{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.953917050691244,
  "eval_steps": 500,
  "global_step": 540,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18433179723502305,
      "grad_norm": 15.2578125,
      "learning_rate": 0.00019983081582712685,
      "loss": 1.1335,
      "step": 10
    },
    {
      "epoch": 0.3686635944700461,
      "grad_norm": 15.1484375,
      "learning_rate": 0.00019932383577419432,
      "loss": 1.0389,
      "step": 20
    },
    {
      "epoch": 0.5529953917050692,
      "grad_norm": 16.21875,
      "learning_rate": 0.00019848077530122083,
      "loss": 1.0017,
      "step": 30
    },
    {
      "epoch": 0.7373271889400922,
      "grad_norm": 13.3359375,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.9937,
      "step": 40
    },
    {
      "epoch": 0.9216589861751152,
      "grad_norm": 13.1171875,
      "learning_rate": 0.0001957989512315489,
      "loss": 0.9773,
      "step": 50
    },
    {
      "epoch": 1.1059907834101383,
      "grad_norm": 11.2578125,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.9484,
      "step": 60
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 13.71875,
      "learning_rate": 0.00019182161068802741,
      "loss": 0.9577,
      "step": 70
    },
    {
      "epoch": 1.4746543778801844,
      "grad_norm": 10.65625,
      "learning_rate": 0.00018936326403234125,
      "loss": 0.9277,
      "step": 80
    },
    {
      "epoch": 1.6589861751152073,
      "grad_norm": 12.90625,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.9301,
      "step": 90
    },
    {
      "epoch": 1.8433179723502304,
      "grad_norm": 13.7578125,
      "learning_rate": 0.00018354878114129367,
      "loss": 0.9212,
      "step": 100
    },
    {
      "epoch": 2.0276497695852536,
      "grad_norm": 10.140625,
      "learning_rate": 0.0001802123192755044,
      "loss": 0.8985,
      "step": 110
    },
    {
      "epoch": 2.2119815668202767,
      "grad_norm": 9.6015625,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.8939,
      "step": 120
    },
    {
      "epoch": 2.3963133640552994,
      "grad_norm": 11.921875,
      "learning_rate": 0.00017273736415730488,
      "loss": 0.8935,
      "step": 130
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 10.8203125,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.8973,
      "step": 140
    },
    {
      "epoch": 2.7649769585253456,
      "grad_norm": 11.7421875,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.9522,
      "step": 150
    },
    {
      "epoch": 2.9493087557603688,
      "grad_norm": 11.5234375,
      "learning_rate": 0.00015971585917027862,
      "loss": 0.9124,
      "step": 160
    },
    {
      "epoch": 3.133640552995392,
      "grad_norm": 10.25,
      "learning_rate": 0.0001549508978070806,
      "loss": 0.899,
      "step": 170
    },
    {
      "epoch": 3.3179723502304146,
      "grad_norm": 10.4609375,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8893,
      "step": 180
    },
    {
      "epoch": 3.5023041474654377,
      "grad_norm": 9.0078125,
      "learning_rate": 0.00014487991802004623,
      "loss": 0.8878,
      "step": 190
    },
    {
      "epoch": 3.686635944700461,
      "grad_norm": 10.21875,
      "learning_rate": 0.0001396079766039157,
      "loss": 0.8656,
      "step": 200
    },
    {
      "epoch": 3.870967741935484,
      "grad_norm": 7.875,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.8897,
      "step": 210
    },
    {
      "epoch": 4.055299539170507,
      "grad_norm": 9.4921875,
      "learning_rate": 0.00012868032327110904,
      "loss": 0.8549,
      "step": 220
    },
    {
      "epoch": 4.23963133640553,
      "grad_norm": 9.2421875,
      "learning_rate": 0.00012306158707424403,
      "loss": 0.8577,
      "step": 230
    },
    {
      "epoch": 4.423963133640553,
      "grad_norm": 7.875,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.8579,
      "step": 240
    },
    {
      "epoch": 4.6082949308755765,
      "grad_norm": 8.1328125,
      "learning_rate": 0.00011160929141252303,
      "loss": 0.8278,
      "step": 250
    },
    {
      "epoch": 4.792626728110599,
      "grad_norm": 7.01171875,
      "learning_rate": 0.00010581448289104758,
      "loss": 0.8458,
      "step": 260
    },
    {
      "epoch": 4.976958525345622,
      "grad_norm": 6.92578125,
      "learning_rate": 0.0001,
      "loss": 0.874,
      "step": 270
    },
    {
      "epoch": 5.161290322580645,
      "grad_norm": 8.1796875,
      "learning_rate": 9.418551710895243e-05,
      "loss": 0.8455,
      "step": 280
    },
    {
      "epoch": 5.345622119815668,
      "grad_norm": 7.21484375,
      "learning_rate": 8.839070858747697e-05,
      "loss": 0.8316,
      "step": 290
    },
    {
      "epoch": 5.529953917050691,
      "grad_norm": 9.9375,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.8555,
      "step": 300
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 7.5390625,
      "learning_rate": 7.693841292575598e-05,
      "loss": 0.8385,
      "step": 310
    },
    {
      "epoch": 5.8986175115207375,
      "grad_norm": 6.8515625,
      "learning_rate": 7.131967672889101e-05,
      "loss": 0.8339,
      "step": 320
    },
    {
      "epoch": 6.082949308755761,
      "grad_norm": 7.38671875,
      "learning_rate": 6.579798566743314e-05,
      "loss": 0.8497,
      "step": 330
    },
    {
      "epoch": 6.267281105990784,
      "grad_norm": 7.21875,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.836,
      "step": 340
    },
    {
      "epoch": 6.451612903225806,
      "grad_norm": 8.515625,
      "learning_rate": 5.5120081979953785e-05,
      "loss": 0.8411,
      "step": 350
    },
    {
      "epoch": 6.635944700460829,
      "grad_norm": 8.515625,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.822,
      "step": 360
    },
    {
      "epoch": 6.820276497695852,
      "grad_norm": 7.73828125,
      "learning_rate": 4.50491021929194e-05,
      "loss": 0.8298,
      "step": 370
    },
    {
      "epoch": 7.0046082949308754,
      "grad_norm": 7.15625,
      "learning_rate": 4.028414082972141e-05,
      "loss": 0.8366,
      "step": 380
    },
    {
      "epoch": 7.188940092165899,
      "grad_norm": 7.45703125,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.8222,
      "step": 390
    },
    {
      "epoch": 7.373271889400922,
      "grad_norm": 7.94921875,
      "learning_rate": 3.137583621312665e-05,
      "loss": 0.8294,
      "step": 400
    },
    {
      "epoch": 7.557603686635945,
      "grad_norm": 7.80078125,
      "learning_rate": 2.7262635842695127e-05,
      "loss": 0.8189,
      "step": 410
    },
    {
      "epoch": 7.741935483870968,
      "grad_norm": 7.33984375,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.8279,
      "step": 420
    },
    {
      "epoch": 7.926267281105991,
      "grad_norm": 10.0390625,
      "learning_rate": 1.9787680724495617e-05,
      "loss": 0.8299,
      "step": 430
    },
    {
      "epoch": 8.110599078341014,
      "grad_norm": 8.34375,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.8408,
      "step": 440
    },
    {
      "epoch": 8.294930875576037,
      "grad_norm": 7.22265625,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.819,
      "step": 450
    },
    {
      "epoch": 8.47926267281106,
      "grad_norm": 7.890625,
      "learning_rate": 1.0636735967658784e-05,
      "loss": 0.8087,
      "step": 460
    },
    {
      "epoch": 8.663594470046084,
      "grad_norm": 8.9296875,
      "learning_rate": 8.178389311972612e-06,
      "loss": 0.8218,
      "step": 470
    },
    {
      "epoch": 8.847926267281107,
      "grad_norm": 9.421875,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.8213,
      "step": 480
    },
    {
      "epoch": 9.03225806451613,
      "grad_norm": 7.0078125,
      "learning_rate": 4.20104876845111e-06,
      "loss": 0.8259,
      "step": 490
    },
    {
      "epoch": 9.216589861751151,
      "grad_norm": 7.5546875,
      "learning_rate": 2.6955129420176196e-06,
      "loss": 0.8463,
      "step": 500
    },
    {
      "epoch": 9.400921658986174,
      "grad_norm": 8.0546875,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 0.7932,
      "step": 510
    },
    {
      "epoch": 9.585253456221198,
      "grad_norm": 8.109375,
      "learning_rate": 6.761642258056978e-07,
      "loss": 0.8172,
      "step": 520
    },
    {
      "epoch": 9.76958525345622,
      "grad_norm": 7.5859375,
      "learning_rate": 1.6918417287318245e-07,
      "loss": 0.8263,
      "step": 530
    },
    {
      "epoch": 9.953917050691244,
      "grad_norm": 8.59375,
      "learning_rate": 0.0,
      "loss": 0.8372,
      "step": 540
    },
    {
      "epoch": 9.953917050691244,
      "step": 540,
      "total_flos": 3.52542013784064e+16,
      "train_loss": 0.8746989762341535,
      "train_runtime": 468.0964,
      "train_samples_per_second": 4.636,
      "train_steps_per_second": 1.154
    }
  ],
  "logging_steps": 10,
  "max_steps": 540,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 3.52542013784064e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}