{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 540,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 9.9296875,
      "learning_rate": 0.00019983081582712685,
      "loss": 0.8329,
      "step": 10
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 15.890625,
      "learning_rate": 0.00019932383577419432,
      "loss": 0.8473,
      "step": 20
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 15.71875,
      "learning_rate": 0.00019848077530122083,
      "loss": 0.8181,
      "step": 30
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 17.453125,
      "learning_rate": 0.00019730448705798239,
      "loss": 0.8512,
      "step": 40
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 18.234375,
      "learning_rate": 0.0001957989512315489,
      "loss": 0.8302,
      "step": 50
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 25.78125,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.8281,
      "step": 60
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 24.984375,
      "learning_rate": 0.00019182161068802741,
      "loss": 0.8343,
      "step": 70
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 24.296875,
      "learning_rate": 0.00018936326403234125,
      "loss": 0.7968,
      "step": 80
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 16.3125,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.7891,
      "step": 90
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 13.578125,
      "learning_rate": 0.00018354878114129367,
      "loss": 0.7864,
      "step": 100
    },
    {
      "epoch": 2.037037037037037,
      "grad_norm": 14.25,
      "learning_rate": 0.0001802123192755044,
      "loss": 0.7815,
      "step": 110
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 14.7734375,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.7697,
      "step": 120
    },
    {
      "epoch": 2.4074074074074074,
      "grad_norm": 11.3125,
      "learning_rate": 0.00017273736415730488,
      "loss": 0.7728,
      "step": 130
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 11.203125,
      "learning_rate": 0.0001686241637868734,
      "loss": 0.7413,
      "step": 140
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 14.8125,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.749,
      "step": 150
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 11.5,
      "learning_rate": 0.00015971585917027862,
      "loss": 0.7216,
      "step": 160
    },
    {
      "epoch": 3.148148148148148,
      "grad_norm": 13.109375,
      "learning_rate": 0.0001549508978070806,
      "loss": 0.7739,
      "step": 170
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 13.453125,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.733,
      "step": 180
    },
    {
      "epoch": 3.5185185185185186,
      "grad_norm": 17.84375,
      "learning_rate": 0.00014487991802004623,
      "loss": 0.7267,
      "step": 190
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 16.765625,
      "learning_rate": 0.0001396079766039157,
      "loss": 0.7191,
      "step": 200
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 17.515625,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.7207,
      "step": 210
    },
    {
      "epoch": 4.074074074074074,
      "grad_norm": 21.578125,
      "learning_rate": 0.00012868032327110904,
      "loss": 0.7718,
      "step": 220
    },
    {
      "epoch": 4.2592592592592595,
      "grad_norm": 15.7890625,
      "learning_rate": 0.00012306158707424403,
      "loss": 0.7487,
      "step": 230
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 15.9140625,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.7416,
      "step": 240
    },
    {
      "epoch": 4.62962962962963,
      "grad_norm": 19.1875,
      "learning_rate": 0.00011160929141252303,
      "loss": 0.7517,
      "step": 250
    },
    {
      "epoch": 4.814814814814815,
      "grad_norm": 20.03125,
      "learning_rate": 0.00010581448289104758,
      "loss": 0.7521,
      "step": 260
    },
    {
      "epoch": 5.0,
      "grad_norm": 20.421875,
      "learning_rate": 0.0001,
      "loss": 0.753,
      "step": 270
    },
    {
      "epoch": 5.185185185185185,
      "grad_norm": 21.109375,
      "learning_rate": 9.418551710895243e-05,
      "loss": 0.7609,
      "step": 280
    },
    {
      "epoch": 5.37037037037037,
      "grad_norm": 17.53125,
      "learning_rate": 8.839070858747697e-05,
      "loss": 0.7744,
      "step": 290
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 16.90625,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.7907,
      "step": 300
    },
    {
      "epoch": 5.7407407407407405,
      "grad_norm": 20.46875,
      "learning_rate": 7.693841292575598e-05,
      "loss": 0.8155,
      "step": 310
    },
    {
      "epoch": 5.925925925925926,
      "grad_norm": 19.984375,
      "learning_rate": 7.131967672889101e-05,
      "loss": 0.7919,
      "step": 320
    },
    {
      "epoch": 6.111111111111111,
      "grad_norm": 20.0625,
      "learning_rate": 6.579798566743314e-05,
      "loss": 0.7648,
      "step": 330
    },
    {
      "epoch": 6.296296296296296,
      "grad_norm": 18.140625,
      "learning_rate": 6.039202339608432e-05,
      "loss": 0.7645,
      "step": 340
    },
    {
      "epoch": 6.481481481481482,
      "grad_norm": 17.40625,
      "learning_rate": 5.5120081979953785e-05,
      "loss": 0.7765,
      "step": 350
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 18.484375,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.8114,
      "step": 360
    },
    {
      "epoch": 6.851851851851852,
      "grad_norm": 21.609375,
      "learning_rate": 4.50491021929194e-05,
      "loss": 0.7967,
      "step": 370
    },
    {
      "epoch": 7.037037037037037,
      "grad_norm": 26.5625,
      "learning_rate": 4.028414082972141e-05,
      "loss": 0.8445,
      "step": 380
    },
    {
      "epoch": 7.222222222222222,
      "grad_norm": 21.703125,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.8495,
      "step": 390
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 20.984375,
      "learning_rate": 3.137583621312665e-05,
      "loss": 0.8274,
      "step": 400
    },
    {
      "epoch": 7.592592592592593,
      "grad_norm": 19.296875,
      "learning_rate": 2.7262635842695127e-05,
      "loss": 0.8176,
      "step": 410
    },
    {
      "epoch": 7.777777777777778,
      "grad_norm": 21.984375,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.8328,
      "step": 420
    },
    {
      "epoch": 7.962962962962963,
      "grad_norm": 20.515625,
      "learning_rate": 1.9787680724495617e-05,
      "loss": 0.8183,
      "step": 430
    },
    {
      "epoch": 8.148148148148149,
      "grad_norm": 25.671875,
      "learning_rate": 1.6451218858706374e-05,
      "loss": 0.7987,
      "step": 440
    },
    {
      "epoch": 8.333333333333334,
      "grad_norm": 20.28125,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.7994,
      "step": 450
    },
    {
      "epoch": 8.518518518518519,
      "grad_norm": 22.828125,
      "learning_rate": 1.0636735967658784e-05,
      "loss": 0.7928,
      "step": 460
    },
    {
      "epoch": 8.703703703703704,
      "grad_norm": 22.375,
      "learning_rate": 8.178389311972612e-06,
      "loss": 0.7978,
      "step": 470
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 22.171875,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.8077,
      "step": 480
    },
    {
      "epoch": 9.074074074074074,
      "grad_norm": 21.28125,
      "learning_rate": 4.20104876845111e-06,
      "loss": 0.8003,
      "step": 490
    },
    {
      "epoch": 9.25925925925926,
      "grad_norm": 18.765625,
      "learning_rate": 2.6955129420176196e-06,
      "loss": 0.8012,
      "step": 500
    },
    {
      "epoch": 9.444444444444445,
      "grad_norm": 19.609375,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 0.7831,
      "step": 510
    },
    {
      "epoch": 9.62962962962963,
      "grad_norm": 17.96875,
      "learning_rate": 6.761642258056978e-07,
      "loss": 0.783,
      "step": 520
    },
    {
      "epoch": 9.814814814814815,
      "grad_norm": 18.890625,
      "learning_rate": 1.6918417287318245e-07,
      "loss": 0.8059,
      "step": 530
    },
    {
      "epoch": 10.0,
      "grad_norm": 28.9375,
      "learning_rate": 0.0,
      "loss": 0.7967,
      "step": 540
    },
    {
      "epoch": 10.0,
      "step": 540,
      "total_flos": 3.52542013784064e+16,
      "train_loss": 0.7879019375200624,
      "train_runtime": 461.2272,
      "train_samples_per_second": 4.683,
      "train_steps_per_second": 1.171
    }
  ],
  "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
}