{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.572869502222098,
  "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.3009,
      "step": 100
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 1.2653,
      "step": 200
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.25,
      "step": 300
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.2563,
      "step": 400
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.2794,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.271,
      "step": 600
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.2781,
      "step": 700
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001,
      "loss": 1.2829,
      "step": 800
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.2599,
      "step": 900
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 1.2604,
      "step": 1000
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001,
      "loss": 1.265,
      "step": 1100
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 1.2872,
      "step": 1200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001,
      "loss": 1.2787,
      "step": 1300
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.2544,
      "step": 1400
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001,
      "loss": 1.2844,
      "step": 1500
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.2742,
      "step": 1600
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001,
      "loss": 1.2885,
      "step": 1700
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001,
      "loss": 1.2538,
      "step": 1800
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.2642,
      "step": 1900
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0001,
      "loss": 1.2658,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 1.2749,
      "step": 2100
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001,
      "loss": 1.2729,
      "step": 2200
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.2688,
      "step": 2300
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 1.2798,
      "step": 2400
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 1.2828,
      "step": 2500
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001,
      "loss": 1.2738,
      "step": 2600
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001,
      "loss": 1.268,
      "step": 2700
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 1.2611,
      "step": 2800
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001,
      "loss": 1.2616,
      "step": 2900
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.2727,
      "step": 3000
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001,
      "loss": 1.2658,
      "step": 3100
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 1.2603,
      "step": 3200
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001,
      "loss": 1.2683,
      "step": 3300
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001,
      "loss": 1.2523,
      "step": 3400
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 1.2813,
      "step": 3500
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 1.2716,
      "step": 3600
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 1.2687,
      "step": 3700
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001,
      "loss": 1.2725,
      "step": 3800
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 1.2591,
      "step": 3900
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001,
      "loss": 1.2795,
      "step": 4000
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 1.265,
      "step": 4100
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001,
      "loss": 1.2772,
      "step": 4200
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001,
      "loss": 1.2947,
      "step": 4300
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.256,
      "step": 4400
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.2934,
      "step": 4500
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.2454,
      "step": 4600
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.2621,
      "step": 4700
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 1.2584,
      "step": 4800
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0001,
      "loss": 1.2683,
      "step": 4900
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.2537,
      "step": 5000
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001,
      "loss": 1.2581,
      "step": 5100
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001,
      "loss": 1.2682,
      "step": 5200
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 1.2689,
      "step": 5300
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001,
      "loss": 1.2766,
      "step": 5400
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.2838,
      "step": 5500
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001,
      "loss": 1.2618,
      "step": 5600
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.2672,
      "step": 5700
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 1.2744,
      "step": 5800
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 1.2714,
      "step": 5900
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001,
      "loss": 1.2668,
      "step": 6000
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001,
      "loss": 1.265,
      "step": 6100
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 1.2595,
      "step": 6200
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001,
      "loss": 1.2746,
      "step": 6300
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 1.2747,
      "step": 6400
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001,
      "loss": 1.2798,
      "step": 6500
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 1.2943,
      "step": 6600
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001,
      "loss": 1.2657,
      "step": 6700
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 1.2684,
      "step": 6800
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001,
      "loss": 1.2621,
      "step": 6900
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.283,
      "step": 7000
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.2683,
      "step": 7100
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001,
      "loss": 1.2735,
      "step": 7200
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 1.2891,
      "step": 7300
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001,
      "loss": 1.2804,
      "step": 7400
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.2614,
      "step": 7500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001,
      "loss": 1.2607,
      "step": 7600
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 1.2696,
      "step": 7700
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001,
      "loss": 1.2805,
      "step": 7800
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001,
      "loss": 1.2867,
      "step": 7900
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 1.2486,
      "step": 8000
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001,
      "loss": 1.2447,
      "step": 8100
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.2794,
      "step": 8200
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001,
      "loss": 1.3013,
      "step": 8300
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 1.2673,
      "step": 8400
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001,
      "loss": 1.282,
      "step": 8500
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.2907,
      "step": 8600
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001,
      "loss": 1.2859,
      "step": 8700
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001,
      "loss": 1.2745,
      "step": 8800
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 1.2494,
      "step": 8900
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001,
      "loss": 1.264,
      "step": 9000
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 1.2668,
      "step": 9100
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001,
      "loss": 1.2622,
      "step": 9200
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.2711,
      "step": 9300
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 1.284,
      "step": 9400
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 1.2708,
      "step": 9500
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001,
      "loss": 1.2596,
      "step": 9600
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001,
      "loss": 1.2558,
      "step": 9700
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 1.2743,
      "step": 9800
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0001,
      "loss": 1.2878,
      "step": 9900
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.2765,
      "step": 10000
    },
    {
      "epoch": 0.56,
      "eval_gen_len": 18.999102333931777,
      "eval_loss": 1.3098911046981812,
      "eval_rouge1": 25.1077,
      "eval_rouge2": 12.2495,
      "eval_rougeL": 20.7955,
      "eval_rougeLsum": 23.7161,
      "eval_runtime": 3293.733,
      "eval_samples_per_second": 4.059,
      "eval_steps_per_second": 1.015,
      "step": 10000
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001,
      "loss": 1.2856,
      "step": 10100
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 1.2547,
      "step": 10200
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001,
      "loss": 1.2874,
      "step": 10300
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001,
      "loss": 1.2719,
      "step": 10400
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.2731,
      "step": 10500
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001,
      "loss": 1.2761,
      "step": 10600
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.2642,
      "step": 10700
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0001,
      "loss": 1.2869,
      "step": 10800
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 1.2615,
      "step": 10900
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001,
      "loss": 1.2685,
      "step": 11000
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 1.2776,
      "step": 11100
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001,
      "loss": 1.2706,
      "step": 11200
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001,
      "loss": 1.2584,
      "step": 11300
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.2726,
      "step": 11400
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001,
      "loss": 1.2653,
      "step": 11500
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.2799,
      "step": 11600
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.278,
      "step": 11700
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 1.2758,
      "step": 11800
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001,
      "loss": 1.2838,
      "step": 11900
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 1.2699,
      "step": 12000
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001,
      "loss": 1.259,
      "step": 12100
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001,
      "loss": 1.275,
      "step": 12200
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 1.2807,
      "step": 12300
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001,
      "loss": 1.2779,
      "step": 12400
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.2748,
      "step": 12500
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001,
      "loss": 1.2722,
      "step": 12600
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 1.2643,
      "step": 12700
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001,
      "loss": 1.267,
      "step": 12800
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 1.274,
      "step": 12900
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001,
      "loss": 1.2581,
      "step": 13000
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001,
      "loss": 1.277,
      "step": 13100
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 1.2832,
      "step": 13200
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001,
      "loss": 1.2815,
      "step": 13300
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 1.2785,
      "step": 13400
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001,
      "loss": 1.2816,
      "step": 13500
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 1.2523,
      "step": 13600
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001,
      "loss": 1.261,
      "step": 13700
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 1.2543,
      "step": 13800
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001,
      "loss": 1.2581,
      "step": 13900
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.253,
      "step": 14000
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 1.2582,
      "step": 14100
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001,
      "loss": 1.2621,
      "step": 14200
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 1.2547,
      "step": 14300
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0001,
      "loss": 1.274,
      "step": 14400
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001,
      "loss": 1.2615,
      "step": 14500
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001,
      "loss": 1.2523,
      "step": 14600
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001,
      "loss": 1.2894,
      "step": 14700
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001,
      "loss": 1.2733,
      "step": 14800
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001,
      "loss": 1.2635,
      "step": 14900
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001,
      "loss": 1.259,
      "step": 15000
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001,
      "loss": 1.2545,
      "step": 15100
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001,
      "loss": 1.2751,
      "step": 15200
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001,
      "loss": 1.284,
      "step": 15300
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001,
      "loss": 1.2823,
      "step": 15400
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001,
      "loss": 1.268,
      "step": 15500
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001,
      "loss": 1.2732,
      "step": 15600
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001,
      "loss": 1.2771,
      "step": 15700
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001,
      "loss": 1.2865,
      "step": 15800
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001,
      "loss": 1.2619,
      "step": 15900
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001,
      "loss": 1.2761,
      "step": 16000
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001,
      "loss": 1.2678,
      "step": 16100
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001,
      "loss": 1.2491,
      "step": 16200
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001,
      "loss": 1.2638,
      "step": 16300
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001,
      "loss": 1.267,
      "step": 16400
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001,
      "loss": 1.2818,
      "step": 16500
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001,
      "loss": 1.2757,
      "step": 16600
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001,
      "loss": 1.2541,
      "step": 16700
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001,
      "loss": 1.2747,
      "step": 16800
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0001,
      "loss": 1.2638,
      "step": 16900
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001,
      "loss": 1.2396,
      "step": 17000
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0001,
      "loss": 1.2645,
      "step": 17100
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001,
      "loss": 1.271,
      "step": 17200
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001,
      "loss": 1.271,
      "step": 17300
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001,
      "loss": 1.2475,
      "step": 17400
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001,
      "loss": 1.2691,
      "step": 17500
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001,
      "loss": 1.2554,
      "step": 17600
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001,
      "loss": 1.2831,
      "step": 17700
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001,
      "loss": 1.2584,
      "step": 17800
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 1.2791,
      "step": 17900
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 1.2492,
      "step": 18000
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001,
      "loss": 1.15,
      "step": 18100
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001,
      "loss": 1.1491,
      "step": 18200
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0001,
      "loss": 1.1673,
      "step": 18300
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001,
      "loss": 1.1468,
      "step": 18400
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001,
      "loss": 1.171,
      "step": 18500
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001,
      "loss": 1.1466,
      "step": 18600
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001,
      "loss": 1.1655,
      "step": 18700
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001,
      "loss": 1.1462,
      "step": 18800
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001,
      "loss": 1.1647,
      "step": 18900
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001,
      "loss": 1.1592,
      "step": 19000
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001,
      "loss": 1.1481,
      "step": 19100
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001,
      "loss": 1.185,
      "step": 19200
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001,
      "loss": 1.1562,
      "step": 19300
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001,
      "loss": 1.1649,
      "step": 19400
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001,
      "loss": 1.1578,
      "step": 19500
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001,
      "loss": 1.1358,
      "step": 19600
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001,
      "loss": 1.1497,
      "step": 19700
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0001,
      "loss": 1.1851,
      "step": 19800
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001,
      "loss": 1.1749,
      "step": 19900
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0001,
      "loss": 1.1427,
      "step": 20000
    },
    {
      "epoch": 1.11,
      "eval_gen_len": 18.999925194494313,
      "eval_loss": 1.3236223459243774,
      "eval_rouge1": 25.3599,
      "eval_rouge2": 12.4924,
      "eval_rougeL": 20.9611,
      "eval_rougeLsum": 23.8904,
      "eval_runtime": 3208.3054,
      "eval_samples_per_second": 4.167,
      "eval_steps_per_second": 1.042,
      "step": 20000
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001,
      "loss": 1.1639,
      "step": 20100
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001,
      "loss": 1.1528,
      "step": 20200
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001,
      "loss": 1.1579,
      "step": 20300
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001,
      "loss": 1.1776,
      "step": 20400
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001,
      "loss": 1.1453,
      "step": 20500
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001,
      "loss": 1.1655,
      "step": 20600
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001,
      "loss": 1.1789,
      "step": 20700
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 1.1427,
      "step": 20800
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001,
      "loss": 1.1431,
      "step": 20900
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001,
      "loss": 1.1569,
      "step": 21000
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001,
      "loss": 1.1819,
      "step": 21100
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001,
      "loss": 1.1867,
      "step": 21200
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001,
      "loss": 1.177,
      "step": 21300
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0001,
      "loss": 1.1637,
      "step": 21400
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001,
      "loss": 1.1836,
      "step": 21500
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001,
      "loss": 1.1526,
      "step": 21600
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001,
      "loss": 1.177,
      "step": 21700
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001,
      "loss": 1.1544,
      "step": 21800
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001,
      "loss": 1.176,
      "step": 21900
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001,
      "loss": 1.1804,
      "step": 22000
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001,
      "loss": 1.188,
      "step": 22100
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001,
      "loss": 1.1781,
      "step": 22200
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001,
      "loss": 1.1584,
      "step": 22300
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001,
      "loss": 1.177,
      "step": 22400
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0001,
      "loss": 1.1609,
      "step": 22500
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001,
      "loss": 1.1632,
      "step": 22600
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001,
      "loss": 1.1668,
      "step": 22700
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001,
      "loss": 1.1486,
      "step": 22800
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001,
      "loss": 1.1801,
      "step": 22900
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001,
      "loss": 1.1638,
      "step": 23000
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001,
      "loss": 1.1663,
      "step": 23100
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001,
      "loss": 1.1708,
      "step": 23200
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001,
      "loss": 1.1722,
      "step": 23300
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001,
      "loss": 1.1647,
      "step": 23400
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001,
      "loss": 1.1795,
      "step": 23500
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001,
      "loss": 1.165,
      "step": 23600
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001,
      "loss": 1.1642,
      "step": 23700
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001,
      "loss": 1.1811,
      "step": 23800
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001,
      "loss": 1.174,
      "step": 23900
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001,
      "loss": 1.167,
      "step": 24000
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001,
      "loss": 1.1604,
      "step": 24100
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001,
      "loss": 1.1705,
      "step": 24200
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001,
      "loss": 1.166,
      "step": 24300
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0001,
      "loss": 1.1875,
      "step": 24400
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001,
      "loss": 1.1917,
      "step": 24500
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001,
      "loss": 1.1666,
      "step": 24600
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001,
      "loss": 1.1663,
      "step": 24700
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001,
      "loss": 1.1638,
      "step": 24800
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001,
      "loss": 1.1782,
      "step": 24900
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001,
      "loss": 1.1771,
      "step": 25000
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001,
      "loss": 1.1464,
      "step": 25100
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001,
      "loss": 1.1833,
      "step": 25200
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001,
      "loss": 1.174,
      "step": 25300
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001,
      "loss": 1.1963,
      "step": 25400
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001,
      "loss": 1.213,
      "step": 25500
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001,
      "loss": 1.1782,
      "step": 25600
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001,
      "loss": 1.1755,
      "step": 25700
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001,
      "loss": 1.1699,
      "step": 25800
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001,
      "loss": 1.1791,
      "step": 25900
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001,
      "loss": 1.1763,
      "step": 26000
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001,
      "loss": 1.2031,
      "step": 26100
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0001,
      "loss": 1.1805,
      "step": 26200
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001,
      "loss": 1.1684,
      "step": 26300
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001,
      "loss": 1.1822,
      "step": 26400
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001,
      "loss": 1.1677,
      "step": 26500
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001,
      "loss": 1.1695,
      "step": 26600
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001,
      "loss": 1.1906,
      "step": 26700
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001,
      "loss": 1.1892,
      "step": 26800
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001,
      "loss": 1.1876,
      "step": 26900
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001,
      "loss": 1.1813,
      "step": 27000
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001,
      "loss": 1.1877,
      "step": 27100
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0001,
      "loss": 1.1918,
      "step": 27200
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0001,
      "loss": 1.1679,
      "step": 27300
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001,
      "loss": 1.1726,
      "step": 27400
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001,
      "loss": 1.1718,
      "step": 27500
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001,
      "loss": 1.191,
      "step": 27600
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001,
      "loss": 1.1769,
      "step": 27700
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001,
      "loss": 1.1784,
      "step": 27800
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001,
      "loss": 1.1642,
      "step": 27900
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001,
      "loss": 1.163,
      "step": 28000
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0001,
      "loss": 1.1779,
      "step": 28100
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0001,
      "loss": 1.1889,
      "step": 28200
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001,
      "loss": 1.1813,
      "step": 28300
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001,
      "loss": 1.158,
      "step": 28400
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001,
      "loss": 1.1718,
      "step": 28500
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001,
      "loss": 1.1886,
      "step": 28600
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001,
      "loss": 1.1731,
      "step": 28700
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001,
      "loss": 1.1739,
      "step": 28800
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0001,
      "loss": 1.178,
      "step": 28900
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001,
      "loss": 1.1878,
      "step": 29000
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001,
      "loss": 1.1832,
      "step": 29100
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001,
      "loss": 1.1913,
      "step": 29200
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001,
      "loss": 1.1872,
      "step": 29300
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001,
      "loss": 1.1704,
      "step": 29400
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001,
      "loss": 1.1892,
      "step": 29500
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0001,
      "loss": 1.1832,
      "step": 29600
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001,
      "loss": 1.1816,
      "step": 29700
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001,
      "loss": 1.1864,
      "step": 29800
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001,
      "loss": 1.1966,
      "step": 29900
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0001,
      "loss": 1.1843,
      "step": 30000
    },
    {
      "epoch": 1.67,
      "eval_gen_len": 19.0,
      "eval_loss": 1.3095118999481201,
      "eval_rouge1": 25.3735,
      "eval_rouge2": 12.3866,
      "eval_rougeL": 20.94,
      "eval_rougeLsum": 23.9243,
      "eval_runtime": 3242.2361,
      "eval_samples_per_second": 4.123,
      "eval_steps_per_second": 1.031,
      "step": 30000
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001,
      "loss": 1.204,
      "step": 30100
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001,
      "loss": 1.1791,
      "step": 30200
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001,
      "loss": 1.1953,
      "step": 30300
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001,
      "loss": 1.1757,
      "step": 30400
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001,
      "loss": 1.172,
      "step": 30500
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001,
      "loss": 1.2068,
      "step": 30600
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0001,
      "loss": 1.1775,
      "step": 30700
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001,
      "loss": 1.1829,
      "step": 30800
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.0001,
      "loss": 1.1836,
      "step": 30900
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001,
      "loss": 1.1704,
      "step": 31000
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001,
      "loss": 1.1798,
      "step": 31100
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001,
      "loss": 1.1994,
      "step": 31200
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001,
      "loss": 1.1884,
      "step": 31300
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001,
      "loss": 1.1737,
      "step": 31400
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001,
      "loss": 1.1847,
      "step": 31500
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001,
      "loss": 1.1945,
      "step": 31600
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001,
      "loss": 1.1959,
      "step": 31700
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001,
      "loss": 1.1965,
      "step": 31800
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001,
      "loss": 1.19,
      "step": 31900
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001,
      "loss": 1.1938,
      "step": 32000
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001,
      "loss": 1.1922,
      "step": 32100
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001,
      "loss": 1.1868,
      "step": 32200
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001,
      "loss": 1.191,
      "step": 32300
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001,
      "loss": 1.1928,
      "step": 32400
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001,
      "loss": 1.1873,
      "step": 32500
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001,
      "loss": 1.1899,
      "step": 32600
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001,
      "loss": 1.2058,
      "step": 32700
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001,
      "loss": 1.2103,
      "step": 32800
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001,
      "loss": 1.1597,
      "step": 32900
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001,
      "loss": 1.2053,
      "step": 33000
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001,
      "loss": 1.1726,
      "step": 33100
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001,
      "loss": 1.1919,
      "step": 33200
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0001,
      "loss": 1.1954,
      "step": 33300
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0001,
      "loss": 1.1631,
      "step": 33400
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0001,
      "loss": 1.1797,
      "step": 33500
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0001,
      "loss": 1.1976,
      "step": 33600
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001,
      "loss": 1.1698,
      "step": 33700
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001,
      "loss": 1.1945,
      "step": 33800
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001,
      "loss": 1.1964,
      "step": 33900
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001,
      "loss": 1.1973,
      "step": 34000
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001,
      "loss": 1.1716,
      "step": 34100
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001,
      "loss": 1.1873,
      "step": 34200
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0001,
      "loss": 1.1837,
      "step": 34300
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001,
      "loss": 1.1966,
      "step": 34400
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.0001,
      "loss": 1.1628,
      "step": 34500
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001,
      "loss": 1.1822,
      "step": 34600
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001,
      "loss": 1.1798,
      "step": 34700
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001,
      "loss": 1.217,
      "step": 34800
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001,
      "loss": 1.1985,
      "step": 34900
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001,
      "loss": 1.2223,
      "step": 35000
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001,
      "loss": 1.1855,
      "step": 35100
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001,
      "loss": 1.201,
      "step": 35200
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001,
      "loss": 1.1809,
      "step": 35300
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001,
      "loss": 1.1866,
      "step": 35400
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001,
      "loss": 1.1806,
      "step": 35500
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001,
      "loss": 1.1901,
      "step": 35600
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001,
      "loss": 1.1937,
      "step": 35700
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001,
      "loss": 1.1963,
      "step": 35800
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001,
      "loss": 1.1747,
      "step": 35900
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001,
      "loss": 1.0581,
      "step": 36000
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001,
      "loss": 1.0759,
      "step": 36100
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0001,
      "loss": 1.0915,
      "step": 36200
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0001,
      "loss": 1.0746,
      "step": 36300
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001,
      "loss": 1.0846,
      "step": 36400
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0001,
      "loss": 1.0777,
      "step": 36500
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001,
      "loss": 1.0809,
      "step": 36600
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001,
      "loss": 1.0715,
      "step": 36700
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001,
      "loss": 1.0764,
      "step": 36800
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0001,
      "loss": 1.0839,
      "step": 36900
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.0001,
      "loss": 1.0808,
      "step": 37000
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001,
      "loss": 1.1014,
      "step": 37100
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001,
      "loss": 1.0956,
      "step": 37200
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001,
      "loss": 1.0966,
      "step": 37300
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001,
      "loss": 1.0754,
      "step": 37400
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0001,
      "loss": 1.0856,
      "step": 37500
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001,
      "loss": 1.1022,
      "step": 37600
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.0001,
      "loss": 1.0966,
      "step": 37700
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001,
      "loss": 1.0843,
      "step": 37800
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001,
      "loss": 1.0705,
      "step": 37900
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001,
      "loss": 1.0926,
      "step": 38000
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.0001,
      "loss": 1.0939,
      "step": 38100
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001,
      "loss": 1.1088,
      "step": 38200
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001,
      "loss": 1.0962,
      "step": 38300
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001,
      "loss": 1.0889,
      "step": 38400
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001,
      "loss": 1.0834,
      "step": 38500
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001,
      "loss": 1.0838,
      "step": 38600
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001,
      "loss": 1.1026,
      "step": 38700
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001,
      "loss": 1.1051,
      "step": 38800
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0001,
      "loss": 1.0835,
      "step": 38900
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0001,
      "loss": 1.0839,
      "step": 39000
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001,
      "loss": 1.1064,
      "step": 39100
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001,
      "loss": 1.0943,
      "step": 39200
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0001,
      "loss": 1.0935,
      "step": 39300
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001,
      "loss": 1.0931,
      "step": 39400
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001,
      "loss": 1.0987,
      "step": 39500
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001,
      "loss": 1.1011,
      "step": 39600
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001,
      "loss": 1.1067,
      "step": 39700
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001,
      "loss": 1.088,
      "step": 39800
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001,
      "loss": 1.091,
      "step": 39900
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001,
      "loss": 1.106,
      "step": 40000
    },
    {
      "epoch": 2.23,
      "eval_gen_len": 18.999102333931777,
      "eval_loss": 1.3284715414047241,
      "eval_rouge1": 25.3546,
      "eval_rouge2": 12.4744,
      "eval_rougeL": 20.9669,
      "eval_rougeLsum": 23.8734,
      "eval_runtime": 3272.9462,
      "eval_samples_per_second": 4.084,
      "eval_steps_per_second": 1.021,
      "step": 40000
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001,
      "loss": 1.1061,
      "step": 40100
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0001,
      "loss": 1.0935,
      "step": 40200
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0001,
      "loss": 1.0846,
      "step": 40300
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0001,
      "loss": 1.09,
      "step": 40400
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0001,
      "loss": 1.1088,
      "step": 40500
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0001,
      "loss": 1.0794,
      "step": 40600
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001,
      "loss": 1.1098,
      "step": 40700
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001,
      "loss": 1.0927,
      "step": 40800
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0001,
      "loss": 1.094,
      "step": 40900
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.0001,
      "loss": 1.0979,
      "step": 41000
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0001,
      "loss": 1.1091,
      "step": 41100
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0001,
      "loss": 1.1014,
      "step": 41200
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0001,
      "loss": 1.1137,
      "step": 41300
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001,
      "loss": 1.1115,
      "step": 41400
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0001,
      "loss": 1.1158,
      "step": 41500
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001,
      "loss": 1.1118,
      "step": 41600
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001,
      "loss": 1.081,
      "step": 41700
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0001,
      "loss": 1.1086,
      "step": 41800
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001,
      "loss": 1.1018,
      "step": 41900
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001,
      "loss": 1.0901,
      "step": 42000
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001,
      "loss": 1.0954,
      "step": 42100
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001,
      "loss": 1.0893,
      "step": 42200
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0001,
      "loss": 1.0991,
      "step": 42300
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0001,
      "loss": 1.1134,
      "step": 42400
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001,
      "loss": 1.1084,
      "step": 42500
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001,
      "loss": 1.1045,
      "step": 42600
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001,
      "loss": 1.1214,
      "step": 42700
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0001,
      "loss": 1.098,
      "step": 42800
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0001,
      "loss": 1.1336,
      "step": 42900
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0001,
      "loss": 1.1071,
      "step": 43000
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0001,
      "loss": 1.1065,
      "step": 43100
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001,
      "loss": 1.0897,
      "step": 43200
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001,
      "loss": 1.117,
      "step": 43300
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001,
      "loss": 1.1154,
      "step": 43400
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001,
      "loss": 1.09,
      "step": 43500
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0001,
      "loss": 1.1104,
      "step": 43600
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0001,
      "loss": 1.1033,
      "step": 43700
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0001,
      "loss": 1.0976,
      "step": 43800
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001,
      "loss": 1.1109,
      "step": 43900
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001,
      "loss": 1.0919,
      "step": 44000
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0001,
      "loss": 1.1106,
      "step": 44100
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0001,
      "loss": 1.0952,
      "step": 44200
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001,
      "loss": 1.1055,
      "step": 44300
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001,
      "loss": 1.1131,
      "step": 44400
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001,
      "loss": 1.0952,
      "step": 44500
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0001,
      "loss": 1.11,
      "step": 44600
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0001,
      "loss": 1.1143,
      "step": 44700
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0001,
      "loss": 1.1082,
      "step": 44800
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.0001,
      "loss": 1.1191,
      "step": 44900
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0001,
      "loss": 1.1171,
      "step": 45000
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0001,
      "loss": 1.1146,
      "step": 45100
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0001,
      "loss": 1.1218,
      "step": 45200
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0001,
      "loss": 1.1082,
      "step": 45300
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0001,
      "loss": 1.1235,
      "step": 45400
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001,
      "loss": 1.1162,
      "step": 45500
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001,
      "loss": 1.1332,
      "step": 45600
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0001,
      "loss": 1.0948,
      "step": 45700
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0001,
      "loss": 1.1073,
      "step": 45800
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001,
      "loss": 1.1338,
      "step": 45900
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001,
      "loss": 1.109,
      "step": 46000
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0001,
      "loss": 1.1123,
      "step": 46100
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0001,
      "loss": 1.1247,
      "step": 46200
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0001,
      "loss": 1.1232,
      "step": 46300
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0001,
      "loss": 1.1146,
      "step": 46400
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0001,
      "loss": 1.1177,
      "step": 46500
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0001,
      "loss": 1.1109,
      "step": 46600
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0001,
      "loss": 1.0968,
      "step": 46700
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0001,
      "loss": 1.1135,
      "step": 46800
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0001,
      "loss": 1.1093,
      "step": 46900
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0001,
      "loss": 1.1297,
      "step": 47000
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0001,
      "loss": 1.1166,
      "step": 47100
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0001,
      "loss": 1.1071,
      "step": 47200
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0001,
      "loss": 1.1086,
      "step": 47300
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0001,
      "loss": 1.1264,
      "step": 47400
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001,
      "loss": 1.1236,
      "step": 47500
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001,
      "loss": 1.1261,
      "step": 47600
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0001,
      "loss": 1.1212,
      "step": 47700
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0001,
      "loss": 1.127,
      "step": 47800
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0001,
      "loss": 1.0988,
      "step": 47900
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0001,
      "loss": 1.1217,
      "step": 48000
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0001,
      "loss": 1.1342,
      "step": 48100
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0001,
      "loss": 1.1197,
      "step": 48200
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0001,
      "loss": 1.1266,
      "step": 48300
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0001,
      "loss": 1.1319,
      "step": 48400
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0001,
      "loss": 1.1247,
      "step": 48500
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0001,
      "loss": 1.1401,
      "step": 48600
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0001,
      "loss": 1.1493,
      "step": 48700
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0001,
      "loss": 1.1109,
      "step": 48800
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0001,
      "loss": 1.1149,
      "step": 48900
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0001,
      "loss": 1.1416,
      "step": 49000
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0001,
      "loss": 1.1274,
      "step": 49100
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0001,
      "loss": 1.1229,
      "step": 49200
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0001,
      "loss": 1.1089,
      "step": 49300
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0001,
      "loss": 1.136,
      "step": 49400
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0001,
      "loss": 1.1271,
      "step": 49500
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0001,
      "loss": 1.1265,
      "step": 49600
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.0001,
      "loss": 1.1162,
      "step": 49700
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0001,
      "loss": 1.1156,
      "step": 49800
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0001,
      "loss": 1.1298,
      "step": 49900
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0001,
      "loss": 1.1279,
      "step": 50000
    },
    {
      "epoch": 2.79,
      "eval_gen_len": 19.0,
      "eval_loss": 1.3139911890029907,
      "eval_rouge1": 25.3036,
      "eval_rouge2": 12.4032,
      "eval_rougeL": 20.9035,
      "eval_rougeLsum": 23.8696,
      "eval_runtime": 3328.8093,
      "eval_samples_per_second": 4.016,
      "eval_steps_per_second": 1.004,
      "step": 50000
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0001,
      "loss": 1.1183,
      "step": 50100
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0001,
      "loss": 1.1412,
      "step": 50200
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0001,
      "loss": 1.1097,
      "step": 50300
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0001,
      "loss": 1.1212,
      "step": 50400
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.0001,
      "loss": 1.1152,
      "step": 50500
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0001,
      "loss": 1.1347,
      "step": 50600
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0001,
      "loss": 1.1215,
      "step": 50700
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0001,
      "loss": 1.1362,
      "step": 50800
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0001,
      "loss": 1.1042,
      "step": 50900
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0001,
      "loss": 1.1103,
      "step": 51000
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0001,
      "loss": 1.1173,
      "step": 51100
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0001,
      "loss": 1.119,
      "step": 51200
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0001,
      "loss": 1.1156,
      "step": 51300
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0001,
      "loss": 1.1167,
      "step": 51400
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.0001,
      "loss": 1.1465,
      "step": 51500
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0001,
      "loss": 1.1155,
      "step": 51600
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0001,
      "loss": 1.1495,
      "step": 51700
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0001,
      "loss": 1.1404,
      "step": 51800
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0001,
      "loss": 1.1223,
      "step": 51900
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0001,
      "loss": 1.1454,
      "step": 52000
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0001,
      "loss": 1.1213,
      "step": 52100
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0001,
      "loss": 1.1251,
      "step": 52200
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.0001,
      "loss": 1.1387,
      "step": 52300
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0001,
      "loss": 1.1003,
      "step": 52400
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0001,
      "loss": 1.1266,
      "step": 52500
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0001,
      "loss": 1.1081,
      "step": 52600
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0001,
      "loss": 1.1044,
      "step": 52700
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0001,
      "loss": 1.1344,
      "step": 52800
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0001,
      "loss": 1.1202,
      "step": 52900
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0001,
      "loss": 1.1363,
      "step": 53000
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0001,
      "loss": 1.144,
      "step": 53100
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0001,
      "loss": 1.1224,
      "step": 53200
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0001,
      "loss": 1.1335,
      "step": 53300
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0001,
      "loss": 1.1225,
      "step": 53400
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0001,
      "loss": 1.1048,
      "step": 53500
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0001,
      "loss": 1.1267,
      "step": 53600
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0001,
      "loss": 1.125,
      "step": 53700
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0001,
      "loss": 1.1262,
      "step": 53800
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0001,
      "loss": 1.0593,
      "step": 53900
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.0001,
      "loss": 1.0256,
      "step": 54000
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.0001,
      "loss": 1.0248,
      "step": 54100
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0001,
      "loss": 1.0084,
      "step": 54200
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.0001,
      "loss": 1.0341,
      "step": 54300
    },
    {
      "epoch": 3.03,
      "learning_rate": 0.0001,
      "loss": 1.0109,
      "step": 54400
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001,
      "loss": 1.0174,
      "step": 54500
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.0001,
      "loss": 1.0173,
      "step": 54600
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0001,
      "loss": 1.0247,
      "step": 54700
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.0001,
      "loss": 1.0153,
      "step": 54800
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.0001,
      "loss": 1.0256,
      "step": 54900
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0001,
      "loss": 1.021,
      "step": 55000
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0001,
      "loss": 1.025,
      "step": 55100
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0001,
      "loss": 1.0137,
      "step": 55200
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.0001,
      "loss": 1.0132,
      "step": 55300
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0001,
      "loss": 1.0156,
      "step": 55400
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.0001,
      "loss": 1.0201,
      "step": 55500
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0001,
      "loss": 1.0525,
      "step": 55600
    },
    {
      "epoch": 3.1,
      "learning_rate": 0.0001,
      "loss": 1.0245,
      "step": 55700
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0001,
      "loss": 1.0294,
      "step": 55800
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001,
      "loss": 1.0296,
      "step": 55900
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001,
      "loss": 1.0247,
      "step": 56000
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0001,
      "loss": 1.0288,
      "step": 56100
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.0001,
      "loss": 1.0321,
      "step": 56200
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0001,
      "loss": 1.0239,
      "step": 56300
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.0001,
      "loss": 1.0432,
      "step": 56400
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.0001,
      "loss": 1.0294,
      "step": 56500
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.0001,
      "loss": 1.0174,
      "step": 56600
    },
    {
      "epoch": 3.16,
      "learning_rate": 0.0001,
      "loss": 1.0198,
      "step": 56700
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0001,
      "loss": 1.0098,
      "step": 56800
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.0001,
      "loss": 1.0361,
      "step": 56900
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.0001,
      "loss": 1.0305,
      "step": 57000
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.0001,
      "loss": 1.0298,
      "step": 57100
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0001,
      "loss": 1.049,
      "step": 57200
    },
    {
      "epoch": 3.19,
      "learning_rate": 0.0001,
      "loss": 1.0093,
      "step": 57300
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0001,
      "loss": 1.036,
      "step": 57400
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0001,
      "loss": 1.0248,
      "step": 57500
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.0001,
      "loss": 1.0388,
      "step": 57600
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.0001,
      "loss": 1.0376,
      "step": 57700
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.0001,
      "loss": 1.0331,
      "step": 57800
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0001,
      "loss": 1.0504,
      "step": 57900
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.0001,
      "loss": 1.0441,
      "step": 58000
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0001,
      "loss": 1.0244,
      "step": 58100
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.0001,
      "loss": 1.0378,
      "step": 58200
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0001,
      "loss": 1.0414,
      "step": 58300
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0001,
      "loss": 1.0367,
      "step": 58400
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.0001,
      "loss": 1.0133,
      "step": 58500
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.0001,
      "loss": 1.0498,
      "step": 58600
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.0001,
      "loss": 1.0416,
      "step": 58700
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0001,
      "loss": 1.0465,
      "step": 58800
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.0001,
      "loss": 1.0346,
      "step": 58900
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.0001,
      "loss": 1.0501,
      "step": 59000
    },
    {
      "epoch": 3.29,
      "learning_rate": 0.0001,
      "loss": 1.0503,
      "step": 59100
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.0001,
      "loss": 1.059,
      "step": 59200
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.0001,
      "loss": 1.0414,
      "step": 59300
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.0001,
      "loss": 1.0357,
      "step": 59400
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.0001,
      "loss": 1.0426,
      "step": 59500
    },
    {
      "epoch": 3.32,
      "learning_rate": 0.0001,
      "loss": 1.0303,
      "step": 59600
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0001,
      "loss": 1.0534,
      "step": 59700
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0001,
      "loss": 1.0304,
      "step": 59800
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0001,
      "loss": 1.0554,
      "step": 59900
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.0001,
      "loss": 1.0574,
      "step": 60000
    },
    {
      "epoch": 3.34,
      "eval_gen_len": 18.999775583482943,
      "eval_loss": 1.343895673751831,
      "eval_rouge1": 25.1188,
      "eval_rouge2": 12.1556,
      "eval_rougeL": 20.6878,
      "eval_rougeLsum": 23.6614,
      "eval_runtime": 3246.0297,
      "eval_samples_per_second": 4.118,
      "eval_steps_per_second": 1.03,
      "step": 60000
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0001,
      "loss": 1.05,
      "step": 60100
    },
    {
      "epoch": 3.35,
      "learning_rate": 0.0001,
      "loss": 1.0444,
      "step": 60200
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.0001,
      "loss": 1.0362,
      "step": 60300
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.0001,
      "loss": 1.058,
      "step": 60400
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.0001,
      "loss": 1.0609,
      "step": 60500
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0001,
      "loss": 1.0438,
      "step": 60600
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0001,
      "loss": 1.0497,
      "step": 60700
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.0001,
      "loss": 1.0501,
      "step": 60800
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.0001,
      "loss": 1.0602,
      "step": 60900
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0001,
      "loss": 1.0649,
      "step": 61000
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.0001,
      "loss": 1.0422,
      "step": 61100
    },
    {
      "epoch": 3.41,
      "learning_rate": 0.0001,
      "loss": 1.0465,
      "step": 61200
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0001,
      "loss": 1.044,
      "step": 61300
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.0001,
      "loss": 1.0393,
      "step": 61400
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0001,
      "loss": 1.0491,
      "step": 61500
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.0001,
      "loss": 1.0721,
      "step": 61600
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0001,
      "loss": 1.0583,
      "step": 61700
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0001,
      "loss": 1.0581,
      "step": 61800
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.0001,
      "loss": 1.0448,
      "step": 61900
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0001,
      "loss": 1.0456,
      "step": 62000
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.0001,
      "loss": 1.0368,
      "step": 62100
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.0001,
      "loss": 1.0368,
      "step": 62200
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.0001,
      "loss": 1.0498,
      "step": 62300
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0001,
      "loss": 1.0566,
      "step": 62400
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.0001,
      "loss": 1.052,
      "step": 62500
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.0001,
      "loss": 1.0426,
      "step": 62600
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.0001,
      "loss": 1.0824,
      "step": 62700
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.0001,
      "loss": 1.0321,
      "step": 62800
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0001,
      "loss": 1.0713,
      "step": 62900
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0001,
      "loss": 1.0471,
      "step": 63000
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0001,
      "loss": 1.0509,
      "step": 63100
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.0001,
      "loss": 1.0495,
      "step": 63200
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0001,
      "loss": 1.0467,
      "step": 63300
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.0001,
      "loss": 1.0521,
      "step": 63400
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0001,
      "loss": 1.0492,
      "step": 63500
    },
    {
      "epoch": 3.54,
      "learning_rate": 0.0001,
      "loss": 1.0524,
      "step": 63600
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.0001,
      "loss": 1.0524,
      "step": 63700
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0001,
      "loss": 1.0531,
      "step": 63800
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0001,
      "loss": 1.0578,
      "step": 63900
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.0001,
      "loss": 1.0751,
      "step": 64000
    },
    {
      "epoch": 3.57,
      "learning_rate": 0.0001,
      "loss": 1.0531,
      "step": 64100
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0001,
      "loss": 1.041,
      "step": 64200
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.0001,
      "loss": 1.0646,
      "step": 64300
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.0001,
      "loss": 1.0417,
      "step": 64400
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.0001,
      "loss": 1.0532,
      "step": 64500
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.0001,
      "loss": 1.0643,
      "step": 64600
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.0001,
      "loss": 1.0448,
      "step": 64700
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.0001,
      "loss": 1.0676,
      "step": 64800
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.0001,
      "loss": 1.0608,
      "step": 64900
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.0001,
      "loss": 1.0645,
      "step": 65000
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0001,
      "loss": 1.0458,
      "step": 65100
    },
    {
      "epoch": 3.63,
      "learning_rate": 0.0001,
      "loss": 1.0593,
      "step": 65200
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0001,
      "loss": 1.0631,
      "step": 65300
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0001,
      "loss": 1.0606,
      "step": 65400
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.0001,
      "loss": 1.0666,
      "step": 65500
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0001,
      "loss": 1.0592,
      "step": 65600
    },
    {
      "epoch": 3.66,
      "learning_rate": 0.0001,
      "loss": 1.067,
      "step": 65700
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0001,
      "loss": 1.0809,
      "step": 65800
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0001,
      "loss": 1.0444,
      "step": 65900
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0001,
      "loss": 1.0633,
      "step": 66000
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.0001,
      "loss": 1.0511,
      "step": 66100
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.0001,
      "loss": 1.0508,
      "step": 66200
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.0001,
      "loss": 1.0614,
      "step": 66300
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.0001,
      "loss": 1.0496,
      "step": 66400
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0001,
      "loss": 1.0709,
      "step": 66500
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.0001,
      "loss": 1.0672,
      "step": 66600
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.0001,
      "loss": 1.0599,
      "step": 66700
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.0001,
      "loss": 1.0863,
      "step": 66800
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0001,
      "loss": 1.0551,
      "step": 66900
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0001,
      "loss": 1.0463,
      "step": 67000
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0001,
      "loss": 1.0681,
      "step": 67100
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.0001,
      "loss": 1.0692,
      "step": 67200
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.0001,
      "loss": 1.0647,
      "step": 67300
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.0001,
      "loss": 1.0544,
      "step": 67400
    },
    {
      "epoch": 3.76,
      "learning_rate": 0.0001,
      "loss": 1.0477,
      "step": 67500
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0001,
      "loss": 1.0437,
      "step": 67600
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0001,
      "loss": 1.0731,
      "step": 67700
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0001,
      "loss": 1.0602,
      "step": 67800
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0001,
      "loss": 1.0386,
      "step": 67900
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.0001,
      "loss": 1.0564,
      "step": 68000
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0001,
      "loss": 1.0871,
      "step": 68100
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.0001,
      "loss": 1.0837,
      "step": 68200
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.0001,
      "loss": 1.0645,
      "step": 68300
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.0001,
      "loss": 1.073,
      "step": 68400
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0001,
      "loss": 1.0495,
      "step": 68500
    },
    {
      "epoch": 3.82,
      "learning_rate": 0.0001,
      "loss": 1.0644,
      "step": 68600
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0001,
      "loss": 1.0604,
      "step": 68700
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.0001,
      "loss": 1.0726,
      "step": 68800
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.0001,
      "loss": 1.0691,
      "step": 68900
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.0001,
      "loss": 1.0706,
      "step": 69000
    },
    {
      "epoch": 3.85,
      "learning_rate": 0.0001,
      "loss": 1.0876,
      "step": 69100
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0001,
      "loss": 1.0509,
      "step": 69200
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.0001,
      "loss": 1.0808,
      "step": 69300
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0001,
      "loss": 1.073,
      "step": 69400
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.0001,
      "loss": 1.0671,
      "step": 69500
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.0001,
      "loss": 1.0717,
      "step": 69600
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.0001,
      "loss": 1.0791,
      "step": 69700
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.0001,
      "loss": 1.0827,
      "step": 69800
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0001,
      "loss": 1.0749,
      "step": 69900
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0001,
      "loss": 1.0757,
      "step": 70000
    },
    {
      "epoch": 3.9,
      "eval_gen_len": 18.999251944943147,
      "eval_loss": 1.3321020603179932,
      "eval_rouge1": 25.382,
      "eval_rouge2": 12.3675,
      "eval_rougeL": 20.917,
      "eval_rougeLsum": 23.9467,
      "eval_runtime": 3253.3844,
      "eval_samples_per_second": 4.109,
      "eval_steps_per_second": 1.027,
      "step": 70000
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0001,
      "loss": 1.0539,
      "step": 70100
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.0001,
      "loss": 1.0778,
      "step": 70200
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.0001,
      "loss": 1.0676,
      "step": 70300
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.0001,
      "loss": 1.0694,
      "step": 70400
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0001,
      "loss": 1.0787,
      "step": 70500
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.0001,
      "loss": 1.0748,
      "step": 70600
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.0001,
      "loss": 1.0722,
      "step": 70700
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.0001,
      "loss": 1.0655,
      "step": 70800
    },
    {
      "epoch": 3.95,
      "learning_rate": 0.0001,
      "loss": 1.06,
      "step": 70900
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.0001,
      "loss": 1.0767,
      "step": 71000
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.0001,
      "loss": 1.0774,
      "step": 71100
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.0001,
      "loss": 1.0639,
      "step": 71200
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.0001,
      "loss": 1.0851,
      "step": 71300
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.0001,
      "loss": 1.0559,
      "step": 71400
    },
    {
      "epoch": 3.98,
      "learning_rate": 0.0001,
      "loss": 1.0946,
      "step": 71500
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.0001,
      "loss": 1.0722,
      "step": 71600
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0001,
      "loss": 1.0804,
      "step": 71700
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0001,
      "loss": 1.0494,
      "step": 71800
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.0001,
      "loss": 0.9773,
      "step": 71900
    },
    {
      "epoch": 4.01,
      "learning_rate": 0.0001,
      "loss": 0.9763,
      "step": 72000
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.0001,
      "loss": 0.9483,
      "step": 72100
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.0001,
      "loss": 0.9673,
      "step": 72200
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0001,
      "loss": 0.9691,
      "step": 72300
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0001,
      "loss": 0.9668,
      "step": 72400
    },
    {
      "epoch": 4.04,
      "learning_rate": 0.0001,
      "loss": 0.9567,
      "step": 72500
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.0001,
      "loss": 0.9696,
      "step": 72600
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.0001,
      "loss": 0.9704,
      "step": 72700
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0001,
      "loss": 0.9555,
      "step": 72800
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0001,
      "loss": 0.9598,
      "step": 72900
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.0001,
      "loss": 0.9577,
      "step": 73000
    },
    {
      "epoch": 4.07,
      "learning_rate": 0.0001,
      "loss": 0.963,
      "step": 73100
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.0001,
      "loss": 0.975,
      "step": 73200
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.0001,
      "loss": 0.9876,
      "step": 73300
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.0001,
      "loss": 0.9688,
      "step": 73400
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.0001,
      "loss": 0.9704,
      "step": 73500
    },
    {
      "epoch": 4.1,
      "learning_rate": 0.0001,
      "loss": 0.9694,
      "step": 73600
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0001,
      "loss": 0.964,
      "step": 73700
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0001,
      "loss": 0.9781,
      "step": 73800
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.0001,
      "loss": 0.9856,
      "step": 73900
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.0001,
      "loss": 0.9701,
      "step": 74000
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0001,
      "loss": 0.9852,
      "step": 74100
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0001,
      "loss": 0.9599,
      "step": 74200
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.0001,
      "loss": 0.9781,
      "step": 74300
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.0001,
      "loss": 0.9763,
      "step": 74400
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.0001,
      "loss": 0.96,
      "step": 74500
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.0001,
      "loss": 0.9861,
      "step": 74600
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.0001,
      "loss": 0.9668,
      "step": 74700
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0001,
      "loss": 0.9688,
      "step": 74800
    },
    {
      "epoch": 4.17,
      "learning_rate": 0.0001,
      "loss": 0.9641,
      "step": 74900
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.0001,
      "loss": 0.9808,
      "step": 75000
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0001,
      "loss": 0.9752,
      "step": 75100
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.0001,
      "loss": 0.9704,
      "step": 75200
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0001,
      "loss": 0.9773,
      "step": 75300
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0001,
      "loss": 0.9838,
      "step": 75400
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0001,
      "loss": 0.9852,
      "step": 75500
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.0001,
      "loss": 0.9747,
      "step": 75600
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.0001,
      "loss": 0.9885,
      "step": 75700
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.0001,
      "loss": 0.9754,
      "step": 75800
    },
    {
      "epoch": 4.23,
      "learning_rate": 0.0001,
      "loss": 0.9806,
      "step": 75900
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.0001,
      "loss": 0.9874,
      "step": 76000
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.0001,
      "loss": 1.0192,
      "step": 76100
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0001,
      "loss": 0.9859,
      "step": 76200
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.0001,
      "loss": 0.9773,
      "step": 76300
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0001,
      "loss": 0.9796,
      "step": 76400
    },
    {
      "epoch": 4.26,
      "learning_rate": 0.0001,
      "loss": 0.9938,
      "step": 76500
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0001,
      "loss": 1.0031,
      "step": 76600
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.0001,
      "loss": 0.9829,
      "step": 76700
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.0001,
      "loss": 0.9869,
      "step": 76800
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0001,
      "loss": 0.9869,
      "step": 76900
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0001,
      "loss": 1.001,
      "step": 77000
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.0001,
      "loss": 1.0037,
      "step": 77100
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.0001,
      "loss": 0.9915,
      "step": 77200
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0001,
      "loss": 0.9749,
      "step": 77300
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.0001,
      "loss": 0.9784,
      "step": 77400
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.0001,
      "loss": 0.9886,
      "step": 77500
    },
    {
      "epoch": 4.32,
      "learning_rate": 0.0001,
      "loss": 1.015,
      "step": 77600
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0001,
      "loss": 1.016,
      "step": 77700
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0001,
      "loss": 0.9826,
      "step": 77800
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.0001,
      "loss": 1.002,
      "step": 77900
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.0001,
      "loss": 0.988,
      "step": 78000
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.0001,
      "loss": 0.991,
      "step": 78100
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0001,
      "loss": 0.9868,
      "step": 78200
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.0001,
      "loss": 1.0012,
      "step": 78300
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0001,
      "loss": 1.0,
      "step": 78400
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.0001,
      "loss": 1.0006,
      "step": 78500
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.0001,
      "loss": 0.9805,
      "step": 78600
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.0001,
      "loss": 0.9867,
      "step": 78700
    },
    {
      "epoch": 4.39,
      "learning_rate": 0.0001,
      "loss": 0.9934,
      "step": 78800
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.0001,
      "loss": 1.0039,
      "step": 78900
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.0001,
      "loss": 0.9835,
      "step": 79000
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0001,
      "loss": 0.9789,
      "step": 79100
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.0001,
      "loss": 1.003,
      "step": 79200
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.0001,
      "loss": 0.9873,
      "step": 79300
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.0001,
      "loss": 0.9907,
      "step": 79400
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.0001,
      "loss": 0.9987,
      "step": 79500
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0001,
      "loss": 1.0048,
      "step": 79600
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0001,
      "loss": 0.9998,
      "step": 79700
    },
    {
      "epoch": 4.45,
      "learning_rate": 0.0001,
      "loss": 0.9982,
      "step": 79800
    },
    {
      "epoch": 4.45,
      "learning_rate": 0.0001,
      "loss": 1.01,
      "step": 79900
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.0001,
      "loss": 0.9951,
      "step": 80000
    },
    {
      "epoch": 4.46,
      "eval_gen_len": 18.99970077797726,
      "eval_loss": 1.3570104837417603,
      "eval_rouge1": 25.3708,
      "eval_rouge2": 12.3846,
      "eval_rougeL": 20.9214,
      "eval_rougeLsum": 23.8807,
      "eval_runtime": 3270.2542,
      "eval_samples_per_second": 4.088,
      "eval_steps_per_second": 1.022,
      "step": 80000
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.0001,
      "loss": 0.9905,
      "step": 80100
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.0001,
      "loss": 1.0107,
      "step": 80200
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0001,
      "loss": 0.9988,
      "step": 80300
    },
    {
      "epoch": 4.48,
      "learning_rate": 0.0001,
      "loss": 1.0005,
      "step": 80400
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.0001,
      "loss": 0.9936,
      "step": 80500
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.0001,
      "loss": 0.9958,
      "step": 80600
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0001,
      "loss": 0.9994,
      "step": 80700
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.0001,
      "loss": 0.9882,
      "step": 80800
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0001,
      "loss": 1.0281,
      "step": 80900
    },
    {
      "epoch": 4.51,
      "learning_rate": 0.0001,
      "loss": 0.9902,
      "step": 81000
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.0001,
      "loss": 1.0179,
      "step": 81100
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.0001,
      "loss": 1.0022,
      "step": 81200
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.0001,
      "loss": 1.0152,
      "step": 81300
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.0001,
      "loss": 0.9934,
      "step": 81400
    },
    {
      "epoch": 4.54,
      "learning_rate": 0.0001,
      "loss": 0.9971,
      "step": 81500
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.0001,
      "loss": 1.001,
      "step": 81600
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.0001,
      "loss": 1.0226,
      "step": 81700
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0001,
      "loss": 1.0197,
      "step": 81800
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0001,
      "loss": 1.0071,
      "step": 81900
    },
    {
      "epoch": 4.57,
      "learning_rate": 0.0001,
      "loss": 0.9921,
      "step": 82000
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.0001,
      "loss": 1.009,
      "step": 82100
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.0001,
      "loss": 1.0027,
      "step": 82200
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.0001,
      "loss": 1.0062,
      "step": 82300
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.0001,
      "loss": 0.9977,
      "step": 82400
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0001,
      "loss": 1.0101,
      "step": 82500
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.0001,
      "loss": 1.0,
      "step": 82600
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.0001,
      "loss": 1.0212,
      "step": 82700
    },
    {
      "epoch": 4.61,
      "learning_rate": 0.0001,
      "loss": 1.0097,
      "step": 82800
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.0001,
      "loss": 1.0145,
      "step": 82900
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.0001,
      "loss": 1.0088,
      "step": 83000
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.0001,
      "loss": 0.9913,
      "step": 83100
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0001,
      "loss": 0.9983,
      "step": 83200
    },
    {
      "epoch": 4.64,
      "learning_rate": 0.0001,
      "loss": 1.0055,
      "step": 83300
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.0001,
      "loss": 1.0227,
      "step": 83400
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.0001,
      "loss": 1.0043,
      "step": 83500
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.0001,
      "loss": 1.0148,
      "step": 83600
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.0001,
      "loss": 1.0032,
      "step": 83700
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.0001,
      "loss": 1.0054,
      "step": 83800
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.0001,
      "loss": 1.0131,
      "step": 83900
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.0001,
      "loss": 1.006,
      "step": 84000
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.0001,
      "loss": 1.016,
      "step": 84100
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.0001,
      "loss": 1.01,
      "step": 84200
    },
    {
      "epoch": 4.7,
      "learning_rate": 0.0001,
      "loss": 1.0275,
      "step": 84300
    },
    {
      "epoch": 4.7,
      "learning_rate": 0.0001,
      "loss": 1.0129,
      "step": 84400
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0001,
      "loss": 1.0077,
      "step": 84500
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.0001,
      "loss": 1.0172,
      "step": 84600
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.0001,
      "loss": 1.0113,
      "step": 84700
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.0001,
      "loss": 0.9992,
      "step": 84800
    },
    {
      "epoch": 4.73,
      "learning_rate": 0.0001,
      "loss": 1.0109,
      "step": 84900
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.0001,
      "loss": 1.0169,
      "step": 85000
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.0001,
      "loss": 1.0032,
      "step": 85100
    },
    {
      "epoch": 4.75,
      "learning_rate": 0.0001,
      "loss": 1.042,
      "step": 85200
    },
    {
      "epoch": 4.75,
      "learning_rate": 0.0001,
      "loss": 1.0318,
      "step": 85300
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.0001,
      "loss": 1.0435,
      "step": 85400
    },
    {
      "epoch": 4.76,
      "learning_rate": 0.0001,
      "loss": 1.0147,
      "step": 85500
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.0001,
      "loss": 1.0264,
      "step": 85600
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0001,
      "loss": 1.0118,
      "step": 85700
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0001,
      "loss": 1.0113,
      "step": 85800
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0001,
      "loss": 1.0124,
      "step": 85900
    },
    {
      "epoch": 4.79,
      "learning_rate": 0.0001,
      "loss": 1.0214,
      "step": 86000
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0001,
      "loss": 1.0137,
      "step": 86100
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0001,
      "loss": 1.0218,
      "step": 86200
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0001,
      "loss": 0.9993,
      "step": 86300
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0001,
      "loss": 1.0283,
      "step": 86400
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.0001,
      "loss": 0.9851,
      "step": 86500
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.0001,
      "loss": 1.0117,
      "step": 86600
    },
    {
      "epoch": 4.83,
      "learning_rate": 0.0001,
      "loss": 1.023,
      "step": 86700
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.0001,
      "loss": 1.008,
      "step": 86800
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.0001,
      "loss": 1.0352,
      "step": 86900
    },
    {
      "epoch": 4.85,
      "learning_rate": 0.0001,
      "loss": 1.0129,
      "step": 87000
    },
    {
      "epoch": 4.85,
      "learning_rate": 0.0001,
      "loss": 1.0208,
      "step": 87100
    },
    {
      "epoch": 4.86,
      "learning_rate": 0.0001,
      "loss": 1.0053,
      "step": 87200
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.0001,
      "loss": 1.0232,
      "step": 87300
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.0001,
      "loss": 1.0193,
      "step": 87400
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.0001,
      "loss": 1.023,
      "step": 87500
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.0001,
      "loss": 1.0116,
      "step": 87600
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0001,
      "loss": 1.0352,
      "step": 87700
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0001,
      "loss": 1.0146,
      "step": 87800
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.0001,
      "loss": 1.0334,
      "step": 87900
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.0001,
      "loss": 1.0277,
      "step": 88000
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.0001,
      "loss": 1.0196,
      "step": 88100
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.0001,
      "loss": 1.0296,
      "step": 88200
    },
    {
      "epoch": 4.92,
      "learning_rate": 0.0001,
      "loss": 1.011,
      "step": 88300
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.0001,
      "loss": 1.024,
      "step": 88400
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.0001,
      "loss": 1.011,
      "step": 88500
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0001,
      "loss": 1.0203,
      "step": 88600
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0001,
      "loss": 1.0246,
      "step": 88700
    },
    {
      "epoch": 4.95,
      "learning_rate": 0.0001,
      "loss": 1.0289,
      "step": 88800
    },
    {
      "epoch": 4.95,
      "learning_rate": 0.0001,
      "loss": 1.0327,
      "step": 88900
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.0001,
      "loss": 1.0292,
      "step": 89000
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0001,
      "loss": 1.0436,
      "step": 89100
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.0001,
      "loss": 1.0365,
      "step": 89200
    },
    {
      "epoch": 4.98,
      "learning_rate": 0.0001,
      "loss": 1.0242,
      "step": 89300
    },
    {
      "epoch": 4.98,
      "learning_rate": 0.0001,
      "loss": 1.0268,
      "step": 89400
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0001,
      "loss": 1.0099,
      "step": 89500
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0001,
      "loss": 1.0217,
      "step": 89600
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0001,
      "loss": 1.0175,
      "step": 89700
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0001,
      "loss": 0.955,
      "step": 89800
    },
    {
      "epoch": 5.01,
      "learning_rate": 0.0001,
      "loss": 0.9126,
      "step": 89900
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.0001,
      "loss": 0.9248,
      "step": 90000
    },
    {
      "epoch": 5.02,
      "eval_gen_len": 18.999102333931777,
      "eval_loss": 1.387807846069336,
      "eval_rouge1": 25.1835,
      "eval_rouge2": 12.3016,
      "eval_rougeL": 20.7695,
      "eval_rougeLsum": 23.6703,
      "eval_runtime": 3246.1736,
      "eval_samples_per_second": 4.118,
      "eval_steps_per_second": 1.03,
      "step": 90000
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.0001,
      "loss": 0.9154,
      "step": 90100
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.0001,
      "loss": 0.9226,
      "step": 90200
    },
    {
      "epoch": 5.03,
      "learning_rate": 0.0001,
      "loss": 0.9256,
      "step": 90300
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.0001,
      "loss": 0.9212,
      "step": 90400
    },
    {
      "epoch": 5.04,
      "learning_rate": 0.0001,
      "loss": 0.919,
      "step": 90500
    },
    {
      "epoch": 5.05,
      "learning_rate": 0.0001,
      "loss": 0.9212,
      "step": 90600
    },
    {
      "epoch": 5.05,
      "learning_rate": 0.0001,
      "loss": 0.9249,
      "step": 90700
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.0001,
      "loss": 0.9047,
      "step": 90800
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.0001,
      "loss": 0.9238,
      "step": 90900
    },
    {
      "epoch": 5.07,
      "learning_rate": 0.0001,
      "loss": 0.9355,
      "step": 91000
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.0001,
      "loss": 0.9082,
      "step": 91100
    },
    {
      "epoch": 5.08,
      "learning_rate": 0.0001,
      "loss": 0.914,
      "step": 91200
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.0001,
      "loss": 0.9229,
      "step": 91300
    },
    {
      "epoch": 5.09,
      "learning_rate": 0.0001,
      "loss": 0.9374,
      "step": 91400
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.0001,
      "loss": 0.9287,
      "step": 91500
    },
    {
      "epoch": 5.1,
      "learning_rate": 0.0001,
      "loss": 0.9319,
      "step": 91600
    },
    {
      "epoch": 5.11,
      "learning_rate": 0.0001,
      "loss": 0.9241,
      "step": 91700
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.0001,
      "loss": 0.9242,
      "step": 91800
    },
    {
      "epoch": 5.12,
      "learning_rate": 0.0001,
      "loss": 0.9391,
      "step": 91900
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.0001,
      "loss": 0.9294,
      "step": 92000
    },
    {
      "epoch": 5.13,
      "learning_rate": 0.0001,
      "loss": 0.9301,
      "step": 92100
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.0001,
      "loss": 0.9061,
      "step": 92200
    },
    {
      "epoch": 5.14,
      "learning_rate": 0.0001,
      "loss": 0.9212,
      "step": 92300
    },
    {
      "epoch": 5.15,
      "learning_rate": 0.0001,
      "loss": 0.9396,
      "step": 92400
    },
    {
      "epoch": 5.15,
      "learning_rate": 0.0001,
      "loss": 0.9375,
      "step": 92500
    },
    {
      "epoch": 5.16,
      "learning_rate": 0.0001,
      "loss": 0.9482,
      "step": 92600
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.0001,
      "loss": 0.9203,
      "step": 92700
    },
    {
      "epoch": 5.17,
      "learning_rate": 0.0001,
      "loss": 0.9188,
      "step": 92800
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.0001,
      "loss": 0.9322,
      "step": 92900
    },
    {
      "epoch": 5.18,
      "learning_rate": 0.0001,
      "loss": 0.9444,
      "step": 93000
    },
    {
      "epoch": 5.19,
      "learning_rate": 0.0001,
      "loss": 0.9438,
      "step": 93100
    },
    {
      "epoch": 5.19,
      "learning_rate": 0.0001,
      "loss": 0.9364,
      "step": 93200
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.0001,
      "loss": 0.9458,
      "step": 93300
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.0001,
      "loss": 0.9326,
      "step": 93400
    },
    {
      "epoch": 5.21,
      "learning_rate": 0.0001,
      "loss": 0.9279,
      "step": 93500
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.0001,
      "loss": 0.9332,
      "step": 93600
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.0001,
      "loss": 0.9507,
      "step": 93700
    },
    {
      "epoch": 5.23,
      "learning_rate": 0.0001,
      "loss": 0.9336,
      "step": 93800
    },
    {
      "epoch": 5.23,
      "learning_rate": 0.0001,
      "loss": 0.9551,
      "step": 93900
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.0001,
      "loss": 0.9522,
      "step": 94000
    },
    {
      "epoch": 5.24,
      "learning_rate": 0.0001,
      "loss": 0.9294,
      "step": 94100
    },
    {
      "epoch": 5.25,
      "learning_rate": 0.0001,
      "loss": 0.938,
      "step": 94200
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.0001,
      "loss": 0.9548,
      "step": 94300
    },
    {
      "epoch": 5.26,
      "learning_rate": 0.0001,
      "loss": 0.9333,
      "step": 94400
    },
    {
      "epoch": 5.27,
      "learning_rate": 0.0001,
      "loss": 0.9431,
      "step": 94500
    },
    {
      "epoch": 5.27,
      "learning_rate": 0.0001,
      "loss": 0.9423,
      "step": 94600
    },
    {
      "epoch": 5.28,
      "learning_rate": 0.0001,
      "loss": 0.9342,
      "step": 94700
    },
    {
      "epoch": 5.28,
      "learning_rate": 0.0001,
      "loss": 0.924,
      "step": 94800
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.0001,
      "loss": 0.948,
      "step": 94900
    },
    {
      "epoch": 5.29,
      "learning_rate": 0.0001,
      "loss": 0.9452,
      "step": 95000
    },
    {
      "epoch": 5.3,
      "learning_rate": 0.0001,
      "loss": 0.9575,
      "step": 95100
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.0001,
      "loss": 0.9564,
      "step": 95200
    },
    {
      "epoch": 5.31,
      "learning_rate": 0.0001,
      "loss": 0.9493,
      "step": 95300
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.0001,
      "loss": 0.9519,
      "step": 95400
    },
    {
      "epoch": 5.32,
      "learning_rate": 0.0001,
      "loss": 0.9468,
      "step": 95500
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.0001,
      "loss": 0.9341,
      "step": 95600
    },
    {
      "epoch": 5.33,
      "learning_rate": 0.0001,
      "loss": 0.9477,
      "step": 95700
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0001,
      "loss": 0.9368,
      "step": 95800
    },
    {
      "epoch": 5.34,
      "learning_rate": 0.0001,
      "loss": 0.9488,
      "step": 95900
    },
    {
      "epoch": 5.35,
      "learning_rate": 0.0001,
      "loss": 0.9441,
      "step": 96000
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.0001,
      "loss": 0.925,
      "step": 96100
    },
    {
      "epoch": 5.36,
      "learning_rate": 0.0001,
      "loss": 0.9447,
      "step": 96200
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.0001,
      "loss": 0.9559,
      "step": 96300
    },
    {
      "epoch": 5.37,
      "learning_rate": 0.0001,
      "loss": 0.9435,
      "step": 96400
    },
    {
      "epoch": 5.38,
      "learning_rate": 0.0001,
      "loss": 0.9412,
      "step": 96500
    },
    {
      "epoch": 5.38,
      "learning_rate": 0.0001,
      "loss": 0.9325,
      "step": 96600
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.0001,
      "loss": 0.9463,
      "step": 96700
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.0001,
      "loss": 0.97,
      "step": 96800
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.0001,
      "loss": 0.9689,
      "step": 96900
    },
    {
      "epoch": 5.41,
      "learning_rate": 0.0001,
      "loss": 0.9555,
      "step": 97000
    },
    {
      "epoch": 5.41,
      "learning_rate": 0.0001,
      "loss": 0.9566,
      "step": 97100
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.0001,
      "loss": 0.963,
      "step": 97200
    },
    {
      "epoch": 5.42,
      "learning_rate": 0.0001,
      "loss": 0.9564,
      "step": 97300
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.0001,
      "loss": 0.9583,
      "step": 97400
    },
    {
      "epoch": 5.43,
      "learning_rate": 0.0001,
      "loss": 0.9451,
      "step": 97500
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.0001,
      "loss": 0.9509,
      "step": 97600
    },
    {
      "epoch": 5.44,
      "learning_rate": 0.0001,
      "loss": 0.9542,
      "step": 97700
    },
    {
      "epoch": 5.45,
      "learning_rate": 0.0001,
      "loss": 0.9591,
      "step": 97800
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.0001,
      "loss": 0.9497,
      "step": 97900
    },
    {
      "epoch": 5.46,
      "learning_rate": 0.0001,
      "loss": 0.944,
      "step": 98000
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.0001,
      "loss": 0.943,
      "step": 98100
    },
    {
      "epoch": 5.47,
      "learning_rate": 0.0001,
      "loss": 0.9601,
      "step": 98200
    },
    {
      "epoch": 5.48,
      "learning_rate": 0.0001,
      "loss": 0.971,
      "step": 98300
    },
    {
      "epoch": 5.48,
      "learning_rate": 0.0001,
      "loss": 0.9485,
      "step": 98400
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.0001,
      "loss": 0.9623,
      "step": 98500
    },
    {
      "epoch": 5.49,
      "learning_rate": 0.0001,
      "loss": 0.9329,
      "step": 98600
    },
    {
      "epoch": 5.5,
      "learning_rate": 0.0001,
      "loss": 0.9501,
      "step": 98700
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.0001,
      "loss": 0.9386,
      "step": 98800
    },
    {
      "epoch": 5.51,
      "learning_rate": 0.0001,
      "loss": 0.9706,
      "step": 98900
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.0001,
      "loss": 0.964,
      "step": 99000
    },
    {
      "epoch": 5.52,
      "learning_rate": 0.0001,
      "loss": 0.9619,
      "step": 99100
    },
    {
      "epoch": 5.53,
      "learning_rate": 0.0001,
      "loss": 0.9607,
      "step": 99200
    },
    {
      "epoch": 5.53,
      "learning_rate": 0.0001,
      "loss": 0.9416,
      "step": 99300
    },
    {
      "epoch": 5.54,
      "learning_rate": 0.0001,
      "loss": 0.9538,
      "step": 99400
    },
    {
      "epoch": 5.55,
      "learning_rate": 0.0001,
      "loss": 0.9661,
      "step": 99500
    },
    {
      "epoch": 5.55,
      "learning_rate": 0.0001,
      "loss": 0.9551,
      "step": 99600
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.0001,
      "loss": 0.9453,
      "step": 99700
    },
    {
      "epoch": 5.56,
      "learning_rate": 0.0001,
      "loss": 0.9613,
      "step": 99800
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.0001,
      "loss": 0.956,
      "step": 99900
    },
    {
      "epoch": 5.57,
      "learning_rate": 0.0001,
      "loss": 0.9499,
      "step": 100000
    },
    {
      "epoch": 5.57,
      "eval_gen_len": 18.999476361460204,
      "eval_loss": 1.3799935579299927,
      "eval_rouge1": 25.41,
      "eval_rouge2": 12.467,
      "eval_rougeL": 20.9576,
      "eval_rougeLsum": 23.919,
      "eval_runtime": 3255.4245,
      "eval_samples_per_second": 4.106,
      "eval_steps_per_second": 1.027,
      "step": 100000
    }
  ],
  "max_steps": 502432,
  "num_train_epochs": 28,
  "total_flos": 6.80037621812736e+18,
  "trial_name": null,
  "trial_params": null
}