{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.846153846153847,
  "global_step": 896,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 3e-06,
      "loss": 4.0528,
      "step": 10
    },
    {
      "epoch": 0.22,
      "learning_rate": 6e-06,
      "loss": 4.0182,
      "step": 20
    },
    {
      "epoch": 0.33,
      "learning_rate": 9e-06,
      "loss": 3.9239,
      "step": 30
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.2e-05,
      "loss": 3.5011,
      "step": 40
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.5e-05,
      "loss": 3.2438,
      "step": 50
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.8e-05,
      "loss": 3.1774,
      "step": 60
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.1e-05,
      "loss": 3.1056,
      "step": 70
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.4e-05,
      "loss": 3.0254,
      "step": 80
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 2.941,
      "step": 90
    },
    {
      "epoch": 1.1,
      "learning_rate": 3e-05,
      "loss": 2.8396,
      "step": 100
    },
    {
      "epoch": 1.1,
      "eval_loss": 2.859715223312378,
      "eval_runtime": 56.6611,
      "eval_samples_per_second": 4.73,
      "eval_steps_per_second": 0.088,
      "step": 100
    },
    {
      "epoch": 1.21,
      "learning_rate": 2.962962962962963e-05,
      "loss": 2.7745,
      "step": 110
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.925925925925926e-05,
      "loss": 2.6745,
      "step": 120
    },
    {
      "epoch": 1.43,
      "learning_rate": 2.8888888888888888e-05,
      "loss": 2.6359,
      "step": 130
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.851851851851852e-05,
      "loss": 2.5991,
      "step": 140
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.8148148148148147e-05,
      "loss": 2.6046,
      "step": 150
    },
    {
      "epoch": 1.76,
      "learning_rate": 2.777777777777778e-05,
      "loss": 2.4419,
      "step": 160
    },
    {
      "epoch": 1.87,
      "learning_rate": 2.7407407407407408e-05,
      "loss": 2.4514,
      "step": 170
    },
    {
      "epoch": 1.98,
      "learning_rate": 2.7037037037037037e-05,
      "loss": 2.4557,
      "step": 180
    },
    {
      "epoch": 2.09,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 2.1795,
      "step": 190
    },
    {
      "epoch": 2.2,
      "learning_rate": 2.6296296296296296e-05,
      "loss": 2.1014,
      "step": 200
    },
    {
      "epoch": 2.2,
      "eval_loss": 2.2379915714263916,
      "eval_runtime": 62.1156,
      "eval_samples_per_second": 4.315,
      "eval_steps_per_second": 0.08,
      "step": 200
    },
    {
      "epoch": 2.31,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 2.0129,
      "step": 210
    },
    {
      "epoch": 2.42,
      "learning_rate": 2.5555555555555557e-05,
      "loss": 2.0986,
      "step": 220
    },
    {
      "epoch": 2.53,
      "learning_rate": 2.5185185185185183e-05,
      "loss": 2.0814,
      "step": 230
    },
    {
      "epoch": 2.64,
      "learning_rate": 2.4814814814814816e-05,
      "loss": 1.9973,
      "step": 240
    },
    {
      "epoch": 2.75,
      "learning_rate": 2.4444444444444445e-05,
      "loss": 1.959,
      "step": 250
    },
    {
      "epoch": 2.86,
      "learning_rate": 2.4074074074074074e-05,
      "loss": 1.9774,
      "step": 260
    },
    {
      "epoch": 2.97,
      "learning_rate": 2.3703703703703703e-05,
      "loss": 1.9267,
      "step": 270
    },
    {
      "epoch": 3.08,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.8192,
      "step": 280
    },
    {
      "epoch": 3.19,
      "learning_rate": 2.296296296296296e-05,
      "loss": 1.6512,
      "step": 290
    },
    {
      "epoch": 3.3,
      "learning_rate": 2.2592592592592594e-05,
      "loss": 1.5577,
      "step": 300
    },
    {
      "epoch": 3.3,
      "eval_loss": 2.048072576522827,
      "eval_runtime": 55.3343,
      "eval_samples_per_second": 4.843,
      "eval_steps_per_second": 0.09,
      "step": 300
    },
    {
      "epoch": 3.41,
      "learning_rate": 2.222222222222222e-05,
      "loss": 1.5442,
      "step": 310
    },
    {
      "epoch": 3.52,
      "learning_rate": 2.1851851851851852e-05,
      "loss": 1.5807,
      "step": 320
    },
    {
      "epoch": 3.63,
      "learning_rate": 2.148148148148148e-05,
      "loss": 1.6009,
      "step": 330
    },
    {
      "epoch": 3.74,
      "learning_rate": 2.111111111111111e-05,
      "loss": 1.5485,
      "step": 340
    },
    {
      "epoch": 3.85,
      "learning_rate": 2.074074074074074e-05,
      "loss": 1.6185,
      "step": 350
    },
    {
      "epoch": 3.96,
      "learning_rate": 2.0370370370370372e-05,
      "loss": 1.5032,
      "step": 360
    },
    {
      "epoch": 4.07,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 1.2841,
      "step": 370
    },
    {
      "epoch": 4.18,
      "learning_rate": 1.962962962962963e-05,
      "loss": 1.2237,
      "step": 380
    },
    {
      "epoch": 4.29,
      "learning_rate": 1.925925925925926e-05,
      "loss": 1.2177,
      "step": 390
    },
    {
      "epoch": 4.4,
      "learning_rate": 1.888888888888889e-05,
      "loss": 1.2009,
      "step": 400
    },
    {
      "epoch": 4.4,
      "eval_loss": 1.8517041206359863,
      "eval_runtime": 56.0224,
      "eval_samples_per_second": 4.784,
      "eval_steps_per_second": 0.089,
      "step": 400
    },
    {
      "epoch": 4.51,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 1.1844,
      "step": 410
    },
    {
      "epoch": 4.62,
      "learning_rate": 1.814814814814815e-05,
      "loss": 1.2252,
      "step": 420
    },
    {
      "epoch": 4.73,
      "learning_rate": 1.7777777777777777e-05,
      "loss": 1.1829,
      "step": 430
    },
    {
      "epoch": 4.84,
      "learning_rate": 1.740740740740741e-05,
      "loss": 1.177,
      "step": 440
    },
    {
      "epoch": 4.95,
      "learning_rate": 1.7037037037037035e-05,
      "loss": 1.194,
      "step": 450
    },
    {
      "epoch": 5.05,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.0947,
      "step": 460
    },
    {
      "epoch": 5.16,
      "learning_rate": 1.6296296296296297e-05,
      "loss": 1.0177,
      "step": 470
    },
    {
      "epoch": 5.27,
      "learning_rate": 1.5925925925925926e-05,
      "loss": 0.9692,
      "step": 480
    },
    {
      "epoch": 5.38,
      "learning_rate": 1.5555555555555555e-05,
      "loss": 0.9933,
      "step": 490
    },
    {
      "epoch": 5.49,
      "learning_rate": 1.5185185185185186e-05,
      "loss": 0.9451,
      "step": 500
    },
    {
      "epoch": 5.49,
      "eval_loss": 1.683161973953247,
      "eval_runtime": 51.3302,
      "eval_samples_per_second": 5.221,
      "eval_steps_per_second": 0.097,
      "step": 500
    },
    {
      "epoch": 5.6,
      "learning_rate": 1.4814814814814815e-05,
      "loss": 0.9674,
      "step": 510
    },
    {
      "epoch": 5.71,
      "learning_rate": 1.4444444444444444e-05,
      "loss": 0.9519,
      "step": 520
    },
    {
      "epoch": 5.82,
      "learning_rate": 1.4074074074074073e-05,
      "loss": 0.9108,
      "step": 530
    },
    {
      "epoch": 5.93,
      "learning_rate": 1.3703703703703704e-05,
      "loss": 0.8963,
      "step": 540
    },
    {
      "epoch": 6.04,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.8255,
      "step": 550
    },
    {
      "epoch": 6.15,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.773,
      "step": 560
    },
    {
      "epoch": 6.26,
      "learning_rate": 1.2592592592592592e-05,
      "loss": 0.7945,
      "step": 570
    },
    {
      "epoch": 6.37,
      "learning_rate": 1.2222222222222222e-05,
      "loss": 0.7398,
      "step": 580
    },
    {
      "epoch": 6.48,
      "learning_rate": 1.1851851851851852e-05,
      "loss": 0.7495,
      "step": 590
    },
    {
      "epoch": 6.59,
      "learning_rate": 1.148148148148148e-05,
      "loss": 0.7491,
      "step": 600
    },
    {
      "epoch": 6.59,
      "eval_loss": 1.6291619539260864,
      "eval_runtime": 56.8018,
      "eval_samples_per_second": 4.718,
      "eval_steps_per_second": 0.088,
      "step": 600
    },
    {
      "epoch": 6.7,
      "learning_rate": 1.111111111111111e-05,
      "loss": 0.7644,
      "step": 610
    },
    {
      "epoch": 6.81,
      "learning_rate": 1.074074074074074e-05,
      "loss": 0.7328,
      "step": 620
    },
    {
      "epoch": 6.92,
      "learning_rate": 1.037037037037037e-05,
      "loss": 0.7294,
      "step": 630
    },
    {
      "epoch": 7.03,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.6665,
      "step": 640
    },
    {
      "epoch": 7.14,
      "learning_rate": 9.62962962962963e-06,
      "loss": 0.6109,
      "step": 650
    },
    {
      "epoch": 7.25,
      "learning_rate": 9.259259259259259e-06,
      "loss": 0.6219,
      "step": 660
    },
    {
      "epoch": 7.36,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.592,
      "step": 670
    },
    {
      "epoch": 7.47,
      "learning_rate": 8.518518518518517e-06,
      "loss": 0.5722,
      "step": 680
    },
    {
      "epoch": 7.58,
      "learning_rate": 8.148148148148148e-06,
      "loss": 0.5538,
      "step": 690
    },
    {
      "epoch": 7.69,
      "learning_rate": 7.777777777777777e-06,
      "loss": 0.5546,
      "step": 700
    },
    {
      "epoch": 7.69,
      "eval_loss": 1.5901862382888794,
      "eval_runtime": 52.5596,
      "eval_samples_per_second": 5.099,
      "eval_steps_per_second": 0.095,
      "step": 700
    },
    {
      "epoch": 7.8,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.546,
      "step": 710
    },
    {
      "epoch": 7.91,
      "learning_rate": 7.037037037037037e-06,
      "loss": 0.5322,
      "step": 720
    },
    {
      "epoch": 8.02,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.588,
      "step": 730
    },
    {
      "epoch": 8.13,
      "learning_rate": 6.296296296296296e-06,
      "loss": 0.4936,
      "step": 740
    },
    {
      "epoch": 8.24,
      "learning_rate": 5.925925925925926e-06,
      "loss": 0.4625,
      "step": 750
    },
    {
      "epoch": 8.35,
      "learning_rate": 5.555555555555555e-06,
      "loss": 0.4577,
      "step": 760
    },
    {
      "epoch": 8.46,
      "learning_rate": 5.185185185185185e-06,
      "loss": 0.4619,
      "step": 770
    },
    {
      "epoch": 8.57,
      "learning_rate": 4.814814814814815e-06,
      "loss": 0.5216,
      "step": 780
    },
    {
      "epoch": 8.68,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.4771,
      "step": 790
    },
    {
      "epoch": 8.79,
      "learning_rate": 4.074074074074074e-06,
      "loss": 0.452,
      "step": 800
    },
    {
      "epoch": 8.79,
      "eval_loss": 1.4902839660644531,
      "eval_runtime": 54.4822,
      "eval_samples_per_second": 4.919,
      "eval_steps_per_second": 0.092,
      "step": 800
    },
    {
      "epoch": 8.9,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.4645,
      "step": 810
    },
    {
      "epoch": 9.01,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.4459,
      "step": 820
    },
    {
      "epoch": 9.12,
      "learning_rate": 2.962962962962963e-06,
      "loss": 0.4157,
      "step": 830
    },
    {
      "epoch": 9.23,
      "learning_rate": 2.5925925925925925e-06,
      "loss": 0.3948,
      "step": 840
    },
    {
      "epoch": 9.34,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.4186,
      "step": 850
    },
    {
      "epoch": 9.45,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 0.3841,
      "step": 860
    },
    {
      "epoch": 9.56,
      "learning_rate": 1.4814814814814815e-06,
      "loss": 0.4086,
      "step": 870
    },
    {
      "epoch": 9.67,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.4018,
      "step": 880
    },
    {
      "epoch": 9.78,
      "learning_rate": 7.407407407407407e-07,
      "loss": 0.405,
      "step": 890
    }
  ],
  "max_steps": 910,
  "num_train_epochs": 10,
  "total_flos": 4163675271142080.0,
  "trial_name": null,
  "trial_params": null
}