{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01013299556681444,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001013299556681444,
      "eval_loss": 16.862510681152344,
      "eval_runtime": 661.5478,
      "eval_samples_per_second": 12.563,
      "eval_steps_per_second": 3.141,
      "step": 1
    },
    {
      "epoch": 0.0003039898670044332,
      "grad_norm": 33.69441223144531,
      "learning_rate": 3e-05,
      "loss": 16.9792,
      "step": 3
    },
    {
      "epoch": 0.0006079797340088664,
      "grad_norm": 45.39170837402344,
      "learning_rate": 6e-05,
      "loss": 13.2014,
      "step": 6
    },
    {
      "epoch": 0.0009119696010132996,
      "grad_norm": 12.2316312789917,
      "learning_rate": 9e-05,
      "loss": 3.3711,
      "step": 9
    },
    {
      "epoch": 0.0009119696010132996,
      "eval_loss": 0.060799404978752136,
      "eval_runtime": 664.908,
      "eval_samples_per_second": 12.499,
      "eval_steps_per_second": 3.125,
      "step": 9
    },
    {
      "epoch": 0.0012159594680177328,
      "grad_norm": 0.06092584878206253,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0152,
      "step": 12
    },
    {
      "epoch": 0.0015199493350221659,
      "grad_norm": 0.011796226724982262,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0006,
      "step": 15
    },
    {
      "epoch": 0.0018239392020265991,
      "grad_norm": 0.024324951693415642,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0002,
      "step": 18
    },
    {
      "epoch": 0.0018239392020265991,
      "eval_loss": 0.006653986871242523,
      "eval_runtime": 664.9035,
      "eval_samples_per_second": 12.5,
      "eval_steps_per_second": 3.125,
      "step": 18
    },
    {
      "epoch": 0.0021279290690310324,
      "grad_norm": 0.005161097273230553,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0001,
      "step": 21
    },
    {
      "epoch": 0.0024319189360354656,
      "grad_norm": 7.648368835449219,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0113,
      "step": 24
    },
    {
      "epoch": 0.0027359088030398985,
      "grad_norm": 0.001916556037031114,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.7641,
      "step": 27
    },
    {
      "epoch": 0.0027359088030398985,
      "eval_loss": 0.0008461069082841277,
      "eval_runtime": 664.9037,
      "eval_samples_per_second": 12.5,
      "eval_steps_per_second": 3.125,
      "step": 27
    },
    {
      "epoch": 0.0030398986700443317,
      "grad_norm": 0.013606617227196693,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0001,
      "step": 30
    },
    {
      "epoch": 0.003343888537048765,
      "grad_norm": 0.01366714108735323,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0003,
      "step": 33
    },
    {
      "epoch": 0.0036478784040531982,
      "grad_norm": 0.003967649303376675,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0001,
      "step": 36
    },
    {
      "epoch": 0.0036478784040531982,
      "eval_loss": 0.003455899655818939,
      "eval_runtime": 664.9158,
      "eval_samples_per_second": 12.499,
      "eval_steps_per_second": 3.125,
      "step": 36
    },
    {
      "epoch": 0.003951868271057631,
      "grad_norm": 0.00246708607301116,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0001,
      "step": 39
    },
    {
      "epoch": 0.004255858138062065,
      "grad_norm": 0.0035465415567159653,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0001,
      "step": 42
    },
    {
      "epoch": 0.004559848005066498,
      "grad_norm": 0.0007484377129003406,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0001,
      "step": 45
    },
    {
      "epoch": 0.004559848005066498,
      "eval_loss": 0.002770001068711281,
      "eval_runtime": 664.9046,
      "eval_samples_per_second": 12.5,
      "eval_steps_per_second": 3.125,
      "step": 45
    },
    {
      "epoch": 0.004863837872070931,
      "grad_norm": 0.0005840346566401422,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.005167827739075364,
      "grad_norm": 0.0017318450845777988,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.005471817606079797,
      "grad_norm": 0.00048772143782116473,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.005471817606079797,
      "eval_loss": 0.0009064534096978605,
      "eval_runtime": 664.9125,
      "eval_samples_per_second": 12.499,
      "eval_steps_per_second": 3.125,
      "step": 54
    },
    {
      "epoch": 0.005775807473084231,
      "grad_norm": 0.0005561282159760594,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.0060797973400886635,
      "grad_norm": 0.0007284763851203024,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.006383787207093097,
      "grad_norm": 0.0006130599067546427,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.006383787207093097,
      "eval_loss": 0.0005595112452283502,
      "eval_runtime": 664.9032,
      "eval_samples_per_second": 12.5,
      "eval_steps_per_second": 3.125,
      "step": 63
    },
    {
      "epoch": 0.00668777707409753,
      "grad_norm": 0.0008751649293117225,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.006991766941101964,
      "grad_norm": 0.0003913028631359339,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.0072957568081063965,
      "grad_norm": 0.00039692167774774134,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.0072957568081063965,
      "eval_loss": 0.0004811429826077074,
      "eval_runtime": 664.9117,
      "eval_samples_per_second": 12.499,
      "eval_steps_per_second": 3.125,
      "step": 72
    },
    {
      "epoch": 0.007599746675110829,
      "grad_norm": 0.0005186413764022291,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0004,
      "step": 75
    },
    {
      "epoch": 0.007903736542115262,
      "grad_norm": 0.0011915337527170777,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.008207726409119697,
      "grad_norm": 0.0019847059156745672,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.008207726409119697,
      "eval_loss": 3.187159018125385e-05,
      "eval_runtime": 664.9119,
      "eval_samples_per_second": 12.499,
      "eval_steps_per_second": 3.125,
      "step": 81
    },
    {
      "epoch": 0.00851171627612413,
      "grad_norm": 0.0075191170908510685,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0001,
      "step": 84
    },
    {
      "epoch": 0.008815706143128562,
      "grad_norm": 0.017061585560441017,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0001,
      "step": 87
    },
    {
      "epoch": 0.009119696010132995,
      "grad_norm": 0.00159067299682647,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.009119696010132995,
      "eval_loss": 2.705881888687145e-05,
      "eval_runtime": 664.9024,
      "eval_samples_per_second": 12.5,
      "eval_steps_per_second": 3.125,
      "step": 90
    },
    {
      "epoch": 0.009423685877137428,
      "grad_norm": 0.005036810413002968,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.009727675744141863,
      "grad_norm": 0.0017241941532120109,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.010031665611146295,
      "grad_norm": 0.002947796368971467,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.010031665611146295,
      "eval_loss": 2.4938459318946116e-05,
      "eval_runtime": 664.9068,
      "eval_samples_per_second": 12.499,
      "eval_steps_per_second": 3.125,
      "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": 7.54256789372928e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}