{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11253196930946291,
  "eval_steps": 9,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011366865586814436,
      "eval_loss": 11.095451354980469,
      "eval_runtime": 5.6106,
      "eval_samples_per_second": 132.071,
      "eval_steps_per_second": 33.151,
      "step": 1
    },
    {
      "epoch": 0.0034100596760443308,
      "grad_norm": 2.3856959342956543,
      "learning_rate": 3e-05,
      "loss": 44.3673,
      "step": 3
    },
    {
      "epoch": 0.0068201193520886615,
      "grad_norm": 2.4655117988586426,
      "learning_rate": 6e-05,
      "loss": 44.3703,
      "step": 6
    },
    {
      "epoch": 0.010230179028132993,
      "grad_norm": 2.2212629318237305,
      "learning_rate": 9e-05,
      "loss": 44.3261,
      "step": 9
    },
    {
      "epoch": 0.010230179028132993,
      "eval_loss": 11.074569702148438,
      "eval_runtime": 4.7833,
      "eval_samples_per_second": 154.915,
      "eval_steps_per_second": 38.885,
      "step": 9
    },
    {
      "epoch": 0.013640238704177323,
      "grad_norm": 2.743508815765381,
      "learning_rate": 9.987820251299122e-05,
      "loss": 44.2612,
      "step": 12
    },
    {
      "epoch": 0.017050298380221655,
      "grad_norm": 1.8524738550186157,
      "learning_rate": 9.924038765061042e-05,
      "loss": 44.2154,
      "step": 15
    },
    {
      "epoch": 0.020460358056265986,
      "grad_norm": 1.639198660850525,
      "learning_rate": 9.806308479691595e-05,
      "loss": 44.167,
      "step": 18
    },
    {
      "epoch": 0.020460358056265986,
      "eval_loss": 11.030960083007812,
      "eval_runtime": 4.7631,
      "eval_samples_per_second": 155.569,
      "eval_steps_per_second": 39.05,
      "step": 18
    },
    {
      "epoch": 0.023870417732310314,
      "grad_norm": 1.5570883750915527,
      "learning_rate": 9.635919272833938e-05,
      "loss": 44.1426,
      "step": 21
    },
    {
      "epoch": 0.027280477408354646,
      "grad_norm": 1.5581414699554443,
      "learning_rate": 9.414737964294636e-05,
      "loss": 44.0753,
      "step": 24
    },
    {
      "epoch": 0.030690537084398978,
      "grad_norm": 1.6539247035980225,
      "learning_rate": 9.145187862775209e-05,
      "loss": 44.0163,
      "step": 27
    },
    {
      "epoch": 0.030690537084398978,
      "eval_loss": 10.998085021972656,
      "eval_runtime": 4.7738,
      "eval_samples_per_second": 155.223,
      "eval_steps_per_second": 38.963,
      "step": 27
    },
    {
      "epoch": 0.03410059676044331,
      "grad_norm": 1.4229531288146973,
      "learning_rate": 8.83022221559489e-05,
      "loss": 44.0237,
      "step": 30
    },
    {
      "epoch": 0.03751065643648764,
      "grad_norm": 1.3927640914916992,
      "learning_rate": 8.473291852294987e-05,
      "loss": 43.9566,
      "step": 33
    },
    {
      "epoch": 0.04092071611253197,
      "grad_norm": 1.352387547492981,
      "learning_rate": 8.07830737662829e-05,
      "loss": 43.9265,
      "step": 36
    },
    {
      "epoch": 0.04092071611253197,
      "eval_loss": 10.977602005004883,
      "eval_runtime": 4.7507,
      "eval_samples_per_second": 155.978,
      "eval_steps_per_second": 39.152,
      "step": 36
    },
    {
      "epoch": 0.0443307757885763,
      "grad_norm": 1.2622820138931274,
      "learning_rate": 7.649596321166024e-05,
      "loss": 43.855,
      "step": 39
    },
    {
      "epoch": 0.04774083546462063,
      "grad_norm": 1.1330219507217407,
      "learning_rate": 7.191855733945387e-05,
      "loss": 43.8811,
      "step": 42
    },
    {
      "epoch": 0.05115089514066496,
      "grad_norm": 1.1096593141555786,
      "learning_rate": 6.710100716628344e-05,
      "loss": 43.8743,
      "step": 45
    },
    {
      "epoch": 0.05115089514066496,
      "eval_loss": 10.961272239685059,
      "eval_runtime": 4.7683,
      "eval_samples_per_second": 155.4,
      "eval_steps_per_second": 39.007,
      "step": 45
    },
    {
      "epoch": 0.05456095481670929,
      "grad_norm": 1.0063976049423218,
      "learning_rate": 6.209609477998338e-05,
      "loss": 43.9744,
      "step": 48
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": 1.0805094242095947,
      "learning_rate": 5.695865504800327e-05,
      "loss": 43.7906,
      "step": 51
    },
    {
      "epoch": 0.061381074168797956,
      "grad_norm": 1.041139841079712,
      "learning_rate": 5.174497483512506e-05,
      "loss": 43.8027,
      "step": 54
    },
    {
      "epoch": 0.061381074168797956,
      "eval_loss": 10.949912071228027,
      "eval_runtime": 4.7641,
      "eval_samples_per_second": 155.537,
      "eval_steps_per_second": 39.042,
      "step": 54
    },
    {
      "epoch": 0.06479113384484228,
      "grad_norm": 1.2141445875167847,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 43.8766,
      "step": 57
    },
    {
      "epoch": 0.06820119352088662,
      "grad_norm": 1.179465413093567,
      "learning_rate": 4.131759111665349e-05,
      "loss": 43.7685,
      "step": 60
    },
    {
      "epoch": 0.07161125319693094,
      "grad_norm": 0.8835251331329346,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 43.8831,
      "step": 63
    },
    {
      "epoch": 0.07161125319693094,
      "eval_loss": 10.942551612854004,
      "eval_runtime": 4.747,
      "eval_samples_per_second": 156.099,
      "eval_steps_per_second": 39.183,
      "step": 63
    },
    {
      "epoch": 0.07502131287297528,
      "grad_norm": 1.0751994848251343,
      "learning_rate": 3.12696703292044e-05,
      "loss": 43.777,
      "step": 66
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 1.384466528892517,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 43.6297,
      "step": 69
    },
    {
      "epoch": 0.08184143222506395,
      "grad_norm": 1.247775912284851,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 43.7553,
      "step": 72
    },
    {
      "epoch": 0.08184143222506395,
      "eval_loss": 10.936705589294434,
      "eval_runtime": 4.7575,
      "eval_samples_per_second": 155.753,
      "eval_steps_per_second": 39.096,
      "step": 72
    },
    {
      "epoch": 0.08525149190110827,
      "grad_norm": 1.064352035522461,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 43.7996,
      "step": 75
    },
    {
      "epoch": 0.0886615515771526,
      "grad_norm": 0.9701411128044128,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 43.8023,
      "step": 78
    },
    {
      "epoch": 0.09207161125319693,
      "grad_norm": 1.058826208114624,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 43.8552,
      "step": 81
    },
    {
      "epoch": 0.09207161125319693,
      "eval_loss": 10.935081481933594,
      "eval_runtime": 4.232,
      "eval_samples_per_second": 175.096,
      "eval_steps_per_second": 43.951,
      "step": 81
    },
    {
      "epoch": 0.09548167092924126,
      "grad_norm": 1.081790566444397,
      "learning_rate": 7.597595192178702e-06,
      "loss": 43.735,
      "step": 84
    },
    {
      "epoch": 0.0988917306052856,
      "grad_norm": 0.8974946737289429,
      "learning_rate": 5.060297685041659e-06,
      "loss": 43.7617,
      "step": 87
    },
    {
      "epoch": 0.10230179028132992,
      "grad_norm": 1.1310738325119019,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 43.7058,
      "step": 90
    },
    {
      "epoch": 0.10230179028132992,
      "eval_loss": 10.934582710266113,
      "eval_runtime": 4.682,
      "eval_samples_per_second": 158.267,
      "eval_steps_per_second": 39.727,
      "step": 90
    },
    {
      "epoch": 0.10571184995737426,
      "grad_norm": 1.0372346639633179,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 43.758,
      "step": 93
    },
    {
      "epoch": 0.10912190963341858,
      "grad_norm": 1.142467737197876,
      "learning_rate": 4.865965629214819e-07,
      "loss": 43.7437,
      "step": 96
    },
    {
      "epoch": 0.11253196930946291,
      "grad_norm": 1.0426071882247925,
      "learning_rate": 3.04586490452119e-08,
      "loss": 43.7267,
      "step": 99
    },
    {
      "epoch": 0.11253196930946291,
      "eval_loss": 10.934452056884766,
      "eval_runtime": 4.6402,
      "eval_samples_per_second": 159.693,
      "eval_steps_per_second": 40.085,
      "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 874897735680.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}