{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 3000,
  "global_step": 1080,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.00019814814814814814,
      "loss": 2.1983,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001962962962962963,
      "loss": 2.1208,
      "step": 20
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019444444444444446,
      "loss": 1.8985,
      "step": 30
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001925925925925926,
      "loss": 1.726,
      "step": 40
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019074074074074075,
      "loss": 1.6799,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00018888888888888888,
      "loss": 1.5807,
      "step": 60
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018703703703703704,
      "loss": 1.5165,
      "step": 70
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001851851851851852,
      "loss": 1.4893,
      "step": 80
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00018333333333333334,
      "loss": 1.24,
      "step": 90
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001814814814814815,
      "loss": 1.2977,
      "step": 100
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00017962962962962963,
      "loss": 1.2492,
      "step": 110
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.1566,
      "step": 120
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00017592592592592595,
      "loss": 1.3443,
      "step": 130
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00017407407407407408,
      "loss": 1.2112,
      "step": 140
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00017222222222222224,
      "loss": 1.0302,
      "step": 150
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00017037037037037037,
      "loss": 1.1856,
      "step": 160
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00016851851851851853,
      "loss": 1.1745,
      "step": 170
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.0659,
      "step": 180
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00016481481481481482,
      "loss": 1.0134,
      "step": 190
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00016296296296296295,
      "loss": 0.9692,
      "step": 200
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001611111111111111,
      "loss": 0.8877,
      "step": 210
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00015925925925925927,
      "loss": 0.8419,
      "step": 220
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00015740740740740743,
      "loss": 0.9147,
      "step": 230
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.0111,
      "step": 240
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001537037037037037,
      "loss": 0.9457,
      "step": 250
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015185185185185185,
      "loss": 0.9867,
      "step": 260
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1366,
      "step": 270
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00014814814814814815,
      "loss": 0.7648,
      "step": 280
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001462962962962963,
      "loss": 0.8693,
      "step": 290
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.8179,
      "step": 300
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001425925925925926,
      "loss": 0.8077,
      "step": 310
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00014074074074074076,
      "loss": 0.941,
      "step": 320
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001388888888888889,
      "loss": 0.8906,
      "step": 330
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00013703703703703705,
      "loss": 0.8433,
      "step": 340
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00013518518518518518,
      "loss": 0.7654,
      "step": 350
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.7217,
      "step": 360
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001314814814814815,
      "loss": 0.8744,
      "step": 370
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00012962962962962963,
      "loss": 0.6337,
      "step": 380
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00012777777777777776,
      "loss": 0.6369,
      "step": 390
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00012592592592592592,
      "loss": 0.5268,
      "step": 400
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00012407407407407408,
      "loss": 0.8015,
      "step": 410
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00012222222222222224,
      "loss": 0.5013,
      "step": 420
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00012037037037037037,
      "loss": 0.6063,
      "step": 430
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00011851851851851852,
      "loss": 0.7767,
      "step": 440
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00011666666666666668,
      "loss": 0.5174,
      "step": 450
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00011481481481481482,
      "loss": 0.6391,
      "step": 460
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00011296296296296296,
      "loss": 0.4966,
      "step": 470
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.5991,
      "step": 480
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00010925925925925926,
      "loss": 0.5499,
      "step": 490
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00010740740740740742,
      "loss": 0.5488,
      "step": 500
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00010555555555555557,
      "loss": 0.5834,
      "step": 510
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001037037037037037,
      "loss": 0.6238,
      "step": 520
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00010185185185185186,
      "loss": 0.6365,
      "step": 530
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001,
      "loss": 0.5337,
      "step": 540
    },
    {
      "epoch": 2.04,
      "learning_rate": 9.814814814814815e-05,
      "loss": 0.4326,
      "step": 550
    },
    {
      "epoch": 2.07,
      "learning_rate": 9.62962962962963e-05,
      "loss": 0.4197,
      "step": 560
    },
    {
      "epoch": 2.11,
      "learning_rate": 9.444444444444444e-05,
      "loss": 0.3268,
      "step": 570
    },
    {
      "epoch": 2.15,
      "learning_rate": 9.25925925925926e-05,
      "loss": 0.3066,
      "step": 580
    },
    {
      "epoch": 2.19,
      "learning_rate": 9.074074074074075e-05,
      "loss": 0.4737,
      "step": 590
    },
    {
      "epoch": 2.22,
      "learning_rate": 8.888888888888889e-05,
      "loss": 0.3185,
      "step": 600
    },
    {
      "epoch": 2.26,
      "learning_rate": 8.703703703703704e-05,
      "loss": 0.4233,
      "step": 610
    },
    {
      "epoch": 2.3,
      "learning_rate": 8.518518518518518e-05,
      "loss": 0.3377,
      "step": 620
    },
    {
      "epoch": 2.33,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.3957,
      "step": 630
    },
    {
      "epoch": 2.37,
      "learning_rate": 8.148148148148148e-05,
      "loss": 0.3915,
      "step": 640
    },
    {
      "epoch": 2.41,
      "learning_rate": 7.962962962962964e-05,
      "loss": 0.3025,
      "step": 650
    },
    {
      "epoch": 2.44,
      "learning_rate": 7.777777777777778e-05,
      "loss": 0.2896,
      "step": 660
    },
    {
      "epoch": 2.48,
      "learning_rate": 7.592592592592593e-05,
      "loss": 0.2558,
      "step": 670
    },
    {
      "epoch": 2.52,
      "learning_rate": 7.407407407407407e-05,
      "loss": 0.3477,
      "step": 680
    },
    {
      "epoch": 2.56,
      "learning_rate": 7.222222222222222e-05,
      "loss": 0.2111,
      "step": 690
    },
    {
      "epoch": 2.59,
      "learning_rate": 7.037037037037038e-05,
      "loss": 0.2885,
      "step": 700
    },
    {
      "epoch": 2.63,
      "learning_rate": 6.851851851851852e-05,
      "loss": 0.2953,
      "step": 710
    },
    {
      "epoch": 2.67,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.2415,
      "step": 720
    },
    {
      "epoch": 2.7,
      "learning_rate": 6.481481481481482e-05,
      "loss": 0.3242,
      "step": 730
    },
    {
      "epoch": 2.74,
      "learning_rate": 6.296296296296296e-05,
      "loss": 0.2616,
      "step": 740
    },
    {
      "epoch": 2.78,
      "learning_rate": 6.111111111111112e-05,
      "loss": 0.2853,
      "step": 750
    },
    {
      "epoch": 2.81,
      "learning_rate": 5.925925925925926e-05,
      "loss": 0.2828,
      "step": 760
    },
    {
      "epoch": 2.85,
      "learning_rate": 5.740740740740741e-05,
      "loss": 0.2382,
      "step": 770
    },
    {
      "epoch": 2.89,
      "learning_rate": 5.555555555555556e-05,
      "loss": 0.3508,
      "step": 780
    },
    {
      "epoch": 2.93,
      "learning_rate": 5.370370370370371e-05,
      "loss": 0.2794,
      "step": 790
    },
    {
      "epoch": 2.96,
      "learning_rate": 5.185185185185185e-05,
      "loss": 0.3247,
      "step": 800
    },
    {
      "epoch": 3.0,
      "learning_rate": 5e-05,
      "loss": 0.2753,
      "step": 810
    },
    {
      "epoch": 3.04,
      "learning_rate": 4.814814814814815e-05,
      "loss": 0.1453,
      "step": 820
    },
    {
      "epoch": 3.07,
      "learning_rate": 4.62962962962963e-05,
      "loss": 0.1666,
      "step": 830
    },
    {
      "epoch": 3.11,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 0.1369,
      "step": 840
    },
    {
      "epoch": 3.15,
      "learning_rate": 4.259259259259259e-05,
      "loss": 0.1086,
      "step": 850
    },
    {
      "epoch": 3.19,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.0967,
      "step": 860
    },
    {
      "epoch": 3.22,
      "learning_rate": 3.888888888888889e-05,
      "loss": 0.1327,
      "step": 870
    },
    {
      "epoch": 3.26,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.0848,
      "step": 880
    },
    {
      "epoch": 3.3,
      "learning_rate": 3.518518518518519e-05,
      "loss": 0.1173,
      "step": 890
    },
    {
      "epoch": 3.33,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.135,
      "step": 900
    },
    {
      "epoch": 3.37,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.1979,
      "step": 910
    },
    {
      "epoch": 3.41,
      "learning_rate": 2.962962962962963e-05,
      "loss": 0.1181,
      "step": 920
    },
    {
      "epoch": 3.44,
      "learning_rate": 2.777777777777778e-05,
      "loss": 0.0957,
      "step": 930
    },
    {
      "epoch": 3.48,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.0927,
      "step": 940
    },
    {
      "epoch": 3.52,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 0.094,
      "step": 950
    },
    {
      "epoch": 3.56,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.1197,
      "step": 960
    },
    {
      "epoch": 3.59,
      "learning_rate": 2.037037037037037e-05,
      "loss": 0.0927,
      "step": 970
    },
    {
      "epoch": 3.63,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.1523,
      "step": 980
    },
    {
      "epoch": 3.67,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.2582,
      "step": 990
    },
    {
      "epoch": 3.7,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.1101,
      "step": 1000
    },
    {
      "epoch": 3.74,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.1582,
      "step": 1010
    },
    {
      "epoch": 3.78,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 0.0504,
      "step": 1020
    },
    {
      "epoch": 3.81,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.0788,
      "step": 1030
    },
    {
      "epoch": 3.85,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.0607,
      "step": 1040
    },
    {
      "epoch": 3.89,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.1061,
      "step": 1050
    },
    {
      "epoch": 3.93,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.0645,
      "step": 1060
    },
    {
      "epoch": 3.96,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.0971,
      "step": 1070
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0,
      "loss": 0.128,
      "step": 1080
    },
    {
      "epoch": 4.0,
      "step": 1080,
      "total_flos": 1.339145591637934e+18,
      "train_loss": 0.6042599819324634,
      "train_runtime": 412.4773,
      "train_samples_per_second": 41.893,
      "train_steps_per_second": 2.618
    }
  ],
  "logging_steps": 10,
  "max_steps": 1080,
  "num_train_epochs": 4,
  "save_steps": 3000,
  "total_flos": 1.339145591637934e+18,
  "trial_name": null,
  "trial_params": null
}