{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1593625498007968,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015936254980079682,
      "eval_loss": 2.989337921142578,
      "eval_runtime": 48.6787,
      "eval_samples_per_second": 21.714,
      "eval_steps_per_second": 2.732,
      "step": 1
    },
    {
      "epoch": 0.004780876494023904,
      "grad_norm": 6.778011798858643,
      "learning_rate": 3e-05,
      "loss": 3.0699,
      "step": 3
    },
    {
      "epoch": 0.009561752988047808,
      "grad_norm": 5.260283470153809,
      "learning_rate": 6e-05,
      "loss": 2.5658,
      "step": 6
    },
    {
      "epoch": 0.014342629482071713,
      "grad_norm": 3.2668533325195312,
      "learning_rate": 9e-05,
      "loss": 1.707,
      "step": 9
    },
    {
      "epoch": 0.014342629482071713,
      "eval_loss": 1.1742104291915894,
      "eval_runtime": 49.3603,
      "eval_samples_per_second": 21.414,
      "eval_steps_per_second": 2.694,
      "step": 9
    },
    {
      "epoch": 0.019123505976095617,
      "grad_norm": 3.6501824855804443,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.9054,
      "step": 12
    },
    {
      "epoch": 0.02390438247011952,
      "grad_norm": 4.0104780197143555,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6137,
      "step": 15
    },
    {
      "epoch": 0.028685258964143426,
      "grad_norm": 2.6027774810791016,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.3968,
      "step": 18
    },
    {
      "epoch": 0.028685258964143426,
      "eval_loss": 0.41876041889190674,
      "eval_runtime": 49.3388,
      "eval_samples_per_second": 21.423,
      "eval_steps_per_second": 2.696,
      "step": 18
    },
    {
      "epoch": 0.03346613545816733,
      "grad_norm": 1.937503695487976,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.5046,
      "step": 21
    },
    {
      "epoch": 0.03824701195219123,
      "grad_norm": 2.261627674102783,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.3203,
      "step": 24
    },
    {
      "epoch": 0.04302788844621514,
      "grad_norm": 1.538251519203186,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.2675,
      "step": 27
    },
    {
      "epoch": 0.04302788844621514,
      "eval_loss": 0.2730524241924286,
      "eval_runtime": 49.3598,
      "eval_samples_per_second": 21.414,
      "eval_steps_per_second": 2.694,
      "step": 27
    },
    {
      "epoch": 0.04780876494023904,
      "grad_norm": 2.5118038654327393,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2493,
      "step": 30
    },
    {
      "epoch": 0.05258964143426295,
      "grad_norm": 1.49651300907135,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.322,
      "step": 33
    },
    {
      "epoch": 0.05737051792828685,
      "grad_norm": 1.897786021232605,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.331,
      "step": 36
    },
    {
      "epoch": 0.05737051792828685,
      "eval_loss": 0.23753176629543304,
      "eval_runtime": 49.3588,
      "eval_samples_per_second": 21.415,
      "eval_steps_per_second": 2.695,
      "step": 36
    },
    {
      "epoch": 0.062151394422310755,
      "grad_norm": 1.0993199348449707,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2865,
      "step": 39
    },
    {
      "epoch": 0.06693227091633466,
      "grad_norm": 1.5239222049713135,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.3524,
      "step": 42
    },
    {
      "epoch": 0.07171314741035857,
      "grad_norm": 1.9933027029037476,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2956,
      "step": 45
    },
    {
      "epoch": 0.07171314741035857,
      "eval_loss": 0.20888832211494446,
      "eval_runtime": 49.3905,
      "eval_samples_per_second": 21.401,
      "eval_steps_per_second": 2.693,
      "step": 45
    },
    {
      "epoch": 0.07649402390438247,
      "grad_norm": 0.711962878704071,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1154,
      "step": 48
    },
    {
      "epoch": 0.08127490039840637,
      "grad_norm": 1.104442834854126,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2002,
      "step": 51
    },
    {
      "epoch": 0.08605577689243028,
      "grad_norm": 3.417616128921509,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2404,
      "step": 54
    },
    {
      "epoch": 0.08605577689243028,
      "eval_loss": 0.19744670391082764,
      "eval_runtime": 49.3655,
      "eval_samples_per_second": 21.412,
      "eval_steps_per_second": 2.694,
      "step": 54
    },
    {
      "epoch": 0.09083665338645418,
      "grad_norm": 2.4179837703704834,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1789,
      "step": 57
    },
    {
      "epoch": 0.09561752988047809,
      "grad_norm": 1.321290373802185,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1779,
      "step": 60
    },
    {
      "epoch": 0.100398406374502,
      "grad_norm": 2.2034566402435303,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2711,
      "step": 63
    },
    {
      "epoch": 0.100398406374502,
      "eval_loss": 0.1865091472864151,
      "eval_runtime": 49.324,
      "eval_samples_per_second": 21.43,
      "eval_steps_per_second": 2.696,
      "step": 63
    },
    {
      "epoch": 0.1051792828685259,
      "grad_norm": 1.5474563837051392,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.1946,
      "step": 66
    },
    {
      "epoch": 0.1099601593625498,
      "grad_norm": 1.1282577514648438,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1589,
      "step": 69
    },
    {
      "epoch": 0.1147410358565737,
      "grad_norm": 1.7849586009979248,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.1731,
      "step": 72
    },
    {
      "epoch": 0.1147410358565737,
      "eval_loss": 0.17246675491333008,
      "eval_runtime": 49.3783,
      "eval_samples_per_second": 21.406,
      "eval_steps_per_second": 2.693,
      "step": 72
    },
    {
      "epoch": 0.11952191235059761,
      "grad_norm": 1.4825841188430786,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.1867,
      "step": 75
    },
    {
      "epoch": 0.12430278884462151,
      "grad_norm": 0.6733797192573547,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0973,
      "step": 78
    },
    {
      "epoch": 0.12908366533864543,
      "grad_norm": 1.5267447233200073,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1535,
      "step": 81
    },
    {
      "epoch": 0.12908366533864543,
      "eval_loss": 0.16705676913261414,
      "eval_runtime": 49.3711,
      "eval_samples_per_second": 21.409,
      "eval_steps_per_second": 2.694,
      "step": 81
    },
    {
      "epoch": 0.13386454183266933,
      "grad_norm": 0.9840028882026672,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.1613,
      "step": 84
    },
    {
      "epoch": 0.13864541832669322,
      "grad_norm": 1.2228305339813232,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1688,
      "step": 87
    },
    {
      "epoch": 0.14342629482071714,
      "grad_norm": 1.3518067598342896,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.199,
      "step": 90
    },
    {
      "epoch": 0.14342629482071714,
      "eval_loss": 0.16525177657604218,
      "eval_runtime": 49.3759,
      "eval_samples_per_second": 21.407,
      "eval_steps_per_second": 2.694,
      "step": 90
    },
    {
      "epoch": 0.14820717131474104,
      "grad_norm": 0.8513389825820923,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0936,
      "step": 93
    },
    {
      "epoch": 0.15298804780876493,
      "grad_norm": 2.6673593521118164,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.1242,
      "step": 96
    },
    {
      "epoch": 0.15776892430278885,
      "grad_norm": 1.199764609336853,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1485,
      "step": 99
    },
    {
      "epoch": 0.15776892430278885,
      "eval_loss": 0.16491371393203735,
      "eval_runtime": 49.3768,
      "eval_samples_per_second": 21.407,
      "eval_steps_per_second": 2.694,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.594213187695411e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}