{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.246376811594203,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07246376811594203,
      "grad_norm": 1.0494204759597778,
      "learning_rate": 0.00019800000000000002,
      "loss": 4.2586,
      "step": 10
    },
    {
      "epoch": 0.14492753623188406,
      "grad_norm": 2.3070778846740723,
      "learning_rate": 0.000196,
      "loss": 3.4035,
      "step": 20
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 3.2612266540527344,
      "learning_rate": 0.000194,
      "loss": 2.6736,
      "step": 30
    },
    {
      "epoch": 0.2898550724637681,
      "grad_norm": 2.4876601696014404,
      "learning_rate": 0.0001922,
      "loss": 2.1857,
      "step": 40
    },
    {
      "epoch": 0.36231884057971014,
      "grad_norm": 2.367360830307007,
      "learning_rate": 0.0001902,
      "loss": 2.0017,
      "step": 50
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 1.9053794145584106,
      "learning_rate": 0.0001882,
      "loss": 1.7045,
      "step": 60
    },
    {
      "epoch": 0.5072463768115942,
      "grad_norm": 2.813183069229126,
      "learning_rate": 0.00018620000000000003,
      "loss": 1.777,
      "step": 70
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 1.703532099723816,
      "learning_rate": 0.0001842,
      "loss": 1.8335,
      "step": 80
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 2.5876986980438232,
      "learning_rate": 0.0001822,
      "loss": 1.932,
      "step": 90
    },
    {
      "epoch": 0.7246376811594203,
      "grad_norm": 2.3653035163879395,
      "learning_rate": 0.00018020000000000002,
      "loss": 1.5939,
      "step": 100
    },
    {
      "epoch": 0.7971014492753623,
      "grad_norm": 1.8726710081100464,
      "learning_rate": 0.00017820000000000002,
      "loss": 1.816,
      "step": 110
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 1.8513643741607666,
      "learning_rate": 0.0001762,
      "loss": 1.4941,
      "step": 120
    },
    {
      "epoch": 0.9420289855072463,
      "grad_norm": 2.2692129611968994,
      "learning_rate": 0.0001742,
      "loss": 1.5971,
      "step": 130
    },
    {
      "epoch": 1.0144927536231885,
      "grad_norm": 2.6734588146209717,
      "learning_rate": 0.0001722,
      "loss": 1.6418,
      "step": 140
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 3.8182976245880127,
      "learning_rate": 0.00017020000000000002,
      "loss": 1.4724,
      "step": 150
    },
    {
      "epoch": 1.1594202898550725,
      "grad_norm": 2.3226006031036377,
      "learning_rate": 0.0001682,
      "loss": 1.3599,
      "step": 160
    },
    {
      "epoch": 1.2318840579710144,
      "grad_norm": 6.185395240783691,
      "learning_rate": 0.0001662,
      "loss": 1.3629,
      "step": 170
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 2.1148927211761475,
      "learning_rate": 0.0001642,
      "loss": 1.3997,
      "step": 180
    },
    {
      "epoch": 1.3768115942028984,
      "grad_norm": 3.705061197280884,
      "learning_rate": 0.0001622,
      "loss": 1.3026,
      "step": 190
    },
    {
      "epoch": 1.4492753623188406,
      "grad_norm": 3.832019090652466,
      "learning_rate": 0.00016020000000000002,
      "loss": 1.5701,
      "step": 200
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 2.6830215454101562,
      "learning_rate": 0.00015820000000000002,
      "loss": 1.6283,
      "step": 210
    },
    {
      "epoch": 1.5942028985507246,
      "grad_norm": 4.285362243652344,
      "learning_rate": 0.0001562,
      "loss": 1.3493,
      "step": 220
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 3.6948392391204834,
      "learning_rate": 0.0001542,
      "loss": 1.3661,
      "step": 230
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 3.770359992980957,
      "learning_rate": 0.0001522,
      "loss": 1.2724,
      "step": 240
    },
    {
      "epoch": 1.8115942028985508,
      "grad_norm": 4.342422008514404,
      "learning_rate": 0.00015020000000000002,
      "loss": 1.2295,
      "step": 250
    },
    {
      "epoch": 1.8840579710144927,
      "grad_norm": 4.003652572631836,
      "learning_rate": 0.0001482,
      "loss": 1.3862,
      "step": 260
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 3.8167941570281982,
      "learning_rate": 0.0001462,
      "loss": 1.3623,
      "step": 270
    },
    {
      "epoch": 2.028985507246377,
      "grad_norm": 4.051051139831543,
      "learning_rate": 0.0001442,
      "loss": 0.9666,
      "step": 280
    },
    {
      "epoch": 2.101449275362319,
      "grad_norm": 2.2572319507598877,
      "learning_rate": 0.0001422,
      "loss": 0.9071,
      "step": 290
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 5.0580878257751465,
      "learning_rate": 0.0001402,
      "loss": 0.9925,
      "step": 300
    },
    {
      "epoch": 2.246376811594203,
      "grad_norm": 4.157490253448486,
      "learning_rate": 0.0001382,
      "loss": 1.2288,
      "step": 310
    },
    {
      "epoch": 2.318840579710145,
      "grad_norm": 4.6029510498046875,
      "learning_rate": 0.0001362,
      "loss": 0.8646,
      "step": 320
    },
    {
      "epoch": 2.391304347826087,
      "grad_norm": 6.775791645050049,
      "learning_rate": 0.0001342,
      "loss": 1.0872,
      "step": 330
    },
    {
      "epoch": 2.463768115942029,
      "grad_norm": 4.0972113609313965,
      "learning_rate": 0.00013220000000000001,
      "loss": 0.9001,
      "step": 340
    },
    {
      "epoch": 2.536231884057971,
      "grad_norm": 8.093110084533691,
      "learning_rate": 0.00013020000000000002,
      "loss": 0.9329,
      "step": 350
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 5.541107177734375,
      "learning_rate": 0.0001282,
      "loss": 1.1102,
      "step": 360
    },
    {
      "epoch": 2.681159420289855,
      "grad_norm": 4.768208980560303,
      "learning_rate": 0.0001262,
      "loss": 0.9413,
      "step": 370
    },
    {
      "epoch": 2.753623188405797,
      "grad_norm": 6.943519115447998,
      "learning_rate": 0.0001242,
      "loss": 1.1666,
      "step": 380
    },
    {
      "epoch": 2.8260869565217392,
      "grad_norm": 4.54674768447876,
      "learning_rate": 0.00012220000000000002,
      "loss": 0.9934,
      "step": 390
    },
    {
      "epoch": 2.898550724637681,
      "grad_norm": 4.663645267486572,
      "learning_rate": 0.00012020000000000001,
      "loss": 1.2474,
      "step": 400
    },
    {
      "epoch": 2.971014492753623,
      "grad_norm": 4.170300483703613,
      "learning_rate": 0.0001182,
      "loss": 1.1413,
      "step": 410
    },
    {
      "epoch": 3.0434782608695654,
      "grad_norm": 3.5200247764587402,
      "learning_rate": 0.00011619999999999999,
      "loss": 1.1336,
      "step": 420
    },
    {
      "epoch": 3.1159420289855073,
      "grad_norm": 6.17999792098999,
      "learning_rate": 0.0001142,
      "loss": 0.8005,
      "step": 430
    },
    {
      "epoch": 3.1884057971014492,
      "grad_norm": 6.850672245025635,
      "learning_rate": 0.00011220000000000002,
      "loss": 0.8476,
      "step": 440
    },
    {
      "epoch": 3.260869565217391,
      "grad_norm": 5.512606620788574,
      "learning_rate": 0.00011020000000000001,
      "loss": 0.9174,
      "step": 450
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 5.102043628692627,
      "learning_rate": 0.00010820000000000001,
      "loss": 0.7113,
      "step": 460
    },
    {
      "epoch": 3.4057971014492754,
      "grad_norm": 3.110646963119507,
      "learning_rate": 0.0001062,
      "loss": 0.752,
      "step": 470
    },
    {
      "epoch": 3.4782608695652173,
      "grad_norm": 4.310419082641602,
      "learning_rate": 0.00010420000000000001,
      "loss": 0.8261,
      "step": 480
    },
    {
      "epoch": 3.550724637681159,
      "grad_norm": 6.366318225860596,
      "learning_rate": 0.0001022,
      "loss": 0.793,
      "step": 490
    },
    {
      "epoch": 3.6231884057971016,
      "grad_norm": 7.170370578765869,
      "learning_rate": 0.00010020000000000001,
      "loss": 1.0607,
      "step": 500
    },
    {
      "epoch": 3.6956521739130435,
      "grad_norm": 5.464928150177002,
      "learning_rate": 9.82e-05,
      "loss": 0.5825,
      "step": 510
    },
    {
      "epoch": 3.7681159420289854,
      "grad_norm": 5.7281951904296875,
      "learning_rate": 9.620000000000001e-05,
      "loss": 0.786,
      "step": 520
    },
    {
      "epoch": 3.8405797101449277,
      "grad_norm": 5.510980129241943,
      "learning_rate": 9.42e-05,
      "loss": 0.6948,
      "step": 530
    },
    {
      "epoch": 3.9130434782608696,
      "grad_norm": 1.936035394668579,
      "learning_rate": 9.22e-05,
      "loss": 0.6707,
      "step": 540
    },
    {
      "epoch": 3.9855072463768115,
      "grad_norm": 3.7161924839019775,
      "learning_rate": 9.020000000000001e-05,
      "loss": 0.8582,
      "step": 550
    },
    {
      "epoch": 4.057971014492754,
      "grad_norm": 4.582805156707764,
      "learning_rate": 8.82e-05,
      "loss": 0.5581,
      "step": 560
    },
    {
      "epoch": 4.130434782608695,
      "grad_norm": 6.6975250244140625,
      "learning_rate": 8.620000000000001e-05,
      "loss": 0.6891,
      "step": 570
    },
    {
      "epoch": 4.202898550724638,
      "grad_norm": 4.396116256713867,
      "learning_rate": 8.42e-05,
      "loss": 0.6131,
      "step": 580
    },
    {
      "epoch": 4.27536231884058,
      "grad_norm": 8.45380687713623,
      "learning_rate": 8.22e-05,
      "loss": 0.49,
      "step": 590
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 5.600996017456055,
      "learning_rate": 8.020000000000001e-05,
      "loss": 0.6265,
      "step": 600
    },
    {
      "epoch": 4.420289855072464,
      "grad_norm": 9.154874801635742,
      "learning_rate": 7.82e-05,
      "loss": 0.6905,
      "step": 610
    },
    {
      "epoch": 4.492753623188406,
      "grad_norm": 6.6350202560424805,
      "learning_rate": 7.620000000000001e-05,
      "loss": 0.5512,
      "step": 620
    },
    {
      "epoch": 4.565217391304348,
      "grad_norm": 5.929750442504883,
      "learning_rate": 7.42e-05,
      "loss": 0.6337,
      "step": 630
    },
    {
      "epoch": 4.63768115942029,
      "grad_norm": 4.856590270996094,
      "learning_rate": 7.22e-05,
      "loss": 0.5576,
      "step": 640
    },
    {
      "epoch": 4.710144927536232,
      "grad_norm": 6.00139856338501,
      "learning_rate": 7.02e-05,
      "loss": 0.839,
      "step": 650
    },
    {
      "epoch": 4.782608695652174,
      "grad_norm": 7.68943452835083,
      "learning_rate": 6.82e-05,
      "loss": 0.6007,
      "step": 660
    },
    {
      "epoch": 4.855072463768116,
      "grad_norm": 3.7272567749023438,
      "learning_rate": 6.620000000000001e-05,
      "loss": 0.6239,
      "step": 670
    },
    {
      "epoch": 4.927536231884058,
      "grad_norm": 4.914477825164795,
      "learning_rate": 6.42e-05,
      "loss": 0.6188,
      "step": 680
    },
    {
      "epoch": 5.0,
      "grad_norm": 9.873302459716797,
      "learning_rate": 6.220000000000001e-05,
      "loss": 0.5975,
      "step": 690
    },
    {
      "epoch": 5.072463768115942,
      "grad_norm": 8.113228797912598,
      "learning_rate": 6.02e-05,
      "loss": 0.4262,
      "step": 700
    },
    {
      "epoch": 5.144927536231884,
      "grad_norm": 2.4135184288024902,
      "learning_rate": 5.82e-05,
      "loss": 0.3966,
      "step": 710
    },
    {
      "epoch": 5.217391304347826,
      "grad_norm": 3.7978782653808594,
      "learning_rate": 5.620000000000001e-05,
      "loss": 0.5201,
      "step": 720
    },
    {
      "epoch": 5.2898550724637685,
      "grad_norm": 4.620602607727051,
      "learning_rate": 5.420000000000001e-05,
      "loss": 0.5306,
      "step": 730
    },
    {
      "epoch": 5.36231884057971,
      "grad_norm": 7.97003173828125,
      "learning_rate": 5.22e-05,
      "loss": 0.4757,
      "step": 740
    },
    {
      "epoch": 5.434782608695652,
      "grad_norm": 3.4005777835845947,
      "learning_rate": 5.02e-05,
      "loss": 0.3991,
      "step": 750
    },
    {
      "epoch": 5.507246376811594,
      "grad_norm": 9.03802490234375,
      "learning_rate": 4.82e-05,
      "loss": 0.4278,
      "step": 760
    },
    {
      "epoch": 5.579710144927536,
      "grad_norm": 4.8757123947143555,
      "learning_rate": 4.6200000000000005e-05,
      "loss": 0.4691,
      "step": 770
    },
    {
      "epoch": 5.6521739130434785,
      "grad_norm": 7.352402210235596,
      "learning_rate": 4.4200000000000004e-05,
      "loss": 0.4877,
      "step": 780
    },
    {
      "epoch": 5.72463768115942,
      "grad_norm": 4.516758918762207,
      "learning_rate": 4.22e-05,
      "loss": 0.506,
      "step": 790
    },
    {
      "epoch": 5.797101449275362,
      "grad_norm": 6.949781894683838,
      "learning_rate": 4.02e-05,
      "loss": 0.688,
      "step": 800
    },
    {
      "epoch": 5.869565217391305,
      "grad_norm": 8.907429695129395,
      "learning_rate": 3.82e-05,
      "loss": 0.5848,
      "step": 810
    },
    {
      "epoch": 5.942028985507246,
      "grad_norm": 8.472686767578125,
      "learning_rate": 3.62e-05,
      "loss": 0.4619,
      "step": 820
    },
    {
      "epoch": 6.0144927536231885,
      "grad_norm": 3.424809217453003,
      "learning_rate": 3.4200000000000005e-05,
      "loss": 0.4204,
      "step": 830
    },
    {
      "epoch": 6.086956521739131,
      "grad_norm": 6.555367946624756,
      "learning_rate": 3.2200000000000003e-05,
      "loss": 0.3869,
      "step": 840
    },
    {
      "epoch": 6.159420289855072,
      "grad_norm": 7.202473163604736,
      "learning_rate": 3.02e-05,
      "loss": 0.4058,
      "step": 850
    },
    {
      "epoch": 6.231884057971015,
      "grad_norm": 9.05301570892334,
      "learning_rate": 2.8199999999999998e-05,
      "loss": 0.3875,
      "step": 860
    },
    {
      "epoch": 6.304347826086957,
      "grad_norm": 8.509578704833984,
      "learning_rate": 2.6200000000000003e-05,
      "loss": 0.4036,
      "step": 870
    },
    {
      "epoch": 6.3768115942028984,
      "grad_norm": 4.049665451049805,
      "learning_rate": 2.4200000000000002e-05,
      "loss": 0.4272,
      "step": 880
    },
    {
      "epoch": 6.449275362318841,
      "grad_norm": 3.557060718536377,
      "learning_rate": 2.22e-05,
      "loss": 0.3636,
      "step": 890
    },
    {
      "epoch": 6.521739130434782,
      "grad_norm": 8.958136558532715,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 0.4378,
      "step": 900
    },
    {
      "epoch": 6.594202898550725,
      "grad_norm": 2.7690534591674805,
      "learning_rate": 1.8200000000000002e-05,
      "loss": 0.3435,
      "step": 910
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 5.819123268127441,
      "learning_rate": 1.62e-05,
      "loss": 0.4098,
      "step": 920
    },
    {
      "epoch": 6.739130434782608,
      "grad_norm": 6.891845226287842,
      "learning_rate": 1.42e-05,
      "loss": 0.3363,
      "step": 930
    },
    {
      "epoch": 6.811594202898551,
      "grad_norm": 7.646413326263428,
      "learning_rate": 1.22e-05,
      "loss": 0.4361,
      "step": 940
    },
    {
      "epoch": 6.884057971014493,
      "grad_norm": 7.139030933380127,
      "learning_rate": 1.02e-05,
      "loss": 0.3213,
      "step": 950
    },
    {
      "epoch": 6.956521739130435,
      "grad_norm": 8.147725105285645,
      "learning_rate": 8.200000000000001e-06,
      "loss": 0.4433,
      "step": 960
    },
    {
      "epoch": 7.028985507246377,
      "grad_norm": 9.252585411071777,
      "learning_rate": 6.2e-06,
      "loss": 0.4423,
      "step": 970
    },
    {
      "epoch": 7.101449275362318,
      "grad_norm": 3.595215320587158,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 0.389,
      "step": 980
    },
    {
      "epoch": 7.173913043478261,
      "grad_norm": 2.2256908416748047,
      "learning_rate": 2.2e-06,
      "loss": 0.3653,
      "step": 990
    },
    {
      "epoch": 7.246376811594203,
      "grad_norm": 7.12455415725708,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 0.3505,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 787356038406144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}