{
  "best_metric": 1.6501820087432861,
  "best_model_checkpoint": "/mnt/bn/qingyi-bn-lq/llama/saved_bloominstinwild-belle1.5m/checkpoint-1400",
  "epoch": 0.9000321440051431,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.3902,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00011999999999999999,
      "loss": 2.1808,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.9937,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00023999999999999998,
      "loss": 1.8967,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 1.8529,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002958762886597938,
      "loss": 1.8004,
      "step": 120
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002917525773195876,
      "loss": 1.785,
      "step": 140
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002876288659793814,
      "loss": 1.7755,
      "step": 160
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00028350515463917525,
      "loss": 1.7554,
      "step": 180
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0002793814432989691,
      "loss": 1.7534,
      "step": 200
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.7528996467590332,
      "eval_runtime": 17.6175,
      "eval_samples_per_second": 113.524,
      "eval_steps_per_second": 1.816,
      "step": 200
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00027525773195876286,
      "loss": 1.7375,
      "step": 220
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0002711340206185567,
      "loss": 1.7331,
      "step": 240
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00026701030927835047,
      "loss": 1.7248,
      "step": 260
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002628865979381443,
      "loss": 1.7282,
      "step": 280
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00025876288659793813,
      "loss": 1.7167,
      "step": 300
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002546391752577319,
      "loss": 1.7215,
      "step": 320
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00025051546391752574,
      "loss": 1.7157,
      "step": 340
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0002463917525773196,
      "loss": 1.7146,
      "step": 360
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00024226804123711338,
      "loss": 1.6953,
      "step": 380
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00023814432989690718,
      "loss": 1.6951,
      "step": 400
    },
    {
      "epoch": 0.26,
      "eval_loss": 1.7059786319732666,
      "eval_runtime": 17.3801,
      "eval_samples_per_second": 115.074,
      "eval_steps_per_second": 1.841,
      "step": 400
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00023402061855670102,
      "loss": 1.6916,
      "step": 420
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00022989690721649485,
      "loss": 1.6893,
      "step": 440
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00022577319587628863,
      "loss": 1.6932,
      "step": 460
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00022164948453608246,
      "loss": 1.6913,
      "step": 480
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00021752577319587626,
      "loss": 1.6823,
      "step": 500
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002134020618556701,
      "loss": 1.6921,
      "step": 520
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0002092783505154639,
      "loss": 1.6759,
      "step": 540
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002051546391752577,
      "loss": 1.6758,
      "step": 560
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002010309278350515,
      "loss": 1.6732,
      "step": 580
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019690721649484534,
      "loss": 1.673,
      "step": 600
    },
    {
      "epoch": 0.39,
      "eval_loss": 1.6831790208816528,
      "eval_runtime": 17.4032,
      "eval_samples_per_second": 114.921,
      "eval_steps_per_second": 1.839,
      "step": 600
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019278350515463918,
      "loss": 1.6625,
      "step": 620
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00018865979381443298,
      "loss": 1.666,
      "step": 640
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00018453608247422679,
      "loss": 1.6662,
      "step": 660
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001804123711340206,
      "loss": 1.6692,
      "step": 680
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00017628865979381442,
      "loss": 1.6635,
      "step": 700
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00017216494845360823,
      "loss": 1.6685,
      "step": 720
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00016804123711340206,
      "loss": 1.6534,
      "step": 740
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00016391752577319584,
      "loss": 1.6627,
      "step": 760
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00015979381443298967,
      "loss": 1.6596,
      "step": 780
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001556701030927835,
      "loss": 1.6659,
      "step": 800
    },
    {
      "epoch": 0.51,
      "eval_loss": 1.6697583198547363,
      "eval_runtime": 17.3944,
      "eval_samples_per_second": 114.979,
      "eval_steps_per_second": 1.84,
      "step": 800
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001515463917525773,
      "loss": 1.6599,
      "step": 820
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001474226804123711,
      "loss": 1.6587,
      "step": 840
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00014329896907216494,
      "loss": 1.6586,
      "step": 860
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00013917525773195875,
      "loss": 1.6602,
      "step": 880
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00013505154639175258,
      "loss": 1.6513,
      "step": 900
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00013092783505154639,
      "loss": 1.6477,
      "step": 920
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001268041237113402,
      "loss": 1.6455,
      "step": 940
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.000122680412371134,
      "loss": 1.6543,
      "step": 960
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00011855670103092781,
      "loss": 1.6499,
      "step": 980
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00011443298969072163,
      "loss": 1.647,
      "step": 1000
    },
    {
      "epoch": 0.64,
      "eval_loss": 1.6601147651672363,
      "eval_runtime": 17.3892,
      "eval_samples_per_second": 115.014,
      "eval_steps_per_second": 1.84,
      "step": 1000
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00011030927835051547,
      "loss": 1.649,
      "step": 1020
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00010618556701030927,
      "loss": 1.6562,
      "step": 1040
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00010206185567010309,
      "loss": 1.6488,
      "step": 1060
    },
    {
      "epoch": 0.69,
      "learning_rate": 9.79381443298969e-05,
      "loss": 1.6453,
      "step": 1080
    },
    {
      "epoch": 0.71,
      "learning_rate": 9.381443298969071e-05,
      "loss": 1.6348,
      "step": 1100
    },
    {
      "epoch": 0.72,
      "learning_rate": 8.969072164948453e-05,
      "loss": 1.6453,
      "step": 1120
    },
    {
      "epoch": 0.73,
      "learning_rate": 8.556701030927834e-05,
      "loss": 1.6362,
      "step": 1140
    },
    {
      "epoch": 0.75,
      "learning_rate": 8.144329896907215e-05,
      "loss": 1.6417,
      "step": 1160
    },
    {
      "epoch": 0.76,
      "learning_rate": 7.731958762886596e-05,
      "loss": 1.6382,
      "step": 1180
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.319587628865979e-05,
      "loss": 1.6433,
      "step": 1200
    },
    {
      "epoch": 0.77,
      "eval_loss": 1.6533111333847046,
      "eval_runtime": 17.3863,
      "eval_samples_per_second": 115.033,
      "eval_steps_per_second": 1.841,
      "step": 1200
    },
    {
      "epoch": 0.78,
      "learning_rate": 6.90721649484536e-05,
      "loss": 1.6415,
      "step": 1220
    },
    {
      "epoch": 0.8,
      "learning_rate": 6.494845360824742e-05,
      "loss": 1.6459,
      "step": 1240
    },
    {
      "epoch": 0.81,
      "learning_rate": 6.0824742268041234e-05,
      "loss": 1.644,
      "step": 1260
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.6701030927835046e-05,
      "loss": 1.6472,
      "step": 1280
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.257731958762886e-05,
      "loss": 1.6368,
      "step": 1300
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.8453608247422676e-05,
      "loss": 1.6325,
      "step": 1320
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.4329896907216494e-05,
      "loss": 1.6354,
      "step": 1340
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.0206185567010306e-05,
      "loss": 1.6381,
      "step": 1360
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.608247422680412e-05,
      "loss": 1.6519,
      "step": 1380
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.1958762886597937e-05,
      "loss": 1.6492,
      "step": 1400
    },
    {
      "epoch": 0.9,
      "eval_loss": 1.6501820087432861,
      "eval_runtime": 17.3757,
      "eval_samples_per_second": 115.103,
      "eval_steps_per_second": 1.842,
      "step": 1400
    }
  ],
  "max_steps": 1555,
  "num_train_epochs": 1,
  "total_flos": 1.203777052717613e+19,
  "trial_name": null,
  "trial_params": null
}