{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0514668039114771,
  "eval_steps": 9,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001029336078229542,
      "grad_norm": 0.23270708322525024,
      "learning_rate": 1e-05,
      "loss": 4.8778,
      "step": 1
    },
    {
      "epoch": 0.001029336078229542,
      "eval_loss": 2.449375629425049,
      "eval_runtime": 226.7141,
      "eval_samples_per_second": 3.608,
      "eval_steps_per_second": 0.454,
      "step": 1
    },
    {
      "epoch": 0.002058672156459084,
      "grad_norm": 0.2403886765241623,
      "learning_rate": 2e-05,
      "loss": 4.6643,
      "step": 2
    },
    {
      "epoch": 0.003088008234688626,
      "grad_norm": 0.21336641907691956,
      "learning_rate": 3e-05,
      "loss": 4.8765,
      "step": 3
    },
    {
      "epoch": 0.004117344312918168,
      "grad_norm": 0.24259218573570251,
      "learning_rate": 4e-05,
      "loss": 5.0207,
      "step": 4
    },
    {
      "epoch": 0.0051466803911477095,
      "grad_norm": 0.2876662611961365,
      "learning_rate": 5e-05,
      "loss": 5.0594,
      "step": 5
    },
    {
      "epoch": 0.006176016469377252,
      "grad_norm": 0.3250068724155426,
      "learning_rate": 6e-05,
      "loss": 4.8713,
      "step": 6
    },
    {
      "epoch": 0.007205352547606794,
      "grad_norm": 0.2040358930826187,
      "learning_rate": 7e-05,
      "loss": 4.711,
      "step": 7
    },
    {
      "epoch": 0.008234688625836336,
      "grad_norm": 0.34615465998649597,
      "learning_rate": 8e-05,
      "loss": 4.8104,
      "step": 8
    },
    {
      "epoch": 0.009264024704065878,
      "grad_norm": 0.3927066922187805,
      "learning_rate": 9e-05,
      "loss": 5.0474,
      "step": 9
    },
    {
      "epoch": 0.009264024704065878,
      "eval_loss": 2.4394149780273438,
      "eval_runtime": 226.8989,
      "eval_samples_per_second": 3.605,
      "eval_steps_per_second": 0.454,
      "step": 9
    },
    {
      "epoch": 0.010293360782295419,
      "grad_norm": 0.2759287655353546,
      "learning_rate": 0.0001,
      "loss": 4.8251,
      "step": 10
    },
    {
      "epoch": 0.011322696860524962,
      "grad_norm": 0.35022222995758057,
      "learning_rate": 9.99695413509548e-05,
      "loss": 5.2115,
      "step": 11
    },
    {
      "epoch": 0.012352032938754504,
      "grad_norm": 0.2925807535648346,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.8341,
      "step": 12
    },
    {
      "epoch": 0.013381369016984045,
      "grad_norm": 0.27655553817749023,
      "learning_rate": 9.972609476841367e-05,
      "loss": 4.5449,
      "step": 13
    },
    {
      "epoch": 0.014410705095213588,
      "grad_norm": 0.3062187135219574,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.8675,
      "step": 14
    },
    {
      "epoch": 0.01544004117344313,
      "grad_norm": 0.3353738486766815,
      "learning_rate": 9.924038765061042e-05,
      "loss": 4.7423,
      "step": 15
    },
    {
      "epoch": 0.016469377251672673,
      "grad_norm": 0.3210652470588684,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.0688,
      "step": 16
    },
    {
      "epoch": 0.017498713329902212,
      "grad_norm": 0.36584898829460144,
      "learning_rate": 9.851478631379982e-05,
      "loss": 4.8991,
      "step": 17
    },
    {
      "epoch": 0.018528049408131755,
      "grad_norm": 0.31348302960395813,
      "learning_rate": 9.806308479691595e-05,
      "loss": 4.7511,
      "step": 18
    },
    {
      "epoch": 0.018528049408131755,
      "eval_loss": 2.4040560722351074,
      "eval_runtime": 226.9454,
      "eval_samples_per_second": 3.604,
      "eval_steps_per_second": 0.454,
      "step": 18
    },
    {
      "epoch": 0.0195573854863613,
      "grad_norm": 0.31781822443008423,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.818,
      "step": 19
    },
    {
      "epoch": 0.020586721564590838,
      "grad_norm": 0.27385666966438293,
      "learning_rate": 9.698463103929542e-05,
      "loss": 4.8567,
      "step": 20
    },
    {
      "epoch": 0.02161605764282038,
      "grad_norm": 0.3134090304374695,
      "learning_rate": 9.635919272833938e-05,
      "loss": 4.8306,
      "step": 21
    },
    {
      "epoch": 0.022645393721049924,
      "grad_norm": 0.32903534173965454,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.6411,
      "step": 22
    },
    {
      "epoch": 0.023674729799279464,
      "grad_norm": 0.5250512361526489,
      "learning_rate": 9.493970231495835e-05,
      "loss": 4.9593,
      "step": 23
    },
    {
      "epoch": 0.024704065877509007,
      "grad_norm": 0.31589871644973755,
      "learning_rate": 9.414737964294636e-05,
      "loss": 4.7378,
      "step": 24
    },
    {
      "epoch": 0.02573340195573855,
      "grad_norm": 0.2427978217601776,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.471,
      "step": 25
    },
    {
      "epoch": 0.02676273803396809,
      "grad_norm": 0.3135339617729187,
      "learning_rate": 9.24024048078213e-05,
      "loss": 4.7955,
      "step": 26
    },
    {
      "epoch": 0.027792074112197633,
      "grad_norm": 0.3900616466999054,
      "learning_rate": 9.145187862775209e-05,
      "loss": 5.0081,
      "step": 27
    },
    {
      "epoch": 0.027792074112197633,
      "eval_loss": 2.386911153793335,
      "eval_runtime": 227.018,
      "eval_samples_per_second": 3.603,
      "eval_steps_per_second": 0.454,
      "step": 27
    },
    {
      "epoch": 0.028821410190427176,
      "grad_norm": 0.26265034079551697,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.799,
      "step": 28
    },
    {
      "epoch": 0.029850746268656716,
      "grad_norm": 0.30579325556755066,
      "learning_rate": 8.940053768033609e-05,
      "loss": 4.5961,
      "step": 29
    },
    {
      "epoch": 0.03088008234688626,
      "grad_norm": 0.42424359917640686,
      "learning_rate": 8.83022221559489e-05,
      "loss": 4.8045,
      "step": 30
    },
    {
      "epoch": 0.0319094184251158,
      "grad_norm": 0.3576556444168091,
      "learning_rate": 8.715724127386972e-05,
      "loss": 4.8802,
      "step": 31
    },
    {
      "epoch": 0.032938754503345345,
      "grad_norm": 0.3096839189529419,
      "learning_rate": 8.596699001693255e-05,
      "loss": 4.7263,
      "step": 32
    },
    {
      "epoch": 0.033968090581574885,
      "grad_norm": 0.425644189119339,
      "learning_rate": 8.473291852294987e-05,
      "loss": 4.6257,
      "step": 33
    },
    {
      "epoch": 0.034997426659804425,
      "grad_norm": 0.3519304394721985,
      "learning_rate": 8.345653031794292e-05,
      "loss": 4.7576,
      "step": 34
    },
    {
      "epoch": 0.03602676273803397,
      "grad_norm": 0.38826555013656616,
      "learning_rate": 8.213938048432697e-05,
      "loss": 4.7818,
      "step": 35
    },
    {
      "epoch": 0.03705609881626351,
      "grad_norm": 0.33783453702926636,
      "learning_rate": 8.07830737662829e-05,
      "loss": 4.7301,
      "step": 36
    },
    {
      "epoch": 0.03705609881626351,
      "eval_loss": 2.3819499015808105,
      "eval_runtime": 226.8579,
      "eval_samples_per_second": 3.606,
      "eval_steps_per_second": 0.454,
      "step": 36
    },
    {
      "epoch": 0.03808543489449305,
      "grad_norm": 0.30728089809417725,
      "learning_rate": 7.938926261462366e-05,
      "loss": 4.6269,
      "step": 37
    },
    {
      "epoch": 0.0391147709727226,
      "grad_norm": 0.26561239361763,
      "learning_rate": 7.795964517353735e-05,
      "loss": 4.8023,
      "step": 38
    },
    {
      "epoch": 0.04014410705095214,
      "grad_norm": 0.333359956741333,
      "learning_rate": 7.649596321166024e-05,
      "loss": 4.6354,
      "step": 39
    },
    {
      "epoch": 0.041173443129181676,
      "grad_norm": 0.280263215303421,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.9582,
      "step": 40
    },
    {
      "epoch": 0.04220277920741122,
      "grad_norm": 0.3637993633747101,
      "learning_rate": 7.347357813929454e-05,
      "loss": 5.0495,
      "step": 41
    },
    {
      "epoch": 0.04323211528564076,
      "grad_norm": 0.3035355806350708,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.8531,
      "step": 42
    },
    {
      "epoch": 0.0442614513638703,
      "grad_norm": 0.2905413806438446,
      "learning_rate": 7.033683215379002e-05,
      "loss": 4.8934,
      "step": 43
    },
    {
      "epoch": 0.04529078744209985,
      "grad_norm": 0.2680681049823761,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.8269,
      "step": 44
    },
    {
      "epoch": 0.04632012352032939,
      "grad_norm": 0.2697928547859192,
      "learning_rate": 6.710100716628344e-05,
      "loss": 4.5012,
      "step": 45
    },
    {
      "epoch": 0.04632012352032939,
      "eval_loss": 2.379274845123291,
      "eval_runtime": 226.8561,
      "eval_samples_per_second": 3.606,
      "eval_steps_per_second": 0.454,
      "step": 45
    },
    {
      "epoch": 0.04734945959855893,
      "grad_norm": 0.34642162919044495,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.8511,
      "step": 46
    },
    {
      "epoch": 0.048378795676788475,
      "grad_norm": 0.3296074867248535,
      "learning_rate": 6.378186779084995e-05,
      "loss": 4.8204,
      "step": 47
    },
    {
      "epoch": 0.049408131755018014,
      "grad_norm": 0.27953025698661804,
      "learning_rate": 6.209609477998338e-05,
      "loss": 5.0973,
      "step": 48
    },
    {
      "epoch": 0.050437467833247554,
      "grad_norm": 0.3788706660270691,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 5.0161,
      "step": 49
    },
    {
      "epoch": 0.0514668039114771,
      "grad_norm": 0.32087740302085876,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.8925,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.077221192492646e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}