{
  "best_metric": 1.1948214769363403,
  "best_model_checkpoint": "outputs/checkpoint-600",
  "epoch": 0.192,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 1.8184,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 1.7858,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 3e-05,
      "loss": 1.7218,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 1.7218,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.7009,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 1.6714,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 7e-05,
      "loss": 1.6582,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.5659,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 9e-05,
      "loss": 1.5343,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.5252,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.414,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012,
      "loss": 1.3919,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.352,
      "step": 65
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014,
      "loss": 1.3762,
      "step": 70
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.3238,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016,
      "loss": 1.3306,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017,
      "loss": 1.3423,
      "step": 85
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018,
      "loss": 1.3199,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019,
      "loss": 1.3506,
      "step": 95
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.3315,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001998921832884097,
      "loss": 1.3142,
      "step": 105
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019978436657681943,
      "loss": 1.2994,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019967654986522912,
      "loss": 1.2972,
      "step": 115
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019956873315363883,
      "loss": 1.3135,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019946091644204851,
      "loss": 1.2903,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019935309973045823,
      "loss": 1.2783,
      "step": 130
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019924528301886794,
      "loss": 1.3044,
      "step": 135
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019913746630727762,
      "loss": 1.2947,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019902964959568736,
      "loss": 1.2759,
      "step": 145
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019892183288409705,
      "loss": 1.2746,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019881401617250676,
      "loss": 1.2869,
      "step": 155
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019870619946091644,
      "loss": 1.26,
      "step": 160
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019859838274932616,
      "loss": 1.258,
      "step": 165
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019849056603773587,
      "loss": 1.2649,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019838274932614555,
      "loss": 1.2549,
      "step": 175
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019827493261455526,
      "loss": 1.2859,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019816711590296498,
      "loss": 1.2934,
      "step": 185
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019805929919137466,
      "loss": 1.3011,
      "step": 190
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019795148247978437,
      "loss": 1.2304,
      "step": 195
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019784366576819408,
      "loss": 1.2849,
      "step": 200
    },
    {
      "epoch": 0.06,
      "eval_loss": 1.2345943450927734,
      "eval_runtime": 710.2534,
      "eval_samples_per_second": 7.04,
      "eval_steps_per_second": 0.88,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001977358490566038,
      "loss": 1.2726,
      "step": 205
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019762803234501348,
      "loss": 1.2996,
      "step": 210
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001975202156334232,
      "loss": 1.2456,
      "step": 215
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001974123989218329,
      "loss": 1.2794,
      "step": 220
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001973045822102426,
      "loss": 1.2637,
      "step": 225
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001971967654986523,
      "loss": 1.252,
      "step": 230
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000197088948787062,
      "loss": 1.2492,
      "step": 235
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001969811320754717,
      "loss": 1.2972,
      "step": 240
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001968733153638814,
      "loss": 1.3023,
      "step": 245
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019676549865229112,
      "loss": 1.2682,
      "step": 250
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019665768194070083,
      "loss": 1.2981,
      "step": 255
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019654986522911052,
      "loss": 1.3084,
      "step": 260
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019644204851752023,
      "loss": 1.2666,
      "step": 265
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019633423180592994,
      "loss": 1.2623,
      "step": 270
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019622641509433963,
      "loss": 1.2406,
      "step": 275
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019611859838274934,
      "loss": 1.2623,
      "step": 280
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019601078167115905,
      "loss": 1.2562,
      "step": 285
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019590296495956873,
      "loss": 1.2166,
      "step": 290
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019579514824797845,
      "loss": 1.2931,
      "step": 295
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019568733153638813,
      "loss": 1.2354,
      "step": 300
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019557951482479787,
      "loss": 1.2246,
      "step": 305
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019547169811320755,
      "loss": 1.2236,
      "step": 310
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019536388140161727,
      "loss": 1.2442,
      "step": 315
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019525606469002698,
      "loss": 1.2779,
      "step": 320
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019514824797843666,
      "loss": 1.2285,
      "step": 325
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019504043126684637,
      "loss": 1.2157,
      "step": 330
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019493261455525606,
      "loss": 1.2405,
      "step": 335
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001948247978436658,
      "loss": 1.2335,
      "step": 340
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019471698113207548,
      "loss": 1.2401,
      "step": 345
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019460916442048517,
      "loss": 1.2521,
      "step": 350
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001945013477088949,
      "loss": 1.2386,
      "step": 355
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001943935309973046,
      "loss": 1.2196,
      "step": 360
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001942857142857143,
      "loss": 1.192,
      "step": 365
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000194177897574124,
      "loss": 1.1964,
      "step": 370
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001940700808625337,
      "loss": 1.2876,
      "step": 375
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001939622641509434,
      "loss": 1.2622,
      "step": 380
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001938544474393531,
      "loss": 1.2183,
      "step": 385
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019374663072776284,
      "loss": 1.206,
      "step": 390
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019363881401617252,
      "loss": 1.2697,
      "step": 395
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001935309973045822,
      "loss": 1.2515,
      "step": 400
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.207701563835144,
      "eval_runtime": 709.7794,
      "eval_samples_per_second": 7.044,
      "eval_steps_per_second": 0.881,
      "step": 400
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019342318059299192,
      "loss": 1.2596,
      "step": 405
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019331536388140163,
      "loss": 1.2537,
      "step": 410
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019320754716981134,
      "loss": 1.2545,
      "step": 415
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019309973045822103,
      "loss": 1.2473,
      "step": 420
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019299191374663074,
      "loss": 1.2308,
      "step": 425
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019288409703504045,
      "loss": 1.2482,
      "step": 430
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019277628032345013,
      "loss": 1.2342,
      "step": 435
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019266846361185985,
      "loss": 1.2101,
      "step": 440
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019256064690026956,
      "loss": 1.233,
      "step": 445
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019245283018867927,
      "loss": 1.2401,
      "step": 450
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019234501347708895,
      "loss": 1.2088,
      "step": 455
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019223719676549864,
      "loss": 1.2205,
      "step": 460
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019212938005390838,
      "loss": 1.218,
      "step": 465
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019202156334231806,
      "loss": 1.2208,
      "step": 470
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019191374663072777,
      "loss": 1.2783,
      "step": 475
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019180592991913749,
      "loss": 1.1886,
      "step": 480
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019169811320754717,
      "loss": 1.1939,
      "step": 485
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019159029649595688,
      "loss": 1.2079,
      "step": 490
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019148247978436657,
      "loss": 1.2473,
      "step": 495
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001913746630727763,
      "loss": 1.2295,
      "step": 500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000191266846361186,
      "loss": 1.2064,
      "step": 505
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019115902964959568,
      "loss": 1.2138,
      "step": 510
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019105121293800541,
      "loss": 1.2618,
      "step": 515
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001909433962264151,
      "loss": 1.2495,
      "step": 520
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001908355795148248,
      "loss": 1.2553,
      "step": 525
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001907277628032345,
      "loss": 1.2334,
      "step": 530
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001906199460916442,
      "loss": 1.2442,
      "step": 535
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019051212938005392,
      "loss": 1.2301,
      "step": 540
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001904043126684636,
      "loss": 1.2678,
      "step": 545
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019029649595687334,
      "loss": 1.2116,
      "step": 550
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019018867924528303,
      "loss": 1.2556,
      "step": 555
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019008086253369274,
      "loss": 1.2427,
      "step": 560
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018997304582210242,
      "loss": 1.2138,
      "step": 565
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018986522911051214,
      "loss": 1.248,
      "step": 570
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00018975741239892185,
      "loss": 1.2415,
      "step": 575
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018964959568733153,
      "loss": 1.2303,
      "step": 580
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018954177897574125,
      "loss": 1.1939,
      "step": 585
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018943396226415096,
      "loss": 1.1927,
      "step": 590
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018932614555256064,
      "loss": 1.1982,
      "step": 595
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00018921832884097035,
      "loss": 1.1859,
      "step": 600
    },
    {
      "epoch": 0.19,
      "eval_loss": 1.1948214769363403,
      "eval_runtime": 709.3061,
      "eval_samples_per_second": 7.049,
      "eval_steps_per_second": 0.881,
      "step": 600
    }
  ],
  "max_steps": 9375,
  "num_train_epochs": 3,
  "total_flos": 3.57359129985024e+16,
  "trial_name": null,
  "trial_params": null
}