{
  "best_global_step": 280,
  "best_metric": 1.8434581756591797,
  "best_model_checkpoint": "/workspace/scripts/soutputs/0fe99f84-0038-4cec-8e61-1eb9fea8dc55_8/checkpoint-280",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 8.88685131072998,
      "learning_rate": 1.7366143371721805e-05,
      "loss": 4.6453,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 4.32283353805542,
      "learning_rate": 3.907382258637406e-05,
      "loss": 3.599,
      "step": 10
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 3.268484592437744,
      "learning_rate": 6.078150180102633e-05,
      "loss": 3.1074,
      "step": 15
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.8239047527313232,
      "learning_rate": 8.248918101567858e-05,
      "loss": 2.8444,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 3.067504644393921,
      "learning_rate": 0.00010419686023033085,
      "loss": 2.6663,
      "step": 25
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 2.57623553276062,
      "learning_rate": 0.0001259045394449831,
      "loss": 2.5882,
      "step": 30
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.359346628189087,
      "learning_rate": 0.00014761221865963536,
      "loss": 2.5005,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.330860137939453,
      "learning_rate": 0.00015192340354349201,
      "loss": 2.4555,
      "step": 40
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 2.0505852699279785,
      "learning_rate": 0.0001518001581828618,
      "loss": 2.3906,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 1.8215535879135132,
      "learning_rate": 0.00015158232645757987,
      "loss": 2.3629,
      "step": 50
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 1.6129544973373413,
      "learning_rate": 0.0001512702709270553,
      "loss": 2.3095,
      "step": 55
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.5386137962341309,
      "learning_rate": 0.00015086451097692214,
      "loss": 2.2798,
      "step": 60
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 1.697199821472168,
      "learning_rate": 0.00015036572195457326,
      "loss": 2.2578,
      "step": 65
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.7271143198013306,
      "learning_rate": 0.00014977473404511135,
      "loss": 2.2371,
      "step": 70
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 1.7022008895874023,
      "learning_rate": 0.00014909253088958753,
      "loss": 2.2332,
      "step": 75
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.5951184034347534,
      "learning_rate": 0.00014832024794782817,
      "loss": 2.1967,
      "step": 80
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 1.5995818376541138,
      "learning_rate": 0.00014745917060857383,
      "loss": 2.1501,
      "step": 85
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 1.3882001638412476,
      "learning_rate": 0.0001465107320500767,
      "loss": 2.1184,
      "step": 90
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 1.4893513917922974,
      "learning_rate": 0.00014547651085471683,
      "loss": 2.1836,
      "step": 95
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.5417523384094238,
      "learning_rate": 0.0001443582283816074,
      "loss": 2.1532,
      "step": 100
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.474676251411438,
      "learning_rate": 0.0001431577459015626,
      "loss": 2.1411,
      "step": 105
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 1.6343954801559448,
      "learning_rate": 0.00014187706149919582,
      "loss": 2.1325,
      "step": 110
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 1.6139814853668213,
      "learning_rate": 0.00014051830674730509,
      "loss": 2.1292,
      "step": 115
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.4923847913742065,
      "learning_rate": 0.00013908374315908066,
      "loss": 2.1303,
      "step": 120
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 1.425238013267517,
      "learning_rate": 0.00013757575842403914,
      "loss": 2.0619,
      "step": 125
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.3964207172393799,
      "learning_rate": 0.0001359968624339503,
      "loss": 2.0931,
      "step": 130
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 1.4556257724761963,
      "learning_rate": 0.0001343496831053697,
      "loss": 2.0685,
      "step": 135
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.4229402542114258,
      "learning_rate": 0.00013263696200573104,
      "loss": 2.1007,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.9944559335708618,
      "eval_runtime": 0.6316,
      "eval_samples_per_second": 7.916,
      "eval_steps_per_second": 7.916,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.9944559335708618,
      "eval_runtime": 0.5923,
      "eval_samples_per_second": 8.442,
      "eval_steps_per_second": 8.442,
      "step": 140
    },
    {
      "epoch": 1.0357142857142858,
      "grad_norm": 1.4764453172683716,
      "learning_rate": 0.00013086154979027761,
      "loss": 1.7993,
      "step": 145
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 1.437887191772461,
      "learning_rate": 0.0001290264014574281,
      "loss": 1.7982,
      "step": 150
    },
    {
      "epoch": 1.1071428571428572,
      "grad_norm": 1.459887146949768,
      "learning_rate": 0.0001271345714304733,
      "loss": 1.7868,
      "step": 155
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.4325443506240845,
      "learning_rate": 0.0001251892084737899,
      "loss": 1.7632,
      "step": 160
    },
    {
      "epoch": 1.1785714285714286,
      "grad_norm": 1.3728995323181152,
      "learning_rate": 0.0001231935504520331,
      "loss": 1.7354,
      "step": 165
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 1.3899074792861938,
      "learning_rate": 0.00012115091894103025,
      "loss": 1.7969,
      "step": 170
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.4964189529418945,
      "learning_rate": 0.00011906471369934588,
      "loss": 1.7801,
      "step": 175
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 1.3325155973434448,
      "learning_rate": 0.00011693840700971884,
      "loss": 1.7869,
      "step": 180
    },
    {
      "epoch": 1.3214285714285714,
      "grad_norm": 1.488095998764038,
      "learning_rate": 0.00011477553789979063,
      "loss": 1.7771,
      "step": 185
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 1.3599910736083984,
      "learning_rate": 0.00011257970625174295,
      "loss": 1.7807,
      "step": 190
    },
    {
      "epoch": 1.3928571428571428,
      "grad_norm": 1.425702452659607,
      "learning_rate": 0.0001103545668106492,
      "loss": 1.8142,
      "step": 195
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.4276255369186401,
      "learning_rate": 0.00010810382310151192,
      "loss": 1.7576,
      "step": 200
    },
    {
      "epoch": 1.4642857142857144,
      "grad_norm": 1.3717377185821533,
      "learning_rate": 0.00010583122126511095,
      "loss": 1.7512,
      "step": 205
    },
    {
      "epoch": 1.5,
      "grad_norm": 1.3083884716033936,
      "learning_rate": 0.00010354054382292182,
      "loss": 1.7535,
      "step": 210
    },
    {
      "epoch": 1.5357142857142856,
      "grad_norm": 1.3747572898864746,
      "learning_rate": 0.00010123560338148197,
      "loss": 1.8019,
      "step": 215
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 1.3702155351638794,
      "learning_rate": 9.892023628668355e-05,
      "loss": 1.7736,
      "step": 220
    },
    {
      "epoch": 1.6071428571428572,
      "grad_norm": 1.3148250579833984,
      "learning_rate": 9.659829623855417e-05,
      "loss": 1.747,
      "step": 225
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 1.3732651472091675,
      "learning_rate": 9.42736478771537e-05,
      "loss": 1.7581,
      "step": 230
    },
    {
      "epoch": 1.6785714285714286,
      "grad_norm": 1.2940075397491455,
      "learning_rate": 9.1950160350262e-05,
      "loss": 1.7153,
      "step": 235
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.3065768480300903,
      "learning_rate": 8.963170087356454e-05,
      "loss": 1.7284,
      "step": 240
    },
    {
      "epoch": 1.75,
      "grad_norm": 1.3015515804290771,
      "learning_rate": 8.732212829405351e-05,
      "loss": 1.7104,
      "step": 245
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 1.320367693901062,
      "learning_rate": 8.502528666735768e-05,
      "loss": 1.7164,
      "step": 250
    },
    {
      "epoch": 1.8214285714285714,
      "grad_norm": 1.328780174255371,
      "learning_rate": 8.27449988596913e-05,
      "loss": 1.6933,
      "step": 255
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 1.2614611387252808,
      "learning_rate": 8.048506018507052e-05,
      "loss": 1.7327,
      "step": 260
    },
    {
      "epoch": 1.8928571428571428,
      "grad_norm": 1.3493170738220215,
      "learning_rate": 7.824923208838779e-05,
      "loss": 1.7301,
      "step": 265
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 1.33063542842865,
      "learning_rate": 7.604123588485805e-05,
      "loss": 1.6979,
      "step": 270
    },
    {
      "epoch": 1.9642857142857144,
      "grad_norm": 1.3395414352416992,
      "learning_rate": 7.386474656625674e-05,
      "loss": 1.7222,
      "step": 275
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.3347551822662354,
      "learning_rate": 7.17233866842588e-05,
      "loss": 1.7162,
      "step": 280
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.8434581756591797,
      "eval_runtime": 0.6338,
      "eval_samples_per_second": 7.889,
      "eval_steps_per_second": 7.889,
      "step": 280
    }
  ],
  "logging_steps": 5,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.976417678819328e+17,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}