{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9917203311867526,
  "eval_steps": 500,
  "global_step": 813,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 4.93849938499385e-05,
      "loss": 3.0474,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.8769987699877e-05,
      "loss": 2.5423,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.81549815498155e-05,
      "loss": 2.494,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7539975399754e-05,
      "loss": 2.4624,
      "step": 40
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.6924969249692496e-05,
      "loss": 2.4676,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.6309963099631e-05,
      "loss": 2.4296,
      "step": 60
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.569495694956949e-05,
      "loss": 2.4051,
      "step": 70
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.5079950799507994e-05,
      "loss": 2.4153,
      "step": 80
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.4464944649446495e-05,
      "loss": 2.416,
      "step": 90
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.3849938499385e-05,
      "loss": 2.3806,
      "step": 100
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.323493234932349e-05,
      "loss": 2.359,
      "step": 110
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.261992619926199e-05,
      "loss": 2.3396,
      "step": 120
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.2004920049200495e-05,
      "loss": 2.3664,
      "step": 130
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.1389913899138996e-05,
      "loss": 2.3306,
      "step": 140
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.077490774907749e-05,
      "loss": 2.3515,
      "step": 150
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.015990159901599e-05,
      "loss": 2.2757,
      "step": 160
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.954489544895449e-05,
      "loss": 2.3511,
      "step": 170
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.892988929889299e-05,
      "loss": 2.3337,
      "step": 180
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.831488314883149e-05,
      "loss": 2.2724,
      "step": 190
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.769987699876999e-05,
      "loss": 2.3169,
      "step": 200
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.7084870848708486e-05,
      "loss": 2.2984,
      "step": 210
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.646986469864699e-05,
      "loss": 2.3052,
      "step": 220
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.585485854858548e-05,
      "loss": 2.2797,
      "step": 230
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.5239852398523984e-05,
      "loss": 2.2492,
      "step": 240
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.4624846248462485e-05,
      "loss": 2.2824,
      "step": 250
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.400984009840099e-05,
      "loss": 2.2565,
      "step": 260
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.339483394833948e-05,
      "loss": 2.2766,
      "step": 270
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.277982779827798e-05,
      "loss": 2.1366,
      "step": 280
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.2164821648216484e-05,
      "loss": 2.0625,
      "step": 290
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.1549815498154986e-05,
      "loss": 2.0812,
      "step": 300
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.093480934809348e-05,
      "loss": 2.0876,
      "step": 310
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.0319803198031982e-05,
      "loss": 2.0732,
      "step": 320
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.970479704797048e-05,
      "loss": 2.1055,
      "step": 330
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.908979089790898e-05,
      "loss": 2.0799,
      "step": 340
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.8474784747847476e-05,
      "loss": 2.0846,
      "step": 350
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.7859778597785978e-05,
      "loss": 2.0928,
      "step": 360
    },
    {
      "epoch": 1.36,
      "learning_rate": 2.7244772447724476e-05,
      "loss": 2.0533,
      "step": 370
    },
    {
      "epoch": 1.4,
      "learning_rate": 2.6629766297662977e-05,
      "loss": 2.0432,
      "step": 380
    },
    {
      "epoch": 1.44,
      "learning_rate": 2.6014760147601475e-05,
      "loss": 2.0408,
      "step": 390
    },
    {
      "epoch": 1.47,
      "learning_rate": 2.5399753997539977e-05,
      "loss": 2.1038,
      "step": 400
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.4784747847478475e-05,
      "loss": 2.0639,
      "step": 410
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.4169741697416977e-05,
      "loss": 2.0712,
      "step": 420
    },
    {
      "epoch": 1.58,
      "learning_rate": 2.3554735547355475e-05,
      "loss": 2.0843,
      "step": 430
    },
    {
      "epoch": 1.62,
      "learning_rate": 2.2939729397293973e-05,
      "loss": 2.0795,
      "step": 440
    },
    {
      "epoch": 1.66,
      "learning_rate": 2.2324723247232474e-05,
      "loss": 2.0812,
      "step": 450
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.1709717097170972e-05,
      "loss": 2.0648,
      "step": 460
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.1094710947109474e-05,
      "loss": 2.0476,
      "step": 470
    },
    {
      "epoch": 1.77,
      "learning_rate": 2.0479704797047972e-05,
      "loss": 2.0769,
      "step": 480
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.986469864698647e-05,
      "loss": 2.0753,
      "step": 490
    },
    {
      "epoch": 1.84,
      "learning_rate": 1.924969249692497e-05,
      "loss": 2.0336,
      "step": 500
    },
    {
      "epoch": 1.88,
      "learning_rate": 1.863468634686347e-05,
      "loss": 2.0888,
      "step": 510
    },
    {
      "epoch": 1.91,
      "learning_rate": 1.8019680196801968e-05,
      "loss": 2.0748,
      "step": 520
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.740467404674047e-05,
      "loss": 2.062,
      "step": 530
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.6789667896678967e-05,
      "loss": 2.0263,
      "step": 540
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.617466174661747e-05,
      "loss": 1.9472,
      "step": 550
    },
    {
      "epoch": 2.06,
      "learning_rate": 1.5559655596555967e-05,
      "loss": 1.9055,
      "step": 560
    },
    {
      "epoch": 2.1,
      "learning_rate": 1.4944649446494467e-05,
      "loss": 1.9086,
      "step": 570
    },
    {
      "epoch": 2.13,
      "learning_rate": 1.4329643296432965e-05,
      "loss": 1.9112,
      "step": 580
    },
    {
      "epoch": 2.17,
      "learning_rate": 1.3714637146371464e-05,
      "loss": 1.9361,
      "step": 590
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.3099630996309964e-05,
      "loss": 1.9229,
      "step": 600
    },
    {
      "epoch": 2.24,
      "learning_rate": 1.2484624846248464e-05,
      "loss": 1.9133,
      "step": 610
    },
    {
      "epoch": 2.28,
      "learning_rate": 1.1869618696186962e-05,
      "loss": 1.9196,
      "step": 620
    },
    {
      "epoch": 2.32,
      "learning_rate": 1.1254612546125462e-05,
      "loss": 1.9198,
      "step": 630
    },
    {
      "epoch": 2.36,
      "learning_rate": 1.0639606396063962e-05,
      "loss": 1.8842,
      "step": 640
    },
    {
      "epoch": 2.39,
      "learning_rate": 1.0024600246002461e-05,
      "loss": 1.948,
      "step": 650
    },
    {
      "epoch": 2.43,
      "learning_rate": 9.40959409594096e-06,
      "loss": 1.9455,
      "step": 660
    },
    {
      "epoch": 2.47,
      "learning_rate": 8.79458794587946e-06,
      "loss": 1.9538,
      "step": 670
    },
    {
      "epoch": 2.5,
      "learning_rate": 8.179581795817959e-06,
      "loss": 1.9362,
      "step": 680
    },
    {
      "epoch": 2.54,
      "learning_rate": 7.564575645756458e-06,
      "loss": 1.9044,
      "step": 690
    },
    {
      "epoch": 2.58,
      "learning_rate": 6.949569495694958e-06,
      "loss": 1.9351,
      "step": 700
    },
    {
      "epoch": 2.61,
      "learning_rate": 6.334563345633457e-06,
      "loss": 1.9374,
      "step": 710
    },
    {
      "epoch": 2.65,
      "learning_rate": 5.7195571955719566e-06,
      "loss": 1.9474,
      "step": 720
    },
    {
      "epoch": 2.69,
      "learning_rate": 5.1045510455104555e-06,
      "loss": 1.8852,
      "step": 730
    },
    {
      "epoch": 2.72,
      "learning_rate": 4.489544895448955e-06,
      "loss": 1.9285,
      "step": 740
    },
    {
      "epoch": 2.76,
      "learning_rate": 3.874538745387454e-06,
      "loss": 1.8788,
      "step": 750
    },
    {
      "epoch": 2.8,
      "learning_rate": 3.2595325953259536e-06,
      "loss": 1.9447,
      "step": 760
    },
    {
      "epoch": 2.83,
      "learning_rate": 2.6445264452644525e-06,
      "loss": 1.9196,
      "step": 770
    },
    {
      "epoch": 2.87,
      "learning_rate": 2.029520295202952e-06,
      "loss": 1.9037,
      "step": 780
    },
    {
      "epoch": 2.91,
      "learning_rate": 1.4145141451414515e-06,
      "loss": 1.8997,
      "step": 790
    },
    {
      "epoch": 2.94,
      "learning_rate": 7.995079950799507e-07,
      "loss": 1.9194,
      "step": 800
    },
    {
      "epoch": 2.98,
      "learning_rate": 1.845018450184502e-07,
      "loss": 1.8938,
      "step": 810
    },
    {
      "epoch": 2.99,
      "step": 813,
      "total_flos": 2.818102824586445e+16,
      "train_loss": 2.124213267956273,
      "train_runtime": 1043.2,
      "train_samples_per_second": 12.498,
      "train_steps_per_second": 0.779
    }
  ],
  "logging_steps": 10,
  "max_steps": 813,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.818102824586445e+16,
  "trial_name": null,
  "trial_params": null
}