{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9272137227630969,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.999734597774032e-05,
      "loss": 1.6199,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.998938447446803e-05,
      "loss": 1.5062,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.997611718058365e-05,
      "loss": 1.4138,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9957546913022665e-05,
      "loss": 1.369,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.993367761465736e-05,
      "loss": 1.3408,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9904514353459654e-05,
      "loss": 1.3321,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9870063321425105e-05,
      "loss": 1.3251,
      "step": 70
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.983033183325818e-05,
      "loss": 1.3228,
      "step": 80
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.97853283248192e-05,
      "loss": 1.3111,
      "step": 90
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.973506235133323e-05,
      "loss": 1.3013,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.967954458536126e-05,
      "loss": 1.3004,
      "step": 110
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.9618786814534226e-05,
      "loss": 1.2959,
      "step": 120
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.955280193905022e-05,
      "loss": 1.2969,
      "step": 130
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.948160396893553e-05,
      "loss": 1.2879,
      "step": 140
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.9405208021069946e-05,
      "loss": 1.277,
      "step": 150
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.9323630315977156e-05,
      "loss": 1.283,
      "step": 160
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.9236888174380784e-05,
      "loss": 1.288,
      "step": 170
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.91450000135268e-05,
      "loss": 1.287,
      "step": 180
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.9047985343273154e-05,
      "loss": 1.2726,
      "step": 190
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.894586476194739e-05,
      "loss": 1.2808,
      "step": 200
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.883865995197319e-05,
      "loss": 1.2657,
      "step": 210
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.8726393675266716e-05,
      "loss": 1.275,
      "step": 220
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.860908976840376e-05,
      "loss": 1.2667,
      "step": 230
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.848677313755872e-05,
      "loss": 1.2715,
      "step": 240
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.835946975321647e-05,
      "loss": 1.273,
      "step": 250
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.822720664465827e-05,
      "loss": 1.2605,
      "step": 260
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.809001189422287e-05,
      "loss": 1.2766,
      "step": 270
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.794791463134399e-05,
      "loss": 1.262,
      "step": 280
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.780094502636552e-05,
      "loss": 1.255,
      "step": 290
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.764913428413572e-05,
      "loss": 1.2652,
      "step": 300
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.7492514637381727e-05,
      "loss": 1.2668,
      "step": 310
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.733111933986583e-05,
      "loss": 1.2621,
      "step": 320
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.716498265932501e-05,
      "loss": 1.257,
      "step": 330
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.699413987019512e-05,
      "loss": 1.2789,
      "step": 340
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.681862724612141e-05,
      "loss": 1.2634,
      "step": 350
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.663848205225674e-05,
      "loss": 1.2594,
      "step": 360
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.645374253734949e-05,
      "loss": 1.26,
      "step": 370
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.626444792562244e-05,
      "loss": 1.2514,
      "step": 380
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.607063840844463e-05,
      "loss": 1.2506,
      "step": 390
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.587235513579791e-05,
      "loss": 1.2648,
      "step": 400
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.5669640207539786e-05,
      "loss": 1.2511,
      "step": 410
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.546253666446484e-05,
      "loss": 1.2594,
      "step": 420
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.525108847916614e-05,
      "loss": 1.2608,
      "step": 430
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.503534054669892e-05,
      "loss": 1.2597,
      "step": 440
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.481533867504841e-05,
      "loss": 1.2609,
      "step": 450
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.4591129575403765e-05,
      "loss": 1.2505,
      "step": 460
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.43627608522403e-05,
      "loss": 1.2481,
      "step": 470
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.4130280993211974e-05,
      "loss": 1.2612,
      "step": 480
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.389373935885646e-05,
      "loss": 1.2504,
      "step": 490
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.365318617211479e-05,
      "loss": 1.2518,
      "step": 500
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.340867250766794e-05,
      "loss": 1.2458,
      "step": 510
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.316025028109258e-05,
      "loss": 1.2345,
      "step": 520
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.2907972237838225e-05,
      "loss": 1.2521,
      "step": 530
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.2651891942028274e-05,
      "loss": 1.2528,
      "step": 540
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.239206376508717e-05,
      "loss": 1.2462,
      "step": 550
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.212854287419611e-05,
      "loss": 1.2401,
      "step": 560
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.1861385220579934e-05,
      "loss": 1.2496,
      "step": 570
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.1590647527627404e-05,
      "loss": 1.2522,
      "step": 580
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.131638727884762e-05,
      "loss": 1.2377,
      "step": 590
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.103866270566498e-05,
      "loss": 1.2467,
      "step": 600
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.075753277505544e-05,
      "loss": 1.2421,
      "step": 610
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.0473057177026484e-05,
      "loss": 1.2455,
      "step": 620
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.018529631194369e-05,
      "loss": 1.2294,
      "step": 630
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.989431127770635e-05,
      "loss": 1.2509,
      "step": 640
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.960016385677513e-05,
      "loss": 1.2354,
      "step": 650
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.9302916503054246e-05,
      "loss": 1.2318,
      "step": 660
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.9002632328631164e-05,
      "loss": 1.2376,
      "step": 670
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.8699375090376534e-05,
      "loss": 1.2412,
      "step": 680
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.8393209176407223e-05,
      "loss": 1.2479,
      "step": 690
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.8084199592415305e-05,
      "loss": 1.2431,
      "step": 700
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.777241194786591e-05,
      "loss": 1.245,
      "step": 710
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.745791244206697e-05,
      "loss": 1.2393,
      "step": 720
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.714076785011359e-05,
      "loss": 1.2473,
      "step": 730
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.682104550871031e-05,
      "loss": 1.2552,
      "step": 740
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.649881330187401e-05,
      "loss": 1.2356,
      "step": 750
    },
    {
      "epoch": 0.7,
      "learning_rate": 3.617413964652067e-05,
      "loss": 1.2442,
      "step": 760
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.5847093477938956e-05,
      "loss": 1.2605,
      "step": 770
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.551774423515378e-05,
      "loss": 1.2364,
      "step": 780
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.518616184618288e-05,
      "loss": 1.2482,
      "step": 790
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.4852416713189526e-05,
      "loss": 1.2327,
      "step": 800
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.4516579697534705e-05,
      "loss": 1.2548,
      "step": 810
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.417872210473162e-05,
      "loss": 1.2469,
      "step": 820
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.3838915669306034e-05,
      "loss": 1.2424,
      "step": 830
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.349723253956542e-05,
      "loss": 1.2438,
      "step": 840
    },
    {
      "epoch": 0.79,
      "learning_rate": 3.315374526228036e-05,
      "loss": 1.243,
      "step": 850
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.2808526767281225e-05,
      "loss": 1.2416,
      "step": 860
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.246165035197364e-05,
      "loss": 1.2399,
      "step": 870
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.211318966577581e-05,
      "loss": 1.239,
      "step": 880
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.176321869448116e-05,
      "loss": 1.2498,
      "step": 890
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.1411811744549536e-05,
      "loss": 1.2438,
      "step": 900
    },
    {
      "epoch": 0.84,
      "learning_rate": 3.105904342733032e-05,
      "loss": 1.233,
      "step": 910
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.070498864322081e-05,
      "loss": 1.2315,
      "step": 920
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.034972256576328e-05,
      "loss": 1.232,
      "step": 930
    },
    {
      "epoch": 0.87,
      "learning_rate": 2.999332062568395e-05,
      "loss": 1.2467,
      "step": 940
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.9635858494877384e-05,
      "loss": 1.2483,
      "step": 950
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.9277412070339782e-05,
      "loss": 1.2377,
      "step": 960
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.891805745805429e-05,
      "loss": 1.2347,
      "step": 970
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.8557870956832132e-05,
      "loss": 1.2428,
      "step": 980
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.8196929042112652e-05,
      "loss": 1.244,
      "step": 990
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.783530834972594e-05,
      "loss": 1.2317,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2156,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "total_flos": 1.5703812576473252e+18,
  "trial_name": null,
  "trial_params": null
}