{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 740,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 10.65625,
      "learning_rate": 0.00019990989662046818,
      "loss": 1.0534,
      "step": 10
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 10.4765625,
      "learning_rate": 0.00019963974885425266,
      "loss": 0.9925,
      "step": 20
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 12.546875,
      "learning_rate": 0.00019919004352588767,
      "loss": 0.9846,
      "step": 30
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 10.9296875,
      "learning_rate": 0.00019856159103477086,
      "loss": 0.9861,
      "step": 40
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 12.125,
      "learning_rate": 0.00019775552389476864,
      "loss": 0.9614,
      "step": 50
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 11.1640625,
      "learning_rate": 0.0001967732946933499,
      "loss": 0.9254,
      "step": 60
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 11.2109375,
      "learning_rate": 0.00019561667347392508,
      "loss": 0.9275,
      "step": 70
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 12.0703125,
      "learning_rate": 0.00019428774454610843,
      "loss": 0.9252,
      "step": 80
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 10.671875,
      "learning_rate": 0.00019278890272965096,
      "loss": 0.8997,
      "step": 90
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 10.0234375,
      "learning_rate": 0.0001911228490388136,
      "loss": 0.8997,
      "step": 100
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 9.828125,
      "learning_rate": 0.00018929258581495685,
      "loss": 0.9081,
      "step": 110
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 9.78125,
      "learning_rate": 0.00018730141131611882,
      "loss": 0.88,
      "step": 120
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 9.625,
      "learning_rate": 0.00018515291377333112,
      "loss": 0.8677,
      "step": 130
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 10.1875,
      "learning_rate": 0.00018285096492438424,
      "loss": 0.8999,
      "step": 140
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 11.6640625,
      "learning_rate": 0.00018039971303669407,
      "loss": 0.9,
      "step": 150
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 12.2109375,
      "learning_rate": 0.00017780357543184397,
      "loss": 0.912,
      "step": 160
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 14.1640625,
      "learning_rate": 0.00017506723052527242,
      "loss": 0.8953,
      "step": 170
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 15.015625,
      "learning_rate": 0.00017219560939545246,
      "loss": 0.9759,
      "step": 180
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 15.5546875,
      "learning_rate": 0.00016919388689775464,
      "loss": 1.0338,
      "step": 190
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 16.5,
      "learning_rate": 0.00016606747233900815,
      "loss": 1.0389,
      "step": 200
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 16.9375,
      "learning_rate": 0.00016282199972956425,
      "loss": 1.0149,
      "step": 210
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 14.21875,
      "learning_rate": 0.00015946331763042867,
      "loss": 0.9946,
      "step": 220
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 11.09375,
      "learning_rate": 0.00015599747861375955,
      "loss": 0.9629,
      "step": 230
    },
    {
      "epoch": 3.2432432432432434,
      "grad_norm": 13.4921875,
      "learning_rate": 0.00015243072835572318,
      "loss": 0.9677,
      "step": 240
    },
    {
      "epoch": 3.3783783783783785,
      "grad_norm": 13.3046875,
      "learning_rate": 0.00014876949438136347,
      "loss": 0.9327,
      "step": 250
    },
    {
      "epoch": 3.5135135135135136,
      "grad_norm": 13.03125,
      "learning_rate": 0.00014502037448176734,
      "loss": 0.9566,
      "step": 260
    },
    {
      "epoch": 3.6486486486486487,
      "grad_norm": 11.9921875,
      "learning_rate": 0.0001411901248243993,
      "loss": 0.913,
      "step": 270
    },
    {
      "epoch": 3.7837837837837838,
      "grad_norm": 10.953125,
      "learning_rate": 0.00013728564777803088,
      "loss": 0.9266,
      "step": 280
    },
    {
      "epoch": 3.918918918918919,
      "grad_norm": 12.15625,
      "learning_rate": 0.00013331397947420576,
      "loss": 0.8859,
      "step": 290
    },
    {
      "epoch": 4.054054054054054,
      "grad_norm": 13.1171875,
      "learning_rate": 0.00012928227712765504,
      "loss": 0.8896,
      "step": 300
    },
    {
      "epoch": 4.1891891891891895,
      "grad_norm": 11.8203125,
      "learning_rate": 0.00012519780613851254,
      "loss": 0.8317,
      "step": 310
    },
    {
      "epoch": 4.324324324324325,
      "grad_norm": 12.53125,
      "learning_rate": 0.00012106792699957263,
      "loss": 0.8712,
      "step": 320
    },
    {
      "epoch": 4.45945945945946,
      "grad_norm": 12.671875,
      "learning_rate": 0.00011690008203218493,
      "loss": 0.8436,
      "step": 330
    },
    {
      "epoch": 4.594594594594595,
      "grad_norm": 15.8515625,
      "learning_rate": 0.00011270178197468789,
      "loss": 0.8538,
      "step": 340
    },
    {
      "epoch": 4.72972972972973,
      "grad_norm": 12.46875,
      "learning_rate": 0.00010848059244755093,
      "loss": 0.8787,
      "step": 350
    },
    {
      "epoch": 4.864864864864865,
      "grad_norm": 11.921875,
      "learning_rate": 0.00010424412031961484,
      "loss": 0.8823,
      "step": 360
    },
    {
      "epoch": 5.0,
      "grad_norm": 11.8203125,
      "learning_rate": 0.0001,
      "loss": 0.8839,
      "step": 370
    },
    {
      "epoch": 5.135135135135135,
      "grad_norm": 11.515625,
      "learning_rate": 9.57558796803852e-05,
      "loss": 0.8362,
      "step": 380
    },
    {
      "epoch": 5.27027027027027,
      "grad_norm": 12.15625,
      "learning_rate": 9.151940755244912e-05,
      "loss": 0.8678,
      "step": 390
    },
    {
      "epoch": 5.405405405405405,
      "grad_norm": 13.109375,
      "learning_rate": 8.729821802531212e-05,
      "loss": 0.8372,
      "step": 400
    },
    {
      "epoch": 5.54054054054054,
      "grad_norm": 12.96875,
      "learning_rate": 8.309991796781511e-05,
      "loss": 0.8662,
      "step": 410
    },
    {
      "epoch": 5.675675675675675,
      "grad_norm": 15.203125,
      "learning_rate": 7.89320730004274e-05,
      "loss": 0.9021,
      "step": 420
    },
    {
      "epoch": 5.8108108108108105,
      "grad_norm": 12.4765625,
      "learning_rate": 7.48021938614875e-05,
      "loss": 0.8902,
      "step": 430
    },
    {
      "epoch": 5.945945945945946,
      "grad_norm": 12.953125,
      "learning_rate": 7.071772287234497e-05,
      "loss": 0.852,
      "step": 440
    },
    {
      "epoch": 6.081081081081081,
      "grad_norm": 14.9609375,
      "learning_rate": 6.668602052579424e-05,
      "loss": 0.8743,
      "step": 450
    },
    {
      "epoch": 6.216216216216216,
      "grad_norm": 12.8828125,
      "learning_rate": 6.271435222196916e-05,
      "loss": 0.8844,
      "step": 460
    },
    {
      "epoch": 6.351351351351352,
      "grad_norm": 13.3984375,
      "learning_rate": 5.880987517560075e-05,
      "loss": 0.8924,
      "step": 470
    },
    {
      "epoch": 6.486486486486487,
      "grad_norm": 14.3046875,
      "learning_rate": 5.497962551823266e-05,
      "loss": 0.9041,
      "step": 480
    },
    {
      "epoch": 6.621621621621622,
      "grad_norm": 15.421875,
      "learning_rate": 5.123050561863657e-05,
      "loss": 0.871,
      "step": 490
    },
    {
      "epoch": 6.756756756756757,
      "grad_norm": 12.7109375,
      "learning_rate": 4.756927164427685e-05,
      "loss": 0.8924,
      "step": 500
    },
    {
      "epoch": 6.891891891891892,
      "grad_norm": 13.765625,
      "learning_rate": 4.4002521386240466e-05,
      "loss": 0.9047,
      "step": 510
    },
    {
      "epoch": 7.027027027027027,
      "grad_norm": 13.09375,
      "learning_rate": 4.053668236957134e-05,
      "loss": 0.9083,
      "step": 520
    },
    {
      "epoch": 7.162162162162162,
      "grad_norm": 13.875,
      "learning_rate": 3.717800027043576e-05,
      "loss": 0.8721,
      "step": 530
    },
    {
      "epoch": 7.297297297297297,
      "grad_norm": 12.09375,
      "learning_rate": 3.393252766099187e-05,
      "loss": 0.916,
      "step": 540
    },
    {
      "epoch": 7.4324324324324325,
      "grad_norm": 12.3671875,
      "learning_rate": 3.080611310224539e-05,
      "loss": 0.8714,
      "step": 550
    },
    {
      "epoch": 7.5675675675675675,
      "grad_norm": 13.2109375,
      "learning_rate": 2.7804390604547557e-05,
      "loss": 0.8843,
      "step": 560
    },
    {
      "epoch": 7.702702702702703,
      "grad_norm": 13.9765625,
      "learning_rate": 2.493276947472756e-05,
      "loss": 0.8934,
      "step": 570
    },
    {
      "epoch": 7.837837837837838,
      "grad_norm": 14.28125,
      "learning_rate": 2.2196424568156073e-05,
      "loss": 0.8953,
      "step": 580
    },
    {
      "epoch": 7.972972972972973,
      "grad_norm": 14.8828125,
      "learning_rate": 1.9600286963305957e-05,
      "loss": 0.8728,
      "step": 590
    },
    {
      "epoch": 8.108108108108109,
      "grad_norm": 13.2890625,
      "learning_rate": 1.7149035075615794e-05,
      "loss": 0.8995,
      "step": 600
    },
    {
      "epoch": 8.243243243243244,
      "grad_norm": 14.7578125,
      "learning_rate": 1.4847086226668872e-05,
      "loss": 0.8685,
      "step": 610
    },
    {
      "epoch": 8.378378378378379,
      "grad_norm": 12.0703125,
      "learning_rate": 1.2698588683881186e-05,
      "loss": 0.88,
      "step": 620
    },
    {
      "epoch": 8.513513513513514,
      "grad_norm": 16.8125,
      "learning_rate": 1.0707414185043163e-05,
      "loss": 0.8936,
      "step": 630
    },
    {
      "epoch": 8.64864864864865,
      "grad_norm": 14.0859375,
      "learning_rate": 8.87715096118642e-06,
      "loss": 0.8745,
      "step": 640
    },
    {
      "epoch": 8.783783783783784,
      "grad_norm": 13.1796875,
      "learning_rate": 7.211097270349066e-06,
      "loss": 0.8849,
      "step": 650
    },
    {
      "epoch": 8.91891891891892,
      "grad_norm": 12.6328125,
      "learning_rate": 5.71225545389158e-06,
      "loss": 0.8775,
      "step": 660
    },
    {
      "epoch": 9.054054054054054,
      "grad_norm": 12.15625,
      "learning_rate": 4.383326526074916e-06,
      "loss": 0.8663,
      "step": 670
    },
    {
      "epoch": 9.18918918918919,
      "grad_norm": 12.9140625,
      "learning_rate": 3.226705306650113e-06,
      "loss": 0.8975,
      "step": 680
    },
    {
      "epoch": 9.324324324324325,
      "grad_norm": 14.265625,
      "learning_rate": 2.2444761052313856e-06,
      "loss": 0.8677,
      "step": 690
    },
    {
      "epoch": 9.45945945945946,
      "grad_norm": 14.46875,
      "learning_rate": 1.4384089652291543e-06,
      "loss": 0.8565,
      "step": 700
    },
    {
      "epoch": 9.594594594594595,
      "grad_norm": 13.4375,
      "learning_rate": 8.099564741123166e-07,
      "loss": 0.8619,
      "step": 710
    },
    {
      "epoch": 9.72972972972973,
      "grad_norm": 13.5859375,
      "learning_rate": 3.6025114574734785e-07,
      "loss": 0.8956,
      "step": 720
    },
    {
      "epoch": 9.864864864864865,
      "grad_norm": 14.1796875,
      "learning_rate": 9.010337953185843e-08,
      "loss": 0.8906,
      "step": 730
    },
    {
      "epoch": 10.0,
      "grad_norm": 13.2109375,
      "learning_rate": 0.0,
      "loss": 0.8617,
      "step": 740
    },
    {
      "epoch": 10.0,
      "step": 740,
      "total_flos": 4.83113130000384e+16,
      "train_loss": 0.9043467921179694,
      "train_runtime": 626.4938,
      "train_samples_per_second": 4.725,
      "train_steps_per_second": 1.181
    }
  ],
  "logging_steps": 10,
  "max_steps": 740,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 4.83113130000384e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}