{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 16.731555938720703,
      "learning_rate": 9.918367346938776e-06,
      "loss": 0.2616,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 10,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 18.564252853393555,
      "learning_rate": 9.836734693877552e-06,
      "loss": 0.1554,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 20,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 7.802953720092773,
      "learning_rate": 9.755102040816327e-06,
      "loss": 0.126,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 30,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 4.599184036254883,
      "learning_rate": 9.673469387755103e-06,
      "loss": 0.1103,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 40,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 6.734092712402344,
      "learning_rate": 9.591836734693878e-06,
      "loss": 0.1217,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 50,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 1.7976917028427124,
      "learning_rate": 9.510204081632653e-06,
      "loss": 0.08,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 60,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 4.0598835945129395,
      "learning_rate": 9.42857142857143e-06,
      "loss": 0.1023,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 70,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 2.0350396633148193,
      "learning_rate": 9.346938775510204e-06,
      "loss": 0.1128,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 80,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.3673469387755102,
      "grad_norm": 3.785065174102783,
      "learning_rate": 9.26530612244898e-06,
      "loss": 0.0842,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 90,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 1.9926950931549072,
      "learning_rate": 9.183673469387756e-06,
      "loss": 0.0728,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 100,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.4489795918367347,
      "grad_norm": 4.878537178039551,
      "learning_rate": 9.102040816326532e-06,
      "loss": 0.0692,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 110,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 2.5495357513427734,
      "learning_rate": 9.020408163265307e-06,
      "loss": 0.0691,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 120,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.5306122448979592,
      "grad_norm": 3.0813372135162354,
      "learning_rate": 8.938775510204082e-06,
      "loss": 0.0597,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 130,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.2760021686553955,
      "learning_rate": 8.857142857142858e-06,
      "loss": 0.0507,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 140,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 2.0892932415008545,
      "learning_rate": 8.775510204081633e-06,
      "loss": 0.0634,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 150,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 2.0191688537597656,
      "learning_rate": 8.69387755102041e-06,
      "loss": 0.0718,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 160,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.6938775510204082,
      "grad_norm": 2.4970450401306152,
      "learning_rate": 8.612244897959184e-06,
      "loss": 0.0753,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 170,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.7346938775510204,
      "grad_norm": 1.5428143739700317,
      "learning_rate": 8.530612244897961e-06,
      "loss": 0.0612,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 180,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.7755102040816326,
      "grad_norm": 3.6041452884674072,
      "learning_rate": 8.448979591836736e-06,
      "loss": 0.0573,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 190,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 1.0115529298782349,
      "learning_rate": 8.36734693877551e-06,
      "loss": 0.0631,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 200,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.8029147982597351,
      "learning_rate": 8.285714285714287e-06,
      "loss": 0.0643,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 210,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.8979591836734694,
      "grad_norm": 1.130996584892273,
      "learning_rate": 8.204081632653062e-06,
      "loss": 0.0608,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 220,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.9387755102040817,
      "grad_norm": 0.7962849140167236,
      "learning_rate": 8.122448979591837e-06,
      "loss": 0.0535,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 230,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 2.3987386226654053,
      "learning_rate": 8.040816326530613e-06,
      "loss": 0.0499,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 240,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": 1.084067463874817,
      "learning_rate": 7.959183673469388e-06,
      "loss": 0.0612,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 250,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.0612244897959184,
      "grad_norm": 3.247530460357666,
      "learning_rate": 7.877551020408164e-06,
      "loss": 0.055,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 260,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.1020408163265305,
      "grad_norm": 1.5961194038391113,
      "learning_rate": 7.79591836734694e-06,
      "loss": 0.0632,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 270,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.32916340231895447,
      "learning_rate": 7.714285714285716e-06,
      "loss": 0.0565,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 280,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.183673469387755,
      "grad_norm": 0.6009345054626465,
      "learning_rate": 7.63265306122449e-06,
      "loss": 0.0503,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 290,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": 9.806236267089844,
      "learning_rate": 7.551020408163265e-06,
      "loss": 0.0635,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 300,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.2653061224489797,
      "grad_norm": 1.231447696685791,
      "learning_rate": 7.469387755102041e-06,
      "loss": 0.0664,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 310,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.306122448979592,
      "grad_norm": 1.016727328300476,
      "learning_rate": 7.387755102040817e-06,
      "loss": 0.0502,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 320,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.346938775510204,
      "grad_norm": 0.7703081965446472,
      "learning_rate": 7.306122448979592e-06,
      "loss": 0.0599,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 330,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.3877551020408163,
      "grad_norm": 5.310096740722656,
      "learning_rate": 7.224489795918368e-06,
      "loss": 0.0541,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 340,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.1444560289382935,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 0.0493,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 350,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.469387755102041,
      "grad_norm": 3.1823084354400635,
      "learning_rate": 7.061224489795919e-06,
      "loss": 0.0459,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 360,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.510204081632653,
      "grad_norm": 1.1924108266830444,
      "learning_rate": 6.979591836734695e-06,
      "loss": 0.058,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 370,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.5510204081632653,
      "grad_norm": 3.677968740463257,
      "learning_rate": 6.8979591836734705e-06,
      "loss": 0.0468,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 380,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.5918367346938775,
      "grad_norm": 1.0082957744598389,
      "learning_rate": 6.816326530612245e-06,
      "loss": 0.0652,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 390,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": 0.6584922075271606,
      "learning_rate": 6.734693877551021e-06,
      "loss": 0.0605,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 400,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.6734693877551021,
      "grad_norm": 1.2264763116836548,
      "learning_rate": 6.653061224489797e-06,
      "loss": 0.0599,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 410,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.824320912361145,
      "learning_rate": 6.571428571428572e-06,
      "loss": 0.053,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 420,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.7551020408163265,
      "grad_norm": 0.24405838549137115,
      "learning_rate": 6.489795918367348e-06,
      "loss": 0.067,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 430,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.7959183673469388,
      "grad_norm": 1.0410544872283936,
      "learning_rate": 6.408163265306124e-06,
      "loss": 0.06,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 440,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.836734693877551,
      "grad_norm": 0.39765527844429016,
      "learning_rate": 6.326530612244899e-06,
      "loss": 0.043,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 450,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.8775510204081631,
      "grad_norm": 0.29981690645217896,
      "learning_rate": 6.244897959183675e-06,
      "loss": 0.0533,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 460,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.9183673469387754,
      "grad_norm": 0.6634105443954468,
      "learning_rate": 6.163265306122449e-06,
      "loss": 0.0428,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 470,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 1.9591836734693877,
      "grad_norm": 0.2060549110174179,
      "learning_rate": 6.0816326530612245e-06,
      "loss": 0.0505,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 480,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.0800402164459229,
      "learning_rate": 6e-06,
      "loss": 0.0647,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 490,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.0408163265306123,
      "grad_norm": 0.6078592538833618,
      "learning_rate": 5.918367346938776e-06,
      "loss": 0.0596,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 500,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.0816326530612246,
      "grad_norm": 0.6262472867965698,
      "learning_rate": 5.8367346938775515e-06,
      "loss": 0.0495,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 510,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.122448979591837,
      "grad_norm": 1.4308090209960938,
      "learning_rate": 5.755102040816327e-06,
      "loss": 0.0461,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 520,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.163265306122449,
      "grad_norm": 0.8761769533157349,
      "learning_rate": 5.673469387755103e-06,
      "loss": 0.0626,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 530,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.204081632653061,
      "grad_norm": 0.6150110363960266,
      "learning_rate": 5.591836734693878e-06,
      "loss": 0.0576,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 540,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.2448979591836733,
      "grad_norm": 9.280069351196289,
      "learning_rate": 5.510204081632653e-06,
      "loss": 0.0634,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 550,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 2.136209726333618,
      "learning_rate": 5.428571428571429e-06,
      "loss": 0.0579,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 560,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.326530612244898,
      "grad_norm": 0.9547491073608398,
      "learning_rate": 5.3469387755102045e-06,
      "loss": 0.0589,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 570,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.36734693877551,
      "grad_norm": 2.1748363971710205,
      "learning_rate": 5.26530612244898e-06,
      "loss": 0.0672,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 580,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.4081632653061225,
      "grad_norm": 0.9653811454772949,
      "learning_rate": 5.183673469387756e-06,
      "loss": 0.0536,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 590,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.4489795918367347,
      "grad_norm": 0.7852123379707336,
      "learning_rate": 5.1020408163265315e-06,
      "loss": 0.0443,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 600,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.489795918367347,
      "grad_norm": 0.7405697107315063,
      "learning_rate": 5.020408163265307e-06,
      "loss": 0.041,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 610,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.5306122448979593,
      "grad_norm": 0.7166327834129333,
      "learning_rate": 4.938775510204082e-06,
      "loss": 0.0431,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 620,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.5675875544548035,
      "learning_rate": 4.857142857142858e-06,
      "loss": 0.0807,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 630,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.612244897959184,
      "grad_norm": 0.954290509223938,
      "learning_rate": 4.775510204081633e-06,
      "loss": 0.0492,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 640,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.6530612244897958,
      "grad_norm": 0.9061315655708313,
      "learning_rate": 4.693877551020409e-06,
      "loss": 0.0472,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 650,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.693877551020408,
      "grad_norm": 0.7333698868751526,
      "learning_rate": 4.612244897959184e-06,
      "loss": 0.0474,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 660,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.7346938775510203,
      "grad_norm": 1.7820810079574585,
      "learning_rate": 4.530612244897959e-06,
      "loss": 0.0869,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 670,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.7755102040816326,
      "grad_norm": 1.3184058666229248,
      "learning_rate": 4.448979591836735e-06,
      "loss": 0.0494,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 680,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.816326530612245,
      "grad_norm": 0.4212433397769928,
      "learning_rate": 4.367346938775511e-06,
      "loss": 0.0445,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 690,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.39547938108444214,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 0.0429,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 700,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.8979591836734695,
      "grad_norm": 1.0822113752365112,
      "learning_rate": 4.204081632653061e-06,
      "loss": 0.0549,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 710,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.938775510204082,
      "grad_norm": 1.0838605165481567,
      "learning_rate": 4.122448979591837e-06,
      "loss": 0.0582,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 720,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 2.979591836734694,
      "grad_norm": 0.2726249098777771,
      "learning_rate": 4.040816326530612e-06,
      "loss": 0.0341,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 730,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.020408163265306,
      "grad_norm": 0.836703360080719,
      "learning_rate": 3.959183673469388e-06,
      "loss": 0.053,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 740,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.061224489795918,
      "grad_norm": 0.6878814697265625,
      "learning_rate": 3.877551020408164e-06,
      "loss": 0.0618,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 750,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.1020408163265305,
      "grad_norm": 1.3712306022644043,
      "learning_rate": 3.795918367346939e-06,
      "loss": 0.0527,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 760,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.142857142857143,
      "grad_norm": 2.1615536212921143,
      "learning_rate": 3.7142857142857146e-06,
      "loss": 0.069,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 770,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.183673469387755,
      "grad_norm": 0.45463302731513977,
      "learning_rate": 3.6326530612244903e-06,
      "loss": 0.064,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 780,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.2244897959183674,
      "grad_norm": 0.40240758657455444,
      "learning_rate": 3.5510204081632655e-06,
      "loss": 0.0528,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 790,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.2653061224489797,
      "grad_norm": 0.5408643484115601,
      "learning_rate": 3.469387755102041e-06,
      "loss": 0.0433,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 800,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.306122448979592,
      "grad_norm": 0.6606118679046631,
      "learning_rate": 3.3877551020408168e-06,
      "loss": 0.0548,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 810,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.3469387755102042,
      "grad_norm": 0.89394211769104,
      "learning_rate": 3.3061224489795924e-06,
      "loss": 0.0448,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 820,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.387755102040816,
      "grad_norm": 0.3227229416370392,
      "learning_rate": 3.2244897959183672e-06,
      "loss": 0.0491,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 830,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.4285714285714284,
      "grad_norm": 0.928611159324646,
      "learning_rate": 3.142857142857143e-06,
      "loss": 0.0523,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 840,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.4693877551020407,
      "grad_norm": 0.6023752093315125,
      "learning_rate": 3.0612244897959185e-06,
      "loss": 0.0813,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 850,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.510204081632653,
      "grad_norm": 1.1742885112762451,
      "learning_rate": 2.979591836734694e-06,
      "loss": 0.0451,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 860,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.5510204081632653,
      "grad_norm": 0.21970601379871368,
      "learning_rate": 2.8979591836734694e-06,
      "loss": 0.0644,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 870,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.5918367346938775,
      "grad_norm": 1.2270339727401733,
      "learning_rate": 2.816326530612245e-06,
      "loss": 0.044,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 880,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.63265306122449,
      "grad_norm": 0.15171077847480774,
      "learning_rate": 2.7346938775510207e-06,
      "loss": 0.0291,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 890,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.673469387755102,
      "grad_norm": 2.9102306365966797,
      "learning_rate": 2.6530612244897964e-06,
      "loss": 0.0516,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 900,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.7142857142857144,
      "grad_norm": 0.6113564968109131,
      "learning_rate": 2.571428571428571e-06,
      "loss": 0.061,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 910,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.7551020408163263,
      "grad_norm": 0.19307516515254974,
      "learning_rate": 2.489795918367347e-06,
      "loss": 0.0539,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 920,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.795918367346939,
      "grad_norm": 0.38657116889953613,
      "learning_rate": 2.4081632653061225e-06,
      "loss": 0.05,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 930,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.836734693877551,
      "grad_norm": 0.9545940160751343,
      "learning_rate": 2.326530612244898e-06,
      "loss": 0.0481,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 940,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.877551020408163,
      "grad_norm": 1.3555389642715454,
      "learning_rate": 2.244897959183674e-06,
      "loss": 0.0596,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 950,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.9183673469387754,
      "grad_norm": 0.3931931257247925,
      "learning_rate": 2.1632653061224495e-06,
      "loss": 0.0498,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 960,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 3.9591836734693877,
      "grad_norm": 0.6945517063140869,
      "learning_rate": 2.0816326530612247e-06,
      "loss": 0.0734,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 970,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0659183263778687,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0707,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 980,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.040816326530612,
      "grad_norm": 0.8017714023590088,
      "learning_rate": 1.9183673469387756e-06,
      "loss": 0.0476,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 990,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.081632653061225,
      "grad_norm": 1.1733373403549194,
      "learning_rate": 1.8367346938775512e-06,
      "loss": 0.0617,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1000,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.122448979591836,
      "grad_norm": 0.6048600077629089,
      "learning_rate": 1.7551020408163267e-06,
      "loss": 0.0625,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1010,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.163265306122449,
      "grad_norm": 1.096007227897644,
      "learning_rate": 1.6734693877551023e-06,
      "loss": 0.0407,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1020,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.204081632653061,
      "grad_norm": 4.377923965454102,
      "learning_rate": 1.5918367346938775e-06,
      "loss": 0.0528,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1030,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.244897959183674,
      "grad_norm": 0.7295175194740295,
      "learning_rate": 1.5102040816326532e-06,
      "loss": 0.04,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1040,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 0.5129045248031616,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 0.0493,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1050,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.326530612244898,
      "grad_norm": 0.505799412727356,
      "learning_rate": 1.3469387755102043e-06,
      "loss": 0.046,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1060,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.36734693877551,
      "grad_norm": 0.8460046052932739,
      "learning_rate": 1.2653061224489795e-06,
      "loss": 0.0483,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1070,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.408163265306122,
      "grad_norm": 0.5636487603187561,
      "learning_rate": 1.1836734693877552e-06,
      "loss": 0.0523,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1080,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.448979591836735,
      "grad_norm": 0.6893309354782104,
      "learning_rate": 1.1020408163265308e-06,
      "loss": 0.0505,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1090,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.489795918367347,
      "grad_norm": 0.6645925045013428,
      "learning_rate": 1.0204081632653063e-06,
      "loss": 0.0361,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1100,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.530612244897959,
      "grad_norm": 0.14709816873073578,
      "learning_rate": 9.387755102040817e-07,
      "loss": 0.0458,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1110,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 0.8794461488723755,
      "learning_rate": 8.571428571428572e-07,
      "loss": 0.0414,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1120,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.612244897959184,
      "grad_norm": 1.345910906791687,
      "learning_rate": 7.755102040816327e-07,
      "loss": 0.0526,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1130,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.653061224489796,
      "grad_norm": 0.5657418370246887,
      "learning_rate": 6.938775510204082e-07,
      "loss": 0.0721,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1140,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.6938775510204085,
      "grad_norm": 2.0943238735198975,
      "learning_rate": 6.122448979591837e-07,
      "loss": 0.0515,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1150,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.73469387755102,
      "grad_norm": 3.1750009059906006,
      "learning_rate": 5.306122448979592e-07,
      "loss": 0.0607,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1160,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.775510204081632,
      "grad_norm": 0.8910292387008667,
      "learning_rate": 4.489795918367347e-07,
      "loss": 0.054,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1170,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.816326530612245,
      "grad_norm": 0.9796111583709717,
      "learning_rate": 3.6734693877551025e-07,
      "loss": 0.0432,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1180,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.857142857142857,
      "grad_norm": 1.7865172624588013,
      "learning_rate": 2.8571428571428575e-07,
      "loss": 0.0549,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1190,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.8979591836734695,
      "grad_norm": 0.7347144484519958,
      "learning_rate": 2.0408163265306121e-07,
      "loss": 0.0711,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1200,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.938775510204081,
      "grad_norm": 1.210486888885498,
      "learning_rate": 1.2244897959183673e-07,
      "loss": 0.0652,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1210,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 4.979591836734694,
      "grad_norm": 1.2078640460968018,
      "learning_rate": 4.0816326530612253e-08,
      "loss": 0.0414,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1220,
      "total_memory_available (GB)": 94.62
    },
    {
      "epoch": 5.0,
      "max_memory_allocated (GB)": 57.18,
      "memory_allocated (GB)": 50.57,
      "step": 1225,
      "total_flos": 3.0598946525952e+16,
      "total_memory_available (GB)": 94.62,
      "train_loss": 0.06072675045655698,
      "train_runtime": 1077.821,
      "train_samples_per_second": 52.682,
      "train_steps_per_second": 1.318
    }
  ],
  "logging_steps": 10,
  "max_steps": 1225,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0598946525952e+16,
  "train_batch_size": 40,
  "trial_name": null,
  "trial_params": null
}