{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 75,
  "global_step": 297,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1e-06,
      "loss": 0.9799,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-06,
      "loss": 1.0088,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-06,
      "loss": 1.0716,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-06,
      "loss": 0.8604,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 5e-06,
      "loss": 0.8246,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 6e-06,
      "loss": 0.8132,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 7e-06,
      "loss": 0.6148,
      "step": 7
    },
    {
      "epoch": 0.03,
      "learning_rate": 8e-06,
      "loss": 0.7729,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 9e-06,
      "loss": 0.7227,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.999732272500674e-06,
      "loss": 0.8967,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.998929121859591e-06,
      "loss": 1.0003,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.997590643643646e-06,
      "loss": 0.8262,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.99571699711836e-06,
      "loss": 0.9495,
      "step": 13
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.993308405228933e-06,
      "loss": 0.8094,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.990365154573717e-06,
      "loss": 0.8528,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.9868875953701e-06,
      "loss": 0.8767,
      "step": 16
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.982876141412855e-06,
      "loss": 0.8405,
      "step": 17
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.978331270024886e-06,
      "loss": 0.9105,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.973253522000438e-06,
      "loss": 0.9109,
      "step": 19
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.967643501540747e-06,
      "loss": 0.8691,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.961501876182148e-06,
      "loss": 0.7543,
      "step": 21
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.954829376716635e-06,
      "loss": 0.7925,
      "step": 22
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.947626797104924e-06,
      "loss": 0.8162,
      "step": 23
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.939894994381956e-06,
      "loss": 0.7787,
      "step": 24
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.931634888554937e-06,
      "loss": 0.8244,
      "step": 25
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.922847462493856e-06,
      "loss": 0.8088,
      "step": 26
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.913533761814537e-06,
      "loss": 0.8405,
      "step": 27
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.903694894754222e-06,
      "loss": 0.8361,
      "step": 28
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.8933320320397e-06,
      "loss": 0.6428,
      "step": 29
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.882446406748002e-06,
      "loss": 0.6581,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.871039314159675e-06,
      "loss": 0.8059,
      "step": 31
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.859112111604669e-06,
      "loss": 0.8403,
      "step": 32
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.846666218300807e-06,
      "loss": 0.712,
      "step": 33
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.833703115184932e-06,
      "loss": 0.7188,
      "step": 34
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.82022434473668e-06,
      "loss": 0.7583,
      "step": 35
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.80623151079494e-06,
      "loss": 0.7899,
      "step": 36
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.791726278367021e-06,
      "loss": 0.8039,
      "step": 37
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.776710373430525e-06,
      "loss": 0.8014,
      "step": 38
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.761185582727977e-06,
      "loss": 0.8441,
      "step": 39
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.745153753554214e-06,
      "loss": 0.6469,
      "step": 40
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.728616793536588e-06,
      "loss": 0.711,
      "step": 41
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.711576670407966e-06,
      "loss": 0.6167,
      "step": 42
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.694035411772595e-06,
      "loss": 0.8141,
      "step": 43
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.675995104864831e-06,
      "loss": 0.5856,
      "step": 44
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.65745789630079e-06,
      "loss": 0.6113,
      "step": 45
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.638425991822915e-06,
      "loss": 0.8029,
      "step": 46
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.618901656037513e-06,
      "loss": 0.7917,
      "step": 47
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.598887212145291e-06,
      "loss": 0.6432,
      "step": 48
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.578385041664925e-06,
      "loss": 0.6574,
      "step": 49
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.557397584149673e-06,
      "loss": 0.5809,
      "step": 50
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.535927336897097e-06,
      "loss": 0.6016,
      "step": 51
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.513976854651913e-06,
      "loss": 0.6247,
      "step": 52
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.491548749301997e-06,
      "loss": 0.5538,
      "step": 53
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.468645689567598e-06,
      "loss": 0.6069,
      "step": 54
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.445270400683786e-06,
      "loss": 0.6994,
      "step": 55
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.421425664076177e-06,
      "loss": 0.5385,
      "step": 56
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.397114317029975e-06,
      "loss": 0.7693,
      "step": 57
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.372339252352355e-06,
      "loss": 0.6196,
      "step": 58
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.347103418028259e-06,
      "loss": 0.7083,
      "step": 59
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.321409816869605e-06,
      "loss": 0.6298,
      "step": 60
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.295261506157985e-06,
      "loss": 0.5166,
      "step": 61
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.268661597280886e-06,
      "loss": 0.7171,
      "step": 62
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.241613255361455e-06,
      "loss": 0.7374,
      "step": 63
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.214119698881887e-06,
      "loss": 0.5147,
      "step": 64
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.186184199300463e-06,
      "loss": 0.7629,
      "step": 65
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.157810080662269e-06,
      "loss": 0.6447,
      "step": 66
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.129000719203673e-06,
      "loss": 0.5669,
      "step": 67
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.099759542950583e-06,
      "loss": 0.6644,
      "step": 68
    },
    {
      "epoch": 0.23,
      "learning_rate": 8.070090031310558e-06,
      "loss": 0.637,
      "step": 69
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.039995714658776e-06,
      "loss": 0.6364,
      "step": 70
    },
    {
      "epoch": 0.24,
      "learning_rate": 8.009480173917969e-06,
      "loss": 0.6313,
      "step": 71
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.978547040132316e-06,
      "loss": 0.6522,
      "step": 72
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.947199994035401e-06,
      "loss": 0.6039,
      "step": 73
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.915442765612229e-06,
      "loss": 0.5923,
      "step": 74
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.883279133655398e-06,
      "loss": 0.5145,
      "step": 75
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.8153410115496591,
      "eval_accuracy_<|content|>": 0.9983489268024216,
      "eval_accuracy_<|from|>": 0.975,
      "eval_accuracy_<|recipient|>": 0.7946428571428571,
      "eval_accuracy_<|stop|>": 0.8509316770186336,
      "eval_accuracy_total_num_<|content|>": 3634,
      "eval_accuracy_total_num_<|from|>": 560,
      "eval_accuracy_total_num_<|recipient|>": 560,
      "eval_accuracy_total_num_<|stop|>": 3059,
      "eval_loss": 0.6158567070960999,
      "eval_perplexity": 1.0609388823519776,
      "eval_runtime": 222.2983,
      "eval_samples_per_second": 4.705,
      "eval_steps_per_second": 0.148,
      "step": 75
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.850712925315468e-06,
      "loss": 0.7307,
      "step": 76
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.817748015645558e-06,
      "loss": 0.6347,
      "step": 77
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.78438832714026e-06,
      "loss": 0.5611,
      "step": 78
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.7506378292689e-06,
      "loss": 0.5914,
      "step": 79
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.716500538003208e-06,
      "loss": 0.4936,
      "step": 80
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.681980515339464e-06,
      "loss": 0.543,
      "step": 81
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.647081868815153e-06,
      "loss": 0.5267,
      "step": 82
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.611808751020213e-06,
      "loss": 0.6759,
      "step": 83
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.57616535910292e-06,
      "loss": 0.5291,
      "step": 84
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.540155934270472e-06,
      "loss": 0.7263,
      "step": 85
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.5037847612843135e-06,
      "loss": 0.6477,
      "step": 86
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.46705616795031e-06,
      "loss": 0.6295,
      "step": 87
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.429974524603771e-06,
      "loss": 0.5567,
      "step": 88
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.392544243589427e-06,
      "loss": 0.5361,
      "step": 89
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.354769778736405e-06,
      "loss": 0.752,
      "step": 90
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.316655624828267e-06,
      "loss": 0.581,
      "step": 91
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.278206317068173e-06,
      "loss": 0.5523,
      "step": 92
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.239426430539243e-06,
      "loss": 0.6416,
      "step": 93
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.2003205796601645e-06,
      "loss": 0.6665,
      "step": 94
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.160893417636121e-06,
      "loss": 0.7361,
      "step": 95
    },
    {
      "epoch": 0.32,
      "learning_rate": 7.121149635905111e-06,
      "loss": 0.507,
      "step": 96
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.081093963579708e-06,
      "loss": 0.6335,
      "step": 97
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.040731166884352e-06,
      "loss": 0.545,
      "step": 98
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.00006604858821e-06,
      "loss": 0.7382,
      "step": 99
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.959103447433696e-06,
      "loss": 0.7749,
      "step": 100
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.917848237560708e-06,
      "loss": 0.5616,
      "step": 101
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.876305327926656e-06,
      "loss": 0.6483,
      "step": 102
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.834479661722347e-06,
      "loss": 0.7207,
      "step": 103
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.792376215783789e-06,
      "loss": 0.5815,
      "step": 104
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.75e-06,
      "loss": 0.4725,
      "step": 105
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.707356056716886e-06,
      "loss": 0.7133,
      "step": 106
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.664449460137245e-06,
      "loss": 0.5666,
      "step": 107
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.621285315716991e-06,
      "loss": 0.545,
      "step": 108
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.5778687595576535e-06,
      "loss": 0.7437,
      "step": 109
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.5342049577952396e-06,
      "loss": 0.5496,
      "step": 110
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.490299105985506e-06,
      "loss": 0.5883,
      "step": 111
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.446156428485748e-06,
      "loss": 0.5355,
      "step": 112
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.401782177833148e-06,
      "loss": 0.6925,
      "step": 113
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.357181634119776e-06,
      "loss": 0.7328,
      "step": 114
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.312360104364318e-06,
      "loss": 0.6417,
      "step": 115
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.267322921880584e-06,
      "loss": 0.6352,
      "step": 116
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.222075445642905e-06,
      "loss": 0.6245,
      "step": 117
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.176623059648463e-06,
      "loss": 0.572,
      "step": 118
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.130971172276657e-06,
      "loss": 0.5957,
      "step": 119
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.085125215645551e-06,
      "loss": 0.5968,
      "step": 120
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.03909064496551e-06,
      "loss": 0.7397,
      "step": 121
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.992872937890085e-06,
      "loss": 0.4958,
      "step": 122
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.946477593864227e-06,
      "loss": 0.6392,
      "step": 123
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.899910133469909e-06,
      "loss": 0.5666,
      "step": 124
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.853176097769229e-06,
      "loss": 0.4596,
      "step": 125
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.80628104764508e-06,
      "loss": 0.6385,
      "step": 126
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.7592305631394655e-06,
      "loss": 0.578,
      "step": 127
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.7120302427895185e-06,
      "loss": 0.8049,
      "step": 128
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.664685702961344e-06,
      "loss": 0.4874,
      "step": 129
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.617202577181723e-06,
      "loss": 0.5195,
      "step": 130
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.569586515467779e-06,
      "loss": 0.6092,
      "step": 131
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.521843183654679e-06,
      "loss": 0.6794,
      "step": 132
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.473978262721463e-06,
      "loss": 0.4674,
      "step": 133
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.425997448115057e-06,
      "loss": 0.5482,
      "step": 134
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.377906449072578e-06,
      "loss": 0.4731,
      "step": 135
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.3297109879419855e-06,
      "loss": 0.6931,
      "step": 136
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.281416799501187e-06,
      "loss": 0.5254,
      "step": 137
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.23302963027565e-06,
      "loss": 0.5313,
      "step": 138
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.184555237854625e-06,
      "loss": 0.5622,
      "step": 139
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.1359993902060545e-06,
      "loss": 0.5621,
      "step": 140
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.087367864990233e-06,
      "loss": 0.5534,
      "step": 141
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.038666448872331e-06,
      "loss": 0.5932,
      "step": 142
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.989900936833841e-06,
      "loss": 0.5931,
      "step": 143
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.941077131483024e-06,
      "loss": 0.5631,
      "step": 144
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.892200842364463e-06,
      "loss": 0.6102,
      "step": 145
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.843277885267786e-06,
      "loss": 0.6519,
      "step": 146
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.794314081535644e-06,
      "loss": 0.4957,
      "step": 147
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.745315257371029e-06,
      "loss": 0.6076,
      "step": 148
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.696287243144012e-06,
      "loss": 0.6205,
      "step": 149
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.647235872697993e-06,
      "loss": 0.5454,
      "step": 150
    },
    {
      "epoch": 0.51,
      "eval_accuracy": 0.8247416654541203,
      "eval_accuracy_<|content|>": 1.0,
      "eval_accuracy_<|from|>": 0.9892857142857143,
      "eval_accuracy_<|recipient|>": 1.0,
      "eval_accuracy_<|stop|>": 0.8996404053612291,
      "eval_accuracy_total_num_<|content|>": 3634,
      "eval_accuracy_total_num_<|from|>": 560,
      "eval_accuracy_total_num_<|recipient|>": 560,
      "eval_accuracy_total_num_<|stop|>": 3059,
      "eval_loss": 0.5723979473114014,
      "eval_perplexity": 1.056601002074663,
      "eval_runtime": 170.3858,
      "eval_samples_per_second": 6.139,
      "eval_steps_per_second": 0.194,
      "step": 150
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.598166982655526e-06,
      "loss": 0.6884,
      "step": 151
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.549086411723821e-06,
      "loss": 0.5796,
      "step": 152
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.5e-06,
      "loss": 0.5955,
      "step": 153
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.45091358827618e-06,
      "loss": 0.5985,
      "step": 154
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.401833017344475e-06,
      "loss": 0.451,
      "step": 155
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.352764127302008e-06,
      "loss": 0.7329,
      "step": 156
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.303712756855989e-06,
      "loss": 0.6437,
      "step": 157
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.254684742628971e-06,
      "loss": 0.4884,
      "step": 158
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.205685918464356e-06,
      "loss": 0.5665,
      "step": 159
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.156722114732214e-06,
      "loss": 0.5799,
      "step": 160
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.107799157635538e-06,
      "loss": 0.6255,
      "step": 161
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.058922868516977e-06,
      "loss": 0.6124,
      "step": 162
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.01009906316616e-06,
      "loss": 0.5434,
      "step": 163
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.96133355112767e-06,
      "loss": 0.565,
      "step": 164
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.912632135009769e-06,
      "loss": 0.4637,
      "step": 165
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.8640006097939474e-06,
      "loss": 0.5655,
      "step": 166
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.815444762145375e-06,
      "loss": 0.6105,
      "step": 167
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.7669703697243513e-06,
      "loss": 0.5689,
      "step": 168
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.718583200498814e-06,
      "loss": 0.6725,
      "step": 169
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.6702890120580148e-06,
      "loss": 0.4064,
      "step": 170
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.6220935509274233e-06,
      "loss": 0.4969,
      "step": 171
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.5740025518849432e-06,
      "loss": 0.5846,
      "step": 172
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.5260217372785372e-06,
      "loss": 0.5228,
      "step": 173
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.478156816345321e-06,
      "loss": 0.603,
      "step": 174
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.4304134845322217e-06,
      "loss": 0.6142,
      "step": 175
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.3827974228182764e-06,
      "loss": 0.5525,
      "step": 176
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.335314297038656e-06,
      "loss": 0.637,
      "step": 177
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.287969757210483e-06,
      "loss": 0.4829,
      "step": 178
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.240769436860536e-06,
      "loss": 0.7065,
      "step": 179
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.1937189523549205e-06,
      "loss": 0.4831,
      "step": 180
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.1468239022307714e-06,
      "loss": 0.535,
      "step": 181
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.1000898665300915e-06,
      "loss": 0.5843,
      "step": 182
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.053522406135774e-06,
      "loss": 0.5178,
      "step": 183
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.007127062109917e-06,
      "loss": 0.5917,
      "step": 184
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.9609093550344912e-06,
      "loss": 0.5379,
      "step": 185
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.9148747843544492e-06,
      "loss": 0.6937,
      "step": 186
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.869028827723343e-06,
      "loss": 0.4999,
      "step": 187
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.823376940351537e-06,
      "loss": 0.6532,
      "step": 188
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.7779245543570964e-06,
      "loss": 0.4854,
      "step": 189
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.7326770781194174e-06,
      "loss": 0.54,
      "step": 190
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.6876398956356833e-06,
      "loss": 0.4441,
      "step": 191
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.642818365880224e-06,
      "loss": 0.551,
      "step": 192
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.5982178221668532e-06,
      "loss": 0.6079,
      "step": 193
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.5538435715142517e-06,
      "loss": 0.5439,
      "step": 194
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.5097008940144952e-06,
      "loss": 0.6502,
      "step": 195
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.4657950422047615e-06,
      "loss": 0.5396,
      "step": 196
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.4221312404423484e-06,
      "loss": 0.6481,
      "step": 197
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.3787146842830103e-06,
      "loss": 0.5903,
      "step": 198
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.3355505398627564e-06,
      "loss": 0.5244,
      "step": 199
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.292643943283114e-06,
      "loss": 0.6796,
      "step": 200
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.250000000000001e-06,
      "loss": 0.6146,
      "step": 201
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.207623784216212e-06,
      "loss": 0.5408,
      "step": 202
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.1655203382776525e-06,
      "loss": 0.6249,
      "step": 203
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.123694672073344e-06,
      "loss": 0.5816,
      "step": 204
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.082151762439292e-06,
      "loss": 0.4743,
      "step": 205
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.040896552566305e-06,
      "loss": 0.6727,
      "step": 206
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.999933951411791e-06,
      "loss": 0.4752,
      "step": 207
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.9592688331156483e-06,
      "loss": 0.5629,
      "step": 208
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.9189060364202938e-06,
      "loss": 0.4636,
      "step": 209
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8788503640948908e-06,
      "loss": 0.5113,
      "step": 210
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8391065823638805e-06,
      "loss": 0.4424,
      "step": 211
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.7996794203398362e-06,
      "loss": 0.4023,
      "step": 212
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.760573569460757e-06,
      "loss": 0.5816,
      "step": 213
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.7217936829318283e-06,
      "loss": 0.5428,
      "step": 214
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.6833443751717342e-06,
      "loss": 0.4079,
      "step": 215
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.6452302212635958e-06,
      "loss": 0.614,
      "step": 216
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.6074557564105728e-06,
      "loss": 0.3744,
      "step": 217
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.5700254753962297e-06,
      "loss": 0.7146,
      "step": 218
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.5329438320496903e-06,
      "loss": 0.4597,
      "step": 219
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.4962152387156875e-06,
      "loss": 0.5789,
      "step": 220
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.459844065729529e-06,
      "loss": 0.5392,
      "step": 221
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.423834640897079e-06,
      "loss": 0.6789,
      "step": 222
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.3881912489797881e-06,
      "loss": 0.6218,
      "step": 223
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.3529181311848478e-06,
      "loss": 0.5378,
      "step": 224
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.3180194846605365e-06,
      "loss": 0.4189,
      "step": 225
    },
    {
      "epoch": 0.76,
      "eval_accuracy": 0.8321450379495904,
      "eval_accuracy_<|content|>": 1.0,
      "eval_accuracy_<|from|>": 0.9946428571428572,
      "eval_accuracy_<|recipient|>": 1.0,
      "eval_accuracy_<|stop|>": 0.9150049035632559,
      "eval_accuracy_total_num_<|content|>": 3634,
      "eval_accuracy_total_num_<|from|>": 560,
      "eval_accuracy_total_num_<|recipient|>": 560,
      "eval_accuracy_total_num_<|stop|>": 3059,
      "eval_loss": 0.5402337908744812,
      "eval_perplexity": 1.0533657385611068,
      "eval_runtime": 170.1194,
      "eval_samples_per_second": 6.149,
      "eval_steps_per_second": 0.194,
      "step": 225
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.2834994619967923e-06,
      "loss": 0.4984,
      "step": 226
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.2493621707311002e-06,
      "loss": 0.4659,
      "step": 227
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.2156116728597408e-06,
      "loss": 0.5902,
      "step": 228
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.1822519843544422e-06,
      "loss": 0.6117,
      "step": 229
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.1492870746845319e-06,
      "loss": 0.6365,
      "step": 230
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.1167208663446024e-06,
      "loss": 0.5319,
      "step": 231
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.0845572343877717e-06,
      "loss": 0.5895,
      "step": 232
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.0528000059645994e-06,
      "loss": 0.5318,
      "step": 233
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.0214529598676836e-06,
      "loss": 0.6035,
      "step": 234
    },
    {
      "epoch": 0.79,
      "learning_rate": 9.905198260820328e-07,
      "loss": 0.5598,
      "step": 235
    },
    {
      "epoch": 0.79,
      "learning_rate": 9.600042853412235e-07,
      "loss": 0.5064,
      "step": 236
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.299099686894423e-07,
      "loss": 0.6721,
      "step": 237
    },
    {
      "epoch": 0.8,
      "learning_rate": 9.002404570494167e-07,
      "loss": 0.5706,
      "step": 238
    },
    {
      "epoch": 0.8,
      "learning_rate": 8.709992807963281e-07,
      "loss": 0.6527,
      "step": 239
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.42189919337732e-07,
      "loss": 0.6001,
      "step": 240
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.138158006995364e-07,
      "loss": 0.6725,
      "step": 241
    },
    {
      "epoch": 0.81,
      "learning_rate": 7.85880301118113e-07,
      "loss": 0.4701,
      "step": 242
    },
    {
      "epoch": 0.82,
      "learning_rate": 7.58386744638546e-07,
      "loss": 0.5473,
      "step": 243
    },
    {
      "epoch": 0.82,
      "learning_rate": 7.313384027191149e-07,
      "loss": 0.5739,
      "step": 244
    },
    {
      "epoch": 0.82,
      "learning_rate": 7.047384938420153e-07,
      "loss": 0.367,
      "step": 245
    },
    {
      "epoch": 0.83,
      "learning_rate": 6.785901831303956e-07,
      "loss": 0.4433,
      "step": 246
    },
    {
      "epoch": 0.83,
      "learning_rate": 6.528965819717413e-07,
      "loss": 0.4839,
      "step": 247
    },
    {
      "epoch": 0.84,
      "learning_rate": 6.27660747647645e-07,
      "loss": 0.6045,
      "step": 248
    },
    {
      "epoch": 0.84,
      "learning_rate": 6.028856829700259e-07,
      "loss": 0.565,
      "step": 249
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.785743359238243e-07,
      "loss": 0.5618,
      "step": 250
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.547295993162155e-07,
      "loss": 0.397,
      "step": 251
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.313543104324028e-07,
      "loss": 0.5715,
      "step": 252
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.084512506980023e-07,
      "loss": 0.5927,
      "step": 253
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.860231453480866e-07,
      "loss": 0.4835,
      "step": 254
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.640726631029029e-07,
      "loss": 0.5396,
      "step": 255
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.426024158503282e-07,
      "loss": 0.4446,
      "step": 256
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.216149583350753e-07,
      "loss": 0.5833,
      "step": 257
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.0111278785470846e-07,
      "loss": 0.478,
      "step": 258
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.8109834396248805e-07,
      "loss": 0.5802,
      "step": 259
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.6157400817708485e-07,
      "loss": 0.4553,
      "step": 260
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.425421036992097e-07,
      "loss": 0.5408,
      "step": 261
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.2400489513517e-07,
      "loss": 0.4659,
      "step": 262
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.0596458822740705e-07,
      "loss": 0.3709,
      "step": 263
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.884233295920351e-07,
      "loss": 0.3811,
      "step": 264
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.713832064634126e-07,
      "loss": 0.5523,
      "step": 265
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.548462464457865e-07,
      "loss": 0.5376,
      "step": 266
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.388144172720249e-07,
      "loss": 0.5279,
      "step": 267
    },
    {
      "epoch": 0.9,
      "learning_rate": 2.23289626569475e-07,
      "loss": 0.5563,
      "step": 268
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.082737216329793e-07,
      "loss": 0.451,
      "step": 269
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.937684892050603e-07,
      "loss": 0.6432,
      "step": 270
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.797756552633213e-07,
      "loss": 0.4673,
      "step": 271
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.6629688481506783e-07,
      "loss": 0.5042,
      "step": 272
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.533337816991931e-07,
      "loss": 0.7103,
      "step": 273
    },
    {
      "epoch": 0.92,
      "learning_rate": 1.408878883953311e-07,
      "loss": 0.4237,
      "step": 274
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.2896068584032355e-07,
      "loss": 0.4941,
      "step": 275
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.1755359325199866e-07,
      "loss": 0.6746,
      "step": 276
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.0666796796029987e-07,
      "loss": 0.5323,
      "step": 277
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.630510524577751e-08,
      "loss": 0.5387,
      "step": 278
    },
    {
      "epoch": 0.94,
      "learning_rate": 8.646623818546307e-08,
      "loss": 0.5481,
      "step": 279
    },
    {
      "epoch": 0.94,
      "learning_rate": 7.715253750614503e-08,
      "loss": 0.5632,
      "step": 280
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.836511144506392e-08,
      "loss": 0.6036,
      "step": 281
    },
    {
      "epoch": 0.95,
      "learning_rate": 6.01050056180446e-08,
      "loss": 0.4902,
      "step": 282
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.237320289507702e-08,
      "loss": 0.4684,
      "step": 283
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.517062328336458e-08,
      "loss": 0.525,
      "step": 284
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.849812381785328e-08,
      "loss": 0.5128,
      "step": 285
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.235649845925231e-08,
      "loss": 0.7175,
      "step": 286
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.674647799956159e-08,
      "loss": 0.5206,
      "step": 287
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.166872997511432e-08,
      "loss": 0.6999,
      "step": 288
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.7123858587145047e-08,
      "loss": 0.4856,
      "step": 289
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.3112404629900154e-08,
      "loss": 0.6217,
      "step": 290
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.634845426284344e-09,
      "loss": 0.6083,
      "step": 291
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.691594771066067e-09,
      "loss": 0.6078,
      "step": 292
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.283002881639908e-09,
      "loss": 0.5348,
      "step": 293
    },
    {
      "epoch": 0.99,
      "learning_rate": 2.4093563563544198e-09,
      "loss": 0.5764,
      "step": 294
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.070878140408904e-09,
      "loss": 0.5528,
      "step": 295
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.6772749932613136e-10,
      "loss": 0.6354,
      "step": 296
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.3309,
      "step": 297
    },
    {
      "epoch": 1.0,
      "step": 297,
      "total_flos": 124371515473920.0,
      "train_loss": 0.6121062839071357,
      "train_runtime": 9946.9361,
      "train_samples_per_second": 0.953,
      "train_steps_per_second": 0.03
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 297,
  "num_train_epochs": 1,
  "save_steps": 200.0,
  "total_flos": 124371515473920.0,
  "trial_name": null,
  "trial_params": null
}