{
  "best_metric": 1.7459986209869385,
  "best_model_checkpoint": "output/big-baby-tape/checkpoint-520",
  "epoch": 4.0,
  "global_step": 520,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 5.001712368734975e-07,
      "loss": 1.923,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9933913245728244e-06,
      "loss": 2.0321,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.457885751780542e-06,
      "loss": 2.0426,
      "step": 15
    },
    {
      "epoch": 0.15,
      "learning_rate": 7.857716640189785e-06,
      "loss": 2.0776,
      "step": 20
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.2143306799695167e-05,
      "loss": 1.9711,
      "step": 25
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.7252162675462473e-05,
      "loss": 2.0637,
      "step": 30
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.3109785644681427e-05,
      "loss": 1.8713,
      "step": 35
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.9630758374242703e-05,
      "loss": 2.088,
      "step": 40
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.671999039779749e-05,
      "loss": 1.9995,
      "step": 45
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.427410474888204e-05,
      "loss": 2.0004,
      "step": 50
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.218294542987354e-05,
      "loss": 1.9791,
      "step": 55
    },
    {
      "epoch": 0.46,
      "learning_rate": 6.03311837344848e-05,
      "loss": 1.882,
      "step": 60
    },
    {
      "epoch": 0.5,
      "learning_rate": 6.859999999999999e-05,
      "loss": 1.8736,
      "step": 65
    },
    {
      "epoch": 0.54,
      "learning_rate": 7.686881626551516e-05,
      "loss": 1.9173,
      "step": 70
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.501705457012643e-05,
      "loss": 2.0122,
      "step": 75
    },
    {
      "epoch": 0.62,
      "learning_rate": 9.292589525111794e-05,
      "loss": 1.871,
      "step": 80
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00010048000960220248,
      "loss": 2.0619,
      "step": 85
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00010756924162575728,
      "loss": 1.9238,
      "step": 90
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00011409021435531856,
      "loss": 2.0238,
      "step": 95
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001199478373245375,
      "loss": 1.9745,
      "step": 100
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00012505669320030482,
      "loss": 1.9809,
      "step": 105
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001293422833598102,
      "loss": 1.8881,
      "step": 110
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00013274211424821946,
      "loss": 1.8788,
      "step": 115
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013520660867542716,
      "loss": 1.984,
      "step": 120
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013669982876312649,
      "loss": 1.9443,
      "step": 125
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001372,
      "loss": 1.9006,
      "step": 130
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.9121332168579102,
      "eval_runtime": 9.6453,
      "eval_samples_per_second": 20.217,
      "eval_steps_per_second": 2.592,
      "step": 130
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001366998287631265,
      "loss": 1.8831,
      "step": 135
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00013520660867542716,
      "loss": 1.8547,
      "step": 140
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00013274211424821946,
      "loss": 1.87,
      "step": 145
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012934228335981023,
      "loss": 1.8612,
      "step": 150
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012505669320030482,
      "loss": 1.7875,
      "step": 155
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011994783732453754,
      "loss": 1.8327,
      "step": 160
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011409021435531858,
      "loss": 1.9541,
      "step": 165
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00010756924162575734,
      "loss": 1.8205,
      "step": 170
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00010048000960220251,
      "loss": 1.8993,
      "step": 175
    },
    {
      "epoch": 1.38,
      "learning_rate": 9.292589525111797e-05,
      "loss": 1.8431,
      "step": 180
    },
    {
      "epoch": 1.42,
      "learning_rate": 8.501705457012652e-05,
      "loss": 1.8127,
      "step": 185
    },
    {
      "epoch": 1.46,
      "learning_rate": 7.686881626551514e-05,
      "loss": 1.8428,
      "step": 190
    },
    {
      "epoch": 1.5,
      "learning_rate": 6.860000000000001e-05,
      "loss": 1.7509,
      "step": 195
    },
    {
      "epoch": 1.54,
      "learning_rate": 6.03311837344849e-05,
      "loss": 1.7859,
      "step": 200
    },
    {
      "epoch": 1.58,
      "learning_rate": 5.218294542987351e-05,
      "loss": 1.8358,
      "step": 205
    },
    {
      "epoch": 1.62,
      "learning_rate": 4.427410474888207e-05,
      "loss": 1.7393,
      "step": 210
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.6719990397797524e-05,
      "loss": 1.8051,
      "step": 215
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.9630758374242683e-05,
      "loss": 1.8083,
      "step": 220
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.310978564468145e-05,
      "loss": 1.7062,
      "step": 225
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.7252162675462497e-05,
      "loss": 1.7829,
      "step": 230
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.214330679969522e-05,
      "loss": 1.7874,
      "step": 235
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.8577166401898e-06,
      "loss": 1.8435,
      "step": 240
    },
    {
      "epoch": 1.88,
      "learning_rate": 4.457885751780558e-06,
      "loss": 1.8288,
      "step": 245
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.9933913245728472e-06,
      "loss": 1.7984,
      "step": 250
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.001712368734975e-07,
      "loss": 1.8331,
      "step": 255
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0,
      "loss": 1.8175,
      "step": 260
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.8163535594940186,
      "eval_runtime": 9.657,
      "eval_samples_per_second": 20.193,
      "eval_steps_per_second": 2.589,
      "step": 260
    },
    {
      "epoch": 2.04,
      "learning_rate": 5.001712368734899e-07,
      "loss": 1.7297,
      "step": 265
    },
    {
      "epoch": 2.08,
      "learning_rate": 1.9933913245728396e-06,
      "loss": 1.5719,
      "step": 270
    },
    {
      "epoch": 2.12,
      "learning_rate": 4.457885751780535e-06,
      "loss": 1.7261,
      "step": 275
    },
    {
      "epoch": 2.15,
      "learning_rate": 7.857716640189778e-06,
      "loss": 1.6366,
      "step": 280
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.2143306799695189e-05,
      "loss": 1.8032,
      "step": 285
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.725216267546246e-05,
      "loss": 1.8041,
      "step": 290
    },
    {
      "epoch": 2.27,
      "learning_rate": 2.310978564468141e-05,
      "loss": 1.752,
      "step": 295
    },
    {
      "epoch": 2.31,
      "learning_rate": 2.9630758374242642e-05,
      "loss": 1.831,
      "step": 300
    },
    {
      "epoch": 2.35,
      "learning_rate": 3.671999039779748e-05,
      "loss": 1.6489,
      "step": 305
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.427410474888202e-05,
      "loss": 1.7224,
      "step": 310
    },
    {
      "epoch": 2.42,
      "learning_rate": 5.218294542987346e-05,
      "loss": 1.6862,
      "step": 315
    },
    {
      "epoch": 2.46,
      "learning_rate": 6.033118373448485e-05,
      "loss": 1.7129,
      "step": 320
    },
    {
      "epoch": 2.5,
      "learning_rate": 6.859999999999997e-05,
      "loss": 1.9049,
      "step": 325
    },
    {
      "epoch": 2.54,
      "learning_rate": 7.68688162655151e-05,
      "loss": 1.8259,
      "step": 330
    },
    {
      "epoch": 2.58,
      "learning_rate": 8.501705457012648e-05,
      "loss": 1.7537,
      "step": 335
    },
    {
      "epoch": 2.62,
      "learning_rate": 9.292589525111793e-05,
      "loss": 1.7193,
      "step": 340
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.00010048000960220248,
      "loss": 1.7921,
      "step": 345
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.00010756924162575731,
      "loss": 1.7727,
      "step": 350
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00011409021435531856,
      "loss": 1.8267,
      "step": 355
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0001199478373245375,
      "loss": 1.6066,
      "step": 360
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0001250566932003048,
      "loss": 1.757,
      "step": 365
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00012934228335981018,
      "loss": 1.7909,
      "step": 370
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00013274211424821943,
      "loss": 1.7481,
      "step": 375
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.00013520660867542716,
      "loss": 1.7786,
      "step": 380
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00013669982876312649,
      "loss": 1.689,
      "step": 385
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0001372,
      "loss": 1.7754,
      "step": 390
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.8065567016601562,
      "eval_runtime": 9.6575,
      "eval_samples_per_second": 20.192,
      "eval_steps_per_second": 2.589,
      "step": 390
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001366998287631265,
      "loss": 1.6829,
      "step": 395
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0001352066086754272,
      "loss": 1.7295,
      "step": 400
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001327421142482195,
      "loss": 1.6853,
      "step": 405
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.00012934228335981015,
      "loss": 1.7343,
      "step": 410
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.00012505669320030482,
      "loss": 1.7685,
      "step": 415
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.00011994783732453755,
      "loss": 1.6945,
      "step": 420
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.00011409021435531858,
      "loss": 1.7482,
      "step": 425
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.00010756924162575738,
      "loss": 1.5529,
      "step": 430
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.00010048000960220263,
      "loss": 1.7141,
      "step": 435
    },
    {
      "epoch": 3.38,
      "learning_rate": 9.292589525111788e-05,
      "loss": 1.6804,
      "step": 440
    },
    {
      "epoch": 3.42,
      "learning_rate": 8.501705457012643e-05,
      "loss": 1.7525,
      "step": 445
    },
    {
      "epoch": 3.46,
      "learning_rate": 7.686881626551516e-05,
      "loss": 1.6325,
      "step": 450
    },
    {
      "epoch": 3.5,
      "learning_rate": 6.860000000000003e-05,
      "loss": 1.6941,
      "step": 455
    },
    {
      "epoch": 3.54,
      "learning_rate": 6.033118373448492e-05,
      "loss": 1.5753,
      "step": 460
    },
    {
      "epoch": 3.58,
      "learning_rate": 5.218294542987365e-05,
      "loss": 1.6565,
      "step": 465
    },
    {
      "epoch": 3.62,
      "learning_rate": 4.42741047488822e-05,
      "loss": 1.6553,
      "step": 470
    },
    {
      "epoch": 3.65,
      "learning_rate": 3.671999039779743e-05,
      "loss": 1.5705,
      "step": 475
    },
    {
      "epoch": 3.69,
      "learning_rate": 2.9630758374242696e-05,
      "loss": 1.7043,
      "step": 480
    },
    {
      "epoch": 3.73,
      "learning_rate": 2.3109785644681465e-05,
      "loss": 1.5999,
      "step": 485
    },
    {
      "epoch": 3.77,
      "learning_rate": 1.7252162675462504e-05,
      "loss": 1.675,
      "step": 490
    },
    {
      "epoch": 3.81,
      "learning_rate": 1.2143306799695228e-05,
      "loss": 1.6187,
      "step": 495
    },
    {
      "epoch": 3.85,
      "learning_rate": 7.857716640189861e-06,
      "loss": 1.5483,
      "step": 500
    },
    {
      "epoch": 3.88,
      "learning_rate": 4.4578857517805195e-06,
      "loss": 1.6583,
      "step": 505
    },
    {
      "epoch": 3.92,
      "learning_rate": 1.9933913245728244e-06,
      "loss": 1.6295,
      "step": 510
    },
    {
      "epoch": 3.96,
      "learning_rate": 5.001712368734975e-07,
      "loss": 1.5502,
      "step": 515
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0,
      "loss": 1.7657,
      "step": 520
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.7459986209869385,
      "eval_runtime": 9.6571,
      "eval_samples_per_second": 20.192,
      "eval_steps_per_second": 2.589,
      "step": 520
    }
  ],
  "max_steps": 520,
  "num_train_epochs": 4,
  "total_flos": 542964842496000.0,
  "trial_name": null,
  "trial_params": null
}