{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0169491525423728,
  "eval_steps": 500,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.6073,
      "step": 1
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.701,
      "step": 2
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.4e-05,
      "loss": 1.6232,
      "step": 3
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.705,
      "step": 4
    },
    {
      "epoch": 0.05,
      "learning_rate": 4e-05,
      "loss": 1.6552,
      "step": 5
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.8e-05,
      "loss": 1.7611,
      "step": 6
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.6e-05,
      "loss": 1.6008,
      "step": 7
    },
    {
      "epoch": 0.08,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.6468,
      "step": 8
    },
    {
      "epoch": 0.09,
      "learning_rate": 7.2e-05,
      "loss": 1.6148,
      "step": 9
    },
    {
      "epoch": 0.1,
      "learning_rate": 8e-05,
      "loss": 1.6125,
      "step": 10
    },
    {
      "epoch": 0.11,
      "learning_rate": 7.999779207981935e-05,
      "loss": 1.6532,
      "step": 11
    },
    {
      "epoch": 0.12,
      "learning_rate": 7.999116856302298e-05,
      "loss": 1.528,
      "step": 12
    },
    {
      "epoch": 0.13,
      "learning_rate": 7.998013018082072e-05,
      "loss": 1.5758,
      "step": 13
    },
    {
      "epoch": 0.14,
      "learning_rate": 7.996467815180588e-05,
      "loss": 1.6549,
      "step": 14
    },
    {
      "epoch": 0.15,
      "learning_rate": 7.994481418182082e-05,
      "loss": 1.3725,
      "step": 15
    },
    {
      "epoch": 0.15,
      "learning_rate": 7.992054046376854e-05,
      "loss": 1.6324,
      "step": 16
    },
    {
      "epoch": 0.16,
      "learning_rate": 7.989185967737066e-05,
      "loss": 1.5984,
      "step": 17
    },
    {
      "epoch": 0.17,
      "learning_rate": 7.985877498887149e-05,
      "loss": 1.7095,
      "step": 18
    },
    {
      "epoch": 0.18,
      "learning_rate": 7.982129005068865e-05,
      "loss": 1.4843,
      "step": 19
    },
    {
      "epoch": 0.19,
      "learning_rate": 7.977940900100967e-05,
      "loss": 1.6701,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 7.973313646333532e-05,
      "loss": 1.6216,
      "step": 21
    },
    {
      "epoch": 0.21,
      "learning_rate": 7.968247754596908e-05,
      "loss": 1.6616,
      "step": 22
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.962743784145323e-05,
      "loss": 1.5737,
      "step": 23
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.956802342595152e-05,
      "loss": 1.5716,
      "step": 24
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.950424085857827e-05,
      "loss": 1.4727,
      "step": 25
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.943609718067437e-05,
      "loss": 1.676,
      "step": 26
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.936359991502993e-05,
      "loss": 1.5953,
      "step": 27
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.92867570650537e-05,
      "loss": 1.5233,
      "step": 28
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.920557711388967e-05,
      "loss": 1.7087,
      "step": 29
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.912006902348045e-05,
      "loss": 1.6314,
      "step": 30
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.903024223357797e-05,
      "loss": 1.5763,
      "step": 31
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.893610666070134e-05,
      "loss": 1.7077,
      "step": 32
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.883767269704209e-05,
      "loss": 1.5335,
      "step": 33
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.873495120931697e-05,
      "loss": 1.6053,
      "step": 34
    },
    {
      "epoch": 0.34,
      "learning_rate": 7.86279535375683e-05,
      "loss": 1.3602,
      "step": 35
    },
    {
      "epoch": 0.35,
      "learning_rate": 7.851669149391198e-05,
      "loss": 1.3493,
      "step": 36
    },
    {
      "epoch": 0.36,
      "learning_rate": 7.84011773612336e-05,
      "loss": 1.5459,
      "step": 37
    },
    {
      "epoch": 0.37,
      "learning_rate": 7.828142389183239e-05,
      "loss": 1.5918,
      "step": 38
    },
    {
      "epoch": 0.38,
      "learning_rate": 7.815744430601344e-05,
      "loss": 1.4649,
      "step": 39
    },
    {
      "epoch": 0.39,
      "learning_rate": 7.802925229062823e-05,
      "loss": 1.5555,
      "step": 40
    },
    {
      "epoch": 0.4,
      "learning_rate": 7.789686199756365e-05,
      "loss": 1.6162,
      "step": 41
    },
    {
      "epoch": 0.41,
      "learning_rate": 7.776028804217968e-05,
      "loss": 1.5508,
      "step": 42
    },
    {
      "epoch": 0.42,
      "learning_rate": 7.761954550169593e-05,
      "loss": 1.7089,
      "step": 43
    },
    {
      "epoch": 0.43,
      "learning_rate": 7.74746499135272e-05,
      "loss": 1.6471,
      "step": 44
    },
    {
      "epoch": 0.44,
      "learning_rate": 7.732561727356811e-05,
      "loss": 1.5361,
      "step": 45
    },
    {
      "epoch": 0.45,
      "learning_rate": 7.717246403442735e-05,
      "loss": 1.4333,
      "step": 46
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.701520710361129e-05,
      "loss": 1.5406,
      "step": 47
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.685386384165748e-05,
      "loss": 1.6056,
      "step": 48
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.668845206021812e-05,
      "loss": 1.5945,
      "step": 49
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.651899002009375e-05,
      "loss": 1.6727,
      "step": 50
    },
    {
      "epoch": 0.49,
      "learning_rate": 7.634549642921725e-05,
      "loss": 1.6352,
      "step": 51
    },
    {
      "epoch": 0.5,
      "learning_rate": 7.616799044058867e-05,
      "loss": 1.5127,
      "step": 52
    },
    {
      "epoch": 0.51,
      "learning_rate": 7.598649165016073e-05,
      "loss": 1.5696,
      "step": 53
    },
    {
      "epoch": 0.52,
      "learning_rate": 7.58010200946755e-05,
      "loss": 1.5987,
      "step": 54
    },
    {
      "epoch": 0.53,
      "learning_rate": 7.561159624945257e-05,
      "loss": 1.5007,
      "step": 55
    },
    {
      "epoch": 0.54,
      "learning_rate": 7.541824102612839e-05,
      "loss": 1.697,
      "step": 56
    },
    {
      "epoch": 0.55,
      "learning_rate": 7.5220975770348e-05,
      "loss": 1.5062,
      "step": 57
    },
    {
      "epoch": 0.56,
      "learning_rate": 7.501982225940833e-05,
      "loss": 1.6713,
      "step": 58
    },
    {
      "epoch": 0.57,
      "learning_rate": 7.48148026998542e-05,
      "loss": 1.5913,
      "step": 59
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.460593972502674e-05,
      "loss": 1.5841,
      "step": 60
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.439325639256483e-05,
      "loss": 1.5459,
      "step": 61
    },
    {
      "epoch": 0.6,
      "learning_rate": 7.417677618185955e-05,
      "loss": 1.5911,
      "step": 62
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.39565229914622e-05,
      "loss": 1.5862,
      "step": 63
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.373252113644596e-05,
      "loss": 1.6381,
      "step": 64
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.350479534572166e-05,
      "loss": 1.5476,
      "step": 65
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.327337075930775e-05,
      "loss": 1.579,
      "step": 66
    },
    {
      "epoch": 0.65,
      "learning_rate": 7.303827292555495e-05,
      "loss": 1.6105,
      "step": 67
    },
    {
      "epoch": 0.66,
      "learning_rate": 7.279952779832584e-05,
      "loss": 1.5728,
      "step": 68
    },
    {
      "epoch": 0.67,
      "learning_rate": 7.255716173412966e-05,
      "loss": 1.6509,
      "step": 69
    },
    {
      "epoch": 0.68,
      "learning_rate": 7.23112014892126e-05,
      "loss": 1.5586,
      "step": 70
    },
    {
      "epoch": 0.69,
      "learning_rate": 7.20616742166041e-05,
      "loss": 1.3865,
      "step": 71
    },
    {
      "epoch": 0.7,
      "learning_rate": 7.180860746311917e-05,
      "loss": 1.5214,
      "step": 72
    },
    {
      "epoch": 0.71,
      "learning_rate": 7.155202916631743e-05,
      "loss": 1.5699,
      "step": 73
    },
    {
      "epoch": 0.72,
      "learning_rate": 7.129196765141886e-05,
      "loss": 1.388,
      "step": 74
    },
    {
      "epoch": 0.73,
      "learning_rate": 7.10284516281768e-05,
      "loss": 1.5735,
      "step": 75
    },
    {
      "epoch": 0.74,
      "learning_rate": 7.076151018770854e-05,
      "loss": 1.6245,
      "step": 76
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.049117279928374e-05,
      "loss": 1.6489,
      "step": 77
    },
    {
      "epoch": 0.76,
      "learning_rate": 7.021746930707117e-05,
      "loss": 1.5712,
      "step": 78
    },
    {
      "epoch": 0.77,
      "learning_rate": 6.994042992684406e-05,
      "loss": 1.6359,
      "step": 79
    },
    {
      "epoch": 0.77,
      "learning_rate": 6.966008524264429e-05,
      "loss": 1.6452,
      "step": 80
    },
    {
      "epoch": 0.78,
      "learning_rate": 6.937646620340618e-05,
      "loss": 1.5655,
      "step": 81
    },
    {
      "epoch": 0.79,
      "learning_rate": 6.908960411953973e-05,
      "loss": 1.5791,
      "step": 82
    },
    {
      "epoch": 0.8,
      "learning_rate": 6.879953065947416e-05,
      "loss": 1.685,
      "step": 83
    },
    {
      "epoch": 0.81,
      "learning_rate": 6.850627784616178e-05,
      "loss": 1.5755,
      "step": 84
    },
    {
      "epoch": 0.82,
      "learning_rate": 6.82098780535428e-05,
      "loss": 1.5878,
      "step": 85
    },
    {
      "epoch": 0.83,
      "learning_rate": 6.791036400297142e-05,
      "loss": 1.6273,
      "step": 86
    },
    {
      "epoch": 0.84,
      "learning_rate": 6.760776875960347e-05,
      "loss": 1.625,
      "step": 87
    },
    {
      "epoch": 0.85,
      "learning_rate": 6.730212572874618e-05,
      "loss": 1.6891,
      "step": 88
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.699346865217031e-05,
      "loss": 1.5593,
      "step": 89
    },
    {
      "epoch": 0.87,
      "learning_rate": 6.668183160438531e-05,
      "loss": 1.6518,
      "step": 90
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.636724898887751e-05,
      "loss": 1.6314,
      "step": 91
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.604975553431219e-05,
      "loss": 1.6267,
      "step": 92
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.572938629069959e-05,
      "loss": 1.5465,
      "step": 93
    },
    {
      "epoch": 0.91,
      "learning_rate": 6.540617662552565e-05,
      "loss": 1.6302,
      "step": 94
    },
    {
      "epoch": 0.92,
      "learning_rate": 6.508016221984747e-05,
      "loss": 1.5039,
      "step": 95
    },
    {
      "epoch": 0.93,
      "learning_rate": 6.475137906435435e-05,
      "loss": 1.6879,
      "step": 96
    },
    {
      "epoch": 0.94,
      "learning_rate": 6.441986345539446e-05,
      "loss": 1.5822,
      "step": 97
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.408565199096798e-05,
      "loss": 1.5612,
      "step": 98
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.374878156668676e-05,
      "loss": 1.6022,
      "step": 99
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.340928937170118e-05,
      "loss": 1.6292,
      "step": 100
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.30672128845947e-05,
      "loss": 1.6783,
      "step": 101
    },
    {
      "epoch": 0.99,
      "learning_rate": 6.272258986924624e-05,
      "loss": 1.5995,
      "step": 102
    },
    {
      "epoch": 1.0,
      "learning_rate": 6.237545837066133e-05,
      "loss": 1.5811,
      "step": 103
    },
    {
      "epoch": 1.01,
      "learning_rate": 6.202585671077204e-05,
      "loss": 1.5029,
      "step": 104
    },
    {
      "epoch": 1.02,
      "learning_rate": 6.167382348420637e-05,
      "loss": 1.5067,
      "step": 105
    }
  ],
  "logging_steps": 1,
  "max_steps": 309,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 7.038225052524872e+17,
  "trial_name": null,
  "trial_params": null
}