "step": 275
    },
    {
      "epoch": 0.28,
      "grad_norm": 2.8445627689361572,
      "learning_rate": 0.00016833717962595326,
      "loss": 3.3004375457763673,
      "step": 280
    },
    {
      "epoch": 0.285,
      "grad_norm": 19.516523361206055,
      "learning_rate": 0.00016715216500438093,
      "loss": 3.612904739379883,
      "step": 285
    },
    {
      "epoch": 0.29,
      "grad_norm": 25.849435806274414,
      "learning_rate": 0.00016594972103453726,
      "loss": 3.567874526977539,
      "step": 290
    },
    {
      "epoch": 0.295,
      "grad_norm": 58.06301498413086,
      "learning_rate": 0.00016473015981082338,
      "loss": 3.525835418701172,
      "step": 295
    },
    {
      "epoch": 0.3,
      "grad_norm": 191.27548217773438,
      "learning_rate": 0.00016349379787042477,
      "loss": 3.3833484649658203,
      "step": 300
    },
    {
      "epoch": 0.3,
      "eval_loss": 3.7416040897369385,
      "eval_runtime": 200.7531,
      "eval_samples_per_second": 1.484,
      "eval_steps_per_second": 0.299,
      "step": 300
    },
    {
      "epoch": 0.305,
      "grad_norm": 56.349708557128906,
      "learning_rate": 0.00016224095611115384,
      "loss": 3.6572975158691405,
      "step": 305
    },
    {
      "epoch": 0.31,
      "grad_norm": 1745.9088134765625,
      "learning_rate": 0.00016097195970816094,
      "loss": 3.601942443847656,
      "step": 310
    },
    {
      "epoch": 0.315,
      "grad_norm": 1165.1402587890625,
      "learning_rate": 0.0001596871380295351,
      "loss": 3.6535247802734374,
      "step": 315
    },
    {
      "epoch": 0.32,
      "grad_norm": 46.510684967041016,
      "learning_rate": 0.00015838682455081657,
      "loss": 3.5322292327880858,
      "step": 320
    },
    {
      "epoch": 0.325,
      "grad_norm": 147.2434539794922,
      "learning_rate": 0.0001570713567684432,
      "loss": 3.4837066650390627,
      "step": 325
    },
    {
      "epoch": 0.33,
      "grad_norm": 7.8114013671875,
      "learning_rate": 0.00015574107611215319,
      "loss": 3.5842933654785156,
      "step": 330
    },
    {
      "epoch": 0.335,
      "grad_norm": 40.32650375366211,
      "learning_rate": 0.00015439632785636706,
      "loss": 3.451204299926758,
      "step": 335
    },
    {
      "epoch": 0.34,
      "grad_norm": 54.91672134399414,
      "learning_rate": 0.00015303746103057162,
      "loss": 3.6410243988037108,
      "step": 340
    },
    {
      "epoch": 0.345,
      "grad_norm": 143.5968017578125,
      "learning_rate": 0.00015166482832872923,
      "loss": 3.567627716064453,
      "step": 345
    },
    {
      "epoch": 0.35,
      "grad_norm": 66.56953430175781,
      "learning_rate": 0.00015027878601773633,
      "loss": 3.7443378448486326,
      "step": 350
    },
    {
      "epoch": 0.35,
      "eval_loss": 3.8730692863464355,
      "eval_runtime": 200.7554,
      "eval_samples_per_second": 1.484,
      "eval_steps_per_second": 0.299,
      "step": 350
    },
    {
      "epoch": 0.355,
      "grad_norm": 109.56166076660156,
      "learning_rate": 0.00014887969384495402,
      "loss": 3.7462512969970705,
      "step": 355
    },
    {
      "epoch": 0.36,
      "grad_norm": 403.760986328125,
      "learning_rate": 0.00014746791494483583,
      "loss": 3.4167720794677736,
      "step": 360
    },
    {
      "epoch": 0.365,
      "grad_norm": 78.5467300415039,
      "learning_rate": 0.00014604381574467615,
      "loss": 3.653825378417969,
      "step": 365
    },
    {
      "epoch": 0.37,
      "grad_norm": 7.657294273376465,
      "learning_rate": 0.00014460776586950393,
      "loss": 3.5837642669677736,
      "step": 370
    },
    {
      "epoch": 0.375,
      "grad_norm": 232.22654724121094,
      "learning_rate": 0.00014316013804614643,
      "loss": 3.5867897033691407,
      "step": 375
    },
    {
      "epoch": 0.38,
      "grad_norm": 34.94912338256836,
      "learning_rate": 0.00014170130800648814,
      "loss": 3.5861190795898437,
      "step": 380
    },
    {
      "epoch": 0.385,
      "grad_norm": 91.70198059082031,
      "learning_rate": 0.0001402316543899493,
      "loss": 3.66529541015625,
      "step": 385
    },
    {
      "epoch": 0.39,
      "grad_norm": 25.11287498474121,
      "learning_rate": 0.0001387515586452103,
      "loss": 3.6498741149902343,
      "step": 390
    },
    {
      "epoch": 0.395,
      "grad_norm": 93.66793060302734,
      "learning_rate": 0.0001372614049312064,
      "loss": 3.352254867553711,
      "step": 395
    },
    {
      "epoch": 0.4,
      "grad_norm": 4.588032245635986,
      "learning_rate": 0.00013576158001741932,
      "loss": 3.517344665527344,
      "step": 400
    },
    {
      "epoch": 0.4,
      "eval_loss": 3.753708839416504,
      "eval_runtime": 200.6183,
      "eval_samples_per_second": 1.485,
      "eval_steps_per_second": 0.299,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1904846517043200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}