{
  "best_metric": 7.262838840484619,
  "best_model_checkpoint": "sa_bert_12_layer_model_complete_training_new/checkpoint-30000",
  "epoch": 1.5053853884470856,
  "global_step": 137809,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0006747425010840046,
      "loss": 7.3869,
      "step": 500
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007499999999999999,
      "loss": 7.2989,
      "step": 1000
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007940228147639202,
      "loss": 7.2938,
      "step": 1500
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0008252574989159952,
      "loss": 7.2878,
      "step": 2000
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0008494850021680092,
      "loss": 7.2873,
      "step": 2500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0008692803136799154,
      "loss": 7.2802,
      "step": 3000
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0008860170110875688,
      "loss": 7.2848,
      "step": 3500
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0009005149978319905,
      "loss": 7.2802,
      "step": 4000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009133031284438358,
      "loss": 7.2798,
      "step": 4500
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0009247425010840047,
      "loss": 7.2859,
      "step": 5000
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0009350906723735609,
      "loss": 7.2756,
      "step": 5500
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009445378125959107,
      "loss": 7.2844,
      "step": 6000
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0009532283391607137,
      "loss": 7.2735,
      "step": 6500
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000961274510003564,
      "loss": 7.2741,
      "step": 7000
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000968765315847925,
      "loss": 7.2792,
      "step": 7500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0009757724967479857,
      "loss": 7.2781,
      "step": 8000
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.000982354731428573,
      "loss": 7.2829,
      "step": 8500
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.000988560627359831,
      "loss": 7.2828,
      "step": 9000
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0009944309013222117,
      "loss": 7.2764,
      "step": 9500
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0009999999999999998,
      "loss": 7.2755,
      "step": 10000
    },
    {
      "epoch": 0.11,
      "eval_accuracy": 0.046582492639500865,
      "eval_loss": 7.283848762512207,
      "eval_runtime": 1229.5034,
      "eval_samples_per_second": 250.797,
      "eval_steps_per_second": 3.919,
      "step": 10000
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0009988854641293666,
      "loss": 7.2801,
      "step": 10500
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0009977686947199142,
      "loss": 7.2777,
      "step": 11000
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0009966519253104618,
      "loss": 7.2715,
      "step": 11500
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0009955351559010096,
      "loss": 7.2707,
      "step": 12000
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0009944183864915572,
      "loss": 7.2781,
      "step": 12500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0009933016170821049,
      "loss": 7.2767,
      "step": 13000
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0009921848476726527,
      "loss": 7.2771,
      "step": 13500
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0009910680782632003,
      "loss": 7.532,
      "step": 14000
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.000989951308853748,
      "loss": 7.3036,
      "step": 14500
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0009888345394442955,
      "loss": 7.2904,
      "step": 15000
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0009877177700348431,
      "loss": 7.2812,
      "step": 15500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.000986601000625391,
      "loss": 7.2774,
      "step": 16000
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0009854842312159386,
      "loss": 7.2719,
      "step": 16500
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0009843674618064862,
      "loss": 7.2781,
      "step": 17000
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000983250692397034,
      "loss": 7.2725,
      "step": 17500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0009821339229875816,
      "loss": 7.2695,
      "step": 18000
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0009810171535781292,
      "loss": 7.27,
      "step": 18500
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0009799003841686768,
      "loss": 7.2668,
      "step": 19000
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0009787858482980434,
      "loss": 7.2728,
      "step": 19500
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0009776690788885912,
      "loss": 7.2773,
      "step": 20000
    },
    {
      "epoch": 0.22,
      "eval_accuracy": 0.046564609874152695,
      "eval_loss": 7.270238876342773,
      "eval_runtime": 1234.0943,
      "eval_samples_per_second": 249.864,
      "eval_steps_per_second": 3.905,
      "step": 20000
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0009765523094791387,
      "loss": 7.2689,
      "step": 20500
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0009754355400696864,
      "loss": 7.2728,
      "step": 21000
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0009743187706602341,
      "loss": 7.2687,
      "step": 21500
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0009732020012507818,
      "loss": 7.2691,
      "step": 22000
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0009720852318413295,
      "loss": 7.2721,
      "step": 22500
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0009709684624318771,
      "loss": 7.2698,
      "step": 23000
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0009698516930224247,
      "loss": 7.2707,
      "step": 23500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0009696596086839989,
      "loss": 7.3243,
      "step": 24000
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0009689940141159654,
      "loss": 7.2782,
      "step": 24500
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0009680916644331279,
      "loss": 7.2709,
      "step": 25000
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0009673791655498972,
      "loss": 7.2685,
      "step": 25500
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0009672473867595819,
      "loss": 7.2762,
      "step": 26000
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0009671647458232824,
      "loss": 7.2719,
      "step": 26500
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0009670687036540695,
      "loss": 7.2734,
      "step": 27000
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0009669905297954079,
      "loss": 7.2699,
      "step": 27500
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0009669503260966675,
      "loss": 7.2653,
      "step": 28000
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0009668877870097382,
      "loss": 7.2672,
      "step": 28500
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000966543822031627,
      "loss": 7.2607,
      "step": 29000
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.000966400875547217,
      "loss": 7.2639,
      "step": 29500
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0009663964084695792,
      "loss": 7.2658,
      "step": 30000
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.048081692349897294,
      "eval_loss": 7.262838840484619,
      "eval_runtime": 1234.0768,
      "eval_samples_per_second": 249.868,
      "eval_steps_per_second": 3.905,
      "step": 30000
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0009663964084695792,
      "loss": 7.2634,
      "step": 30500
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0009663941749307603,
      "loss": 7.2669,
      "step": 31000
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0009663897078531225,
      "loss": 7.2637,
      "step": 31500
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0009663785401590279,
      "loss": 7.2632,
      "step": 32000
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0009663160010720986,
      "loss": 7.2636,
      "step": 32500
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0009662043241311535,
      "loss": 7.2663,
      "step": 33000
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0009662020905923345,
      "loss": 7.2693,
      "step": 33500
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0009662020905923345,
      "loss": 7.2674,
      "step": 34000
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0009662020905923345,
      "loss": 7.2664,
      "step": 34500
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0009661998570535157,
      "loss": 7.2685,
      "step": 35000
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009661998570535157,
      "loss": 7.2706,
      "step": 35500
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0009661998570535157,
      "loss": 7.2766,
      "step": 36000
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2804,
      "step": 36500
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.302,
      "step": 37000
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2966,
      "step": 37500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2916,
      "step": 38000
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3052,
      "step": 38500
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2999,
      "step": 39000
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3014,
      "step": 39500
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2999,
      "step": 40000
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.046922356759428,
      "eval_loss": 7.3363776206970215,
      "eval_runtime": 1238.125,
      "eval_samples_per_second": 249.051,
      "eval_steps_per_second": 3.892,
      "step": 40000
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2988,
      "step": 40500
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3,
      "step": 41000
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3049,
      "step": 41500
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2998,
      "step": 42000
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2994,
      "step": 42500
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2911,
      "step": 43000
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3037,
      "step": 43500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3031,
      "step": 44000
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3008,
      "step": 44500
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2975,
      "step": 45000
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2991,
      "step": 45500
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2971,
      "step": 46000
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3002,
      "step": 46500
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2979,
      "step": 47000
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3029,
      "step": 47500
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.301,
      "step": 48000
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2994,
      "step": 48500
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3002,
      "step": 49000
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3048,
      "step": 49500
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3,
      "step": 50000
    },
    {
      "epoch": 0.55,
      "eval_accuracy": 0.046966281034843266,
      "eval_loss": 7.338123798370361,
      "eval_runtime": 1236.7304,
      "eval_samples_per_second": 249.332,
      "eval_steps_per_second": 3.897,
      "step": 50000
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2977,
      "step": 50500
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3051,
      "step": 51000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3026,
      "step": 51500
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3036,
      "step": 52000
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.304,
      "step": 52500
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2983,
      "step": 53000
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2994,
      "step": 53500
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.2966,
      "step": 54000
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009661976235146967,
      "loss": 7.3054,
      "step": 54500
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0009661953899758778,
      "loss": 7.2996,
      "step": 55000
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0009661953899758778,
      "loss": 7.3339,
      "step": 55500
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0009661931564370589,
      "loss": 7.3304,
      "step": 56000
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0009661931564370589,
      "loss": 7.3247,
      "step": 56500
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0009661909228982399,
      "loss": 7.3271,
      "step": 57000
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0009661909228982399,
      "loss": 7.3318,
      "step": 57500
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0009661909228982399,
      "loss": 7.3219,
      "step": 58000
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0009661909228982399,
      "loss": 7.3282,
      "step": 58500
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0009661909228982399,
      "loss": 7.3326,
      "step": 59000
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3328,
      "step": 59500
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.342,
      "step": 60000
    },
    {
      "epoch": 0.66,
      "eval_accuracy": 0.047691138834079716,
      "eval_loss": 7.341021537780762,
      "eval_runtime": 1236.7723,
      "eval_samples_per_second": 249.323,
      "eval_steps_per_second": 3.896,
      "step": 60000
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3424,
      "step": 60500
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3356,
      "step": 61000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3449,
      "step": 61500
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3405,
      "step": 62000
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3396,
      "step": 62500
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.336,
      "step": 63000
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3313,
      "step": 63500
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3403,
      "step": 64000
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3409,
      "step": 64500
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3417,
      "step": 65000
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3357,
      "step": 65500
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3417,
      "step": 66000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3376,
      "step": 66500
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3362,
      "step": 67000
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3366,
      "step": 67500
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3416,
      "step": 68000
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3369,
      "step": 68500
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3356,
      "step": 69000
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.337,
      "step": 69500
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3392,
      "step": 70000
    },
    {
      "epoch": 0.76,
      "eval_accuracy": 0.04765096644123483,
      "eval_loss": 7.341658592224121,
      "eval_runtime": 1235.8928,
      "eval_samples_per_second": 249.501,
      "eval_steps_per_second": 3.899,
      "step": 70000
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3396,
      "step": 70500
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3373,
      "step": 71000
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3394,
      "step": 71500
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3401,
      "step": 72000
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3431,
      "step": 72500
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3357,
      "step": 73000
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3383,
      "step": 73500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3405,
      "step": 74000
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3407,
      "step": 74500
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3338,
      "step": 75000
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3386,
      "step": 75500
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3411,
      "step": 76000
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3361,
      "step": 76500
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3431,
      "step": 77000
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3398,
      "step": 77500
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3369,
      "step": 78000
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3414,
      "step": 78500
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3403,
      "step": 79000
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3381,
      "step": 79500
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3357,
      "step": 80000
    },
    {
      "epoch": 0.87,
      "eval_accuracy": 0.04763801266686894,
      "eval_loss": 7.341236114501953,
      "eval_runtime": 1238.5531,
      "eval_samples_per_second": 248.965,
      "eval_steps_per_second": 3.891,
      "step": 80000
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3377,
      "step": 80500
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3383,
      "step": 81000
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3389,
      "step": 81500
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0009661886893594211,
      "loss": 7.3356,
      "step": 82000
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3325,
      "step": 82500
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3304,
      "step": 83000
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3322,
      "step": 83500
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3289,
      "step": 84000
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3313,
      "step": 84500
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.33,
      "step": 85000
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3333,
      "step": 85500
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3386,
      "step": 86000
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3252,
      "step": 86500
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3333,
      "step": 87000
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3297,
      "step": 87500
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3308,
      "step": 88000
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3293,
      "step": 88500
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3298,
      "step": 89000
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3286,
      "step": 89500
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3331,
      "step": 90000
    },
    {
      "epoch": 0.98,
      "eval_accuracy": 0.04418847912382347,
      "eval_loss": 7.434558391571045,
      "eval_runtime": 1236.018,
      "eval_samples_per_second": 249.475,
      "eval_steps_per_second": 3.899,
      "step": 90000
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3307,
      "step": 90500
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3289,
      "step": 91000
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3305,
      "step": 91500
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3297,
      "step": 92000
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3296,
      "step": 92500
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.324,
      "step": 93000
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3319,
      "step": 93500
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3324,
      "step": 94000
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3314,
      "step": 94500
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3352,
      "step": 95000
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3338,
      "step": 95500
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3337,
      "step": 96000
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3328,
      "step": 96500
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3313,
      "step": 97000
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3294,
      "step": 97500
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3344,
      "step": 98000
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3328,
      "step": 98500
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3271,
      "step": 99000
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3322,
      "step": 99500
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3351,
      "step": 100000
    },
    {
      "epoch": 1.09,
      "eval_accuracy": 0.04427367047584467,
      "eval_loss": 7.434557914733887,
      "eval_runtime": 1239.4631,
      "eval_samples_per_second": 248.782,
      "eval_steps_per_second": 3.888,
      "step": 100000
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3359,
      "step": 100500
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3318,
      "step": 101000
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3298,
      "step": 101500
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3336,
      "step": 102000
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3264,
      "step": 102500
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3277,
      "step": 103000
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3243,
      "step": 103500
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3343,
      "step": 104000
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3293,
      "step": 104500
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3276,
      "step": 105000
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3326,
      "step": 105500
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.333,
      "step": 106000
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3285,
      "step": 106500
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.333,
      "step": 107000
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.329,
      "step": 107500
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3326,
      "step": 108000
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3293,
      "step": 108500
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3258,
      "step": 109000
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3294,
      "step": 109500
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3352,
      "step": 110000
    },
    {
      "epoch": 1.2,
      "eval_accuracy": 0.04417750321699954,
      "eval_loss": 7.435162544250488,
      "eval_runtime": 1239.3789,
      "eval_samples_per_second": 248.799,
      "eval_steps_per_second": 3.888,
      "step": 110000
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3302,
      "step": 110500
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3276,
      "step": 111000
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3331,
      "step": 111500
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3336,
      "step": 112000
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3349,
      "step": 112500
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3389,
      "step": 113000
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3273,
      "step": 113500
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3326,
      "step": 114000
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3344,
      "step": 114500
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3291,
      "step": 115000
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3356,
      "step": 115500
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3326,
      "step": 116000
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3275,
      "step": 116500
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3319,
      "step": 117000
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3296,
      "step": 117500
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3324,
      "step": 118000
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3303,
      "step": 118500
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3244,
      "step": 119000
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3336,
      "step": 119500
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3306,
      "step": 120000
    },
    {
      "epoch": 1.31,
      "eval_accuracy": 0.04421948875330736,
      "eval_loss": 7.434651851654053,
      "eval_runtime": 1237.622,
      "eval_samples_per_second": 249.152,
      "eval_steps_per_second": 3.894,
      "step": 120000
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3312,
      "step": 120500
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3294,
      "step": 121000
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3324,
      "step": 121500
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3297,
      "step": 122000
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3291,
      "step": 122500
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3335,
      "step": 123000
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3314,
      "step": 123500
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3386,
      "step": 124000
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3284,
      "step": 124500
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3322,
      "step": 125000
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3249,
      "step": 125500
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3281,
      "step": 126000
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3346,
      "step": 126500
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3344,
      "step": 127000
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3308,
      "step": 127500
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3294,
      "step": 128000
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3349,
      "step": 128500
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3312,
      "step": 129000
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3322,
      "step": 129500
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3281,
      "step": 130000
    },
    {
      "epoch": 1.42,
      "eval_accuracy": 0.044217398460590064,
      "eval_loss": 7.435070991516113,
      "eval_runtime": 1237.16,
      "eval_samples_per_second": 249.245,
      "eval_steps_per_second": 3.895,
      "step": 130000
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3335,
      "step": 130500
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3274,
      "step": 131000
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3285,
      "step": 131500
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3279,
      "step": 132000
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.332,
      "step": 132500
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3306,
      "step": 133000
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3324,
      "step": 133500
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3408,
      "step": 134000
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3298,
      "step": 134500
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3385,
      "step": 135000
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3371,
      "step": 135500
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.331,
      "step": 136000
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3318,
      "step": 136500
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3241,
      "step": 137000
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0009661864558206021,
      "loss": 7.3288,
      "step": 137500
    },
    {
      "epoch": 1.51,
      "step": 137809,
      "total_flos": 2.706179649989247e+18,
      "train_loss": 7.314796883730381,
      "train_runtime": 107981.032,
      "train_samples_per_second": 271.286,
      "train_steps_per_second": 4.239
    }
  ],
  "max_steps": 457720,
  "num_train_epochs": 5,
  "total_flos": 2.706179649989247e+18,
  "trial_name": null,
  "trial_params": null
}