{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.993779160186625,
  "eval_steps": 30,
  "global_step": 749,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 3.4262,
      "step": 9
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002,
      "loss": 2.6518,
      "step": 18
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 2.453,
      "step": 27
    },
    {
      "epoch": 0.28,
      "eval_loss": 2.0444083213806152,
      "eval_runtime": 62.6984,
      "eval_samples_per_second": 20.511,
      "eval_steps_per_second": 2.568,
      "step": 30
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 2.3345,
      "step": 36
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 2.3033,
      "step": 45
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 2.2692,
      "step": 54
    },
    {
      "epoch": 0.56,
      "eval_loss": 1.8969556093215942,
      "eval_runtime": 68.3363,
      "eval_samples_per_second": 18.819,
      "eval_steps_per_second": 2.356,
      "step": 60
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0002,
      "loss": 2.2294,
      "step": 63
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 2.235,
      "step": 72
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 2.1576,
      "step": 81
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 2.1485,
      "step": 90
    },
    {
      "epoch": 0.84,
      "eval_loss": 1.8373124599456787,
      "eval_runtime": 69.5775,
      "eval_samples_per_second": 18.483,
      "eval_steps_per_second": 2.314,
      "step": 90
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002,
      "loss": 2.1657,
      "step": 99
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 2.1049,
      "step": 108
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 2.0469,
      "step": 117
    },
    {
      "epoch": 1.12,
      "eval_loss": 1.8033325672149658,
      "eval_runtime": 69.7392,
      "eval_samples_per_second": 18.44,
      "eval_steps_per_second": 2.309,
      "step": 120
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 2.003,
      "step": 126
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0002,
      "loss": 1.9928,
      "step": 135
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0002,
      "loss": 1.9954,
      "step": 144
    },
    {
      "epoch": 1.4,
      "eval_loss": 1.7761518955230713,
      "eval_runtime": 68.9976,
      "eval_samples_per_second": 18.638,
      "eval_steps_per_second": 2.333,
      "step": 150
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 1.9571,
      "step": 153
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 2.0011,
      "step": 162
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0002,
      "loss": 1.983,
      "step": 171
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 1.9778,
      "step": 180
    },
    {
      "epoch": 1.68,
      "eval_loss": 1.7592827081680298,
      "eval_runtime": 71.1717,
      "eval_samples_per_second": 18.069,
      "eval_steps_per_second": 2.262,
      "step": 180
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0002,
      "loss": 1.9624,
      "step": 189
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 1.9384,
      "step": 198
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 1.9536,
      "step": 207
    },
    {
      "epoch": 1.96,
      "eval_loss": 1.7472261190414429,
      "eval_runtime": 68.6137,
      "eval_samples_per_second": 18.743,
      "eval_steps_per_second": 2.346,
      "step": 210
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0002,
      "loss": 1.9249,
      "step": 216
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0002,
      "loss": 1.8604,
      "step": 225
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0002,
      "loss": 1.8524,
      "step": 234
    },
    {
      "epoch": 2.24,
      "eval_loss": 1.730584740638733,
      "eval_runtime": 68.1311,
      "eval_samples_per_second": 18.875,
      "eval_steps_per_second": 2.363,
      "step": 240
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0002,
      "loss": 1.8442,
      "step": 243
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0002,
      "loss": 1.8647,
      "step": 252
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 1.8218,
      "step": 261
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0002,
      "loss": 1.8438,
      "step": 270
    },
    {
      "epoch": 2.52,
      "eval_loss": 1.7255065441131592,
      "eval_runtime": 67.2395,
      "eval_samples_per_second": 19.126,
      "eval_steps_per_second": 2.394,
      "step": 270
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0002,
      "loss": 1.8491,
      "step": 279
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0002,
      "loss": 1.8304,
      "step": 288
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0002,
      "loss": 1.8436,
      "step": 297
    },
    {
      "epoch": 2.8,
      "eval_loss": 1.7139911651611328,
      "eval_runtime": 70.3499,
      "eval_samples_per_second": 18.28,
      "eval_steps_per_second": 2.289,
      "step": 300
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0002,
      "loss": 1.8039,
      "step": 306
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0002,
      "loss": 1.8255,
      "step": 315
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0002,
      "loss": 1.7765,
      "step": 324
    },
    {
      "epoch": 3.08,
      "eval_loss": 1.7048661708831787,
      "eval_runtime": 70.1678,
      "eval_samples_per_second": 18.328,
      "eval_steps_per_second": 2.295,
      "step": 330
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0002,
      "loss": 1.7546,
      "step": 333
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0002,
      "loss": 1.7389,
      "step": 342
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0002,
      "loss": 1.7248,
      "step": 351
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0002,
      "loss": 1.7537,
      "step": 360
    },
    {
      "epoch": 3.36,
      "eval_loss": 1.7056528329849243,
      "eval_runtime": 70.6453,
      "eval_samples_per_second": 18.204,
      "eval_steps_per_second": 2.279,
      "step": 360
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0002,
      "loss": 1.7234,
      "step": 369
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0002,
      "loss": 1.7208,
      "step": 378
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.0002,
      "loss": 1.7328,
      "step": 387
    },
    {
      "epoch": 3.64,
      "eval_loss": 1.6977263689041138,
      "eval_runtime": 61.7073,
      "eval_samples_per_second": 20.84,
      "eval_steps_per_second": 2.609,
      "step": 390
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.0002,
      "loss": 1.7231,
      "step": 396
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0002,
      "loss": 1.7424,
      "step": 405
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0002,
      "loss": 1.723,
      "step": 414
    },
    {
      "epoch": 3.92,
      "eval_loss": 1.6972527503967285,
      "eval_runtime": 69.7095,
      "eval_samples_per_second": 18.448,
      "eval_steps_per_second": 2.31,
      "step": 420
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.0002,
      "loss": 1.6888,
      "step": 423
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.0002,
      "loss": 1.6847,
      "step": 432
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.0002,
      "loss": 1.6702,
      "step": 441
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0002,
      "loss": 1.6592,
      "step": 450
    },
    {
      "epoch": 4.2,
      "eval_loss": 1.7057932615280151,
      "eval_runtime": 71.3257,
      "eval_samples_per_second": 18.03,
      "eval_steps_per_second": 2.257,
      "step": 450
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0002,
      "loss": 1.6158,
      "step": 459
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0002,
      "loss": 1.6684,
      "step": 468
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.0002,
      "loss": 1.6563,
      "step": 477
    },
    {
      "epoch": 4.48,
      "eval_loss": 1.703405499458313,
      "eval_runtime": 67.5168,
      "eval_samples_per_second": 19.047,
      "eval_steps_per_second": 2.385,
      "step": 480
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.0002,
      "loss": 1.6111,
      "step": 486
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.0002,
      "loss": 1.6514,
      "step": 495
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0002,
      "loss": 1.6443,
      "step": 504
    },
    {
      "epoch": 4.76,
      "eval_loss": 1.6969022750854492,
      "eval_runtime": 68.7108,
      "eval_samples_per_second": 18.716,
      "eval_steps_per_second": 2.343,
      "step": 510
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0002,
      "loss": 1.6255,
      "step": 513
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.0002,
      "loss": 1.6563,
      "step": 522
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.0002,
      "loss": 1.617,
      "step": 531
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.0002,
      "loss": 1.5782,
      "step": 540
    },
    {
      "epoch": 5.04,
      "eval_loss": 1.6952643394470215,
      "eval_runtime": 68.1803,
      "eval_samples_per_second": 18.862,
      "eval_steps_per_second": 2.361,
      "step": 540
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.0002,
      "loss": 1.5834,
      "step": 549
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.0002,
      "loss": 1.5956,
      "step": 558
    },
    {
      "epoch": 5.3,
      "learning_rate": 0.0002,
      "loss": 1.509,
      "step": 567
    },
    {
      "epoch": 5.32,
      "eval_loss": 1.7135779857635498,
      "eval_runtime": 68.335,
      "eval_samples_per_second": 18.819,
      "eval_steps_per_second": 2.356,
      "step": 570
    },
    {
      "epoch": 5.38,
      "learning_rate": 0.0002,
      "loss": 1.5999,
      "step": 576
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.0002,
      "loss": 1.5743,
      "step": 585
    },
    {
      "epoch": 5.55,
      "learning_rate": 0.0002,
      "loss": 1.5516,
      "step": 594
    },
    {
      "epoch": 5.6,
      "eval_loss": 1.7064013481140137,
      "eval_runtime": 69.1824,
      "eval_samples_per_second": 18.589,
      "eval_steps_per_second": 2.327,
      "step": 600
    },
    {
      "epoch": 5.63,
      "learning_rate": 0.0002,
      "loss": 1.5623,
      "step": 603
    },
    {
      "epoch": 5.72,
      "learning_rate": 0.0002,
      "loss": 1.5476,
      "step": 612
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.0002,
      "loss": 1.5587,
      "step": 621
    },
    {
      "epoch": 5.88,
      "learning_rate": 0.0002,
      "loss": 1.558,
      "step": 630
    },
    {
      "epoch": 5.88,
      "eval_loss": 1.7045198678970337,
      "eval_runtime": 69.0953,
      "eval_samples_per_second": 18.612,
      "eval_steps_per_second": 2.33,
      "step": 630
    },
    {
      "epoch": 5.97,
      "learning_rate": 0.0002,
      "loss": 1.5317,
      "step": 639
    },
    {
      "epoch": 6.05,
      "learning_rate": 0.0002,
      "loss": 1.5192,
      "step": 648
    },
    {
      "epoch": 6.14,
      "learning_rate": 0.0002,
      "loss": 1.5016,
      "step": 657
    },
    {
      "epoch": 6.16,
      "eval_loss": 1.718214750289917,
      "eval_runtime": 68.4195,
      "eval_samples_per_second": 18.796,
      "eval_steps_per_second": 2.353,
      "step": 660
    },
    {
      "epoch": 6.22,
      "learning_rate": 0.0002,
      "loss": 1.5243,
      "step": 666
    },
    {
      "epoch": 6.3,
      "learning_rate": 0.0002,
      "loss": 1.4374,
      "step": 675
    },
    {
      "epoch": 6.39,
      "learning_rate": 0.0002,
      "loss": 1.5288,
      "step": 684
    },
    {
      "epoch": 6.44,
      "eval_loss": 1.7111074924468994,
      "eval_runtime": 68.9961,
      "eval_samples_per_second": 18.639,
      "eval_steps_per_second": 2.333,
      "step": 690
    },
    {
      "epoch": 6.47,
      "learning_rate": 0.0002,
      "loss": 1.4874,
      "step": 693
    },
    {
      "epoch": 6.56,
      "learning_rate": 0.0002,
      "loss": 1.4725,
      "step": 702
    },
    {
      "epoch": 6.64,
      "learning_rate": 0.0002,
      "loss": 1.5042,
      "step": 711
    },
    {
      "epoch": 6.72,
      "learning_rate": 0.0002,
      "loss": 1.4665,
      "step": 720
    },
    {
      "epoch": 6.72,
      "eval_loss": 1.7030370235443115,
      "eval_runtime": 67.7732,
      "eval_samples_per_second": 18.975,
      "eval_steps_per_second": 2.376,
      "step": 720
    },
    {
      "epoch": 6.81,
      "learning_rate": 0.0002,
      "loss": 1.4698,
      "step": 729
    },
    {
      "epoch": 6.89,
      "learning_rate": 0.0002,
      "loss": 1.5119,
      "step": 738
    },
    {
      "epoch": 6.98,
      "learning_rate": 0.0002,
      "loss": 1.4489,
      "step": 747
    },
    {
      "epoch": 6.99,
      "step": 749,
      "total_flos": 5.022814063873229e+16,
      "train_loss": 0.7637141177428262,
      "train_runtime": 5381.4192,
      "train_samples_per_second": 6.69,
      "train_steps_per_second": 0.139
    }
  ],
  "logging_steps": 9,
  "max_steps": 749,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "save_steps": 43,
  "total_flos": 5.022814063873229e+16,
  "trial_name": null,
  "trial_params": null
}