{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1440922190201729,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001440922190201729,
      "eval_loss": 1.5874779224395752,
      "eval_runtime": 55.3421,
      "eval_samples_per_second": 21.123,
      "eval_steps_per_second": 2.656,
      "step": 1
    },
    {
      "epoch": 0.004322766570605188,
      "grad_norm": 0.3181666135787964,
      "learning_rate": 3e-05,
      "loss": 1.5867,
      "step": 3
    },
    {
      "epoch": 0.008645533141210375,
      "grad_norm": 0.2867472171783447,
      "learning_rate": 6e-05,
      "loss": 1.6289,
      "step": 6
    },
    {
      "epoch": 0.012968299711815562,
      "grad_norm": 0.20938456058502197,
      "learning_rate": 9e-05,
      "loss": 1.5389,
      "step": 9
    },
    {
      "epoch": 0.012968299711815562,
      "eval_loss": 1.5554473400115967,
      "eval_runtime": 56.1407,
      "eval_samples_per_second": 20.823,
      "eval_steps_per_second": 2.618,
      "step": 9
    },
    {
      "epoch": 0.01729106628242075,
      "grad_norm": 0.17046970129013062,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.5703,
      "step": 12
    },
    {
      "epoch": 0.021613832853025938,
      "grad_norm": 0.18430009484291077,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.5629,
      "step": 15
    },
    {
      "epoch": 0.025936599423631124,
      "grad_norm": 0.1635025143623352,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.5062,
      "step": 18
    },
    {
      "epoch": 0.025936599423631124,
      "eval_loss": 1.5162535905838013,
      "eval_runtime": 56.2328,
      "eval_samples_per_second": 20.789,
      "eval_steps_per_second": 2.614,
      "step": 18
    },
    {
      "epoch": 0.03025936599423631,
      "grad_norm": 0.12090650945901871,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.5448,
      "step": 21
    },
    {
      "epoch": 0.0345821325648415,
      "grad_norm": 0.11275506019592285,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4927,
      "step": 24
    },
    {
      "epoch": 0.03890489913544669,
      "grad_norm": 0.11760012060403824,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.5233,
      "step": 27
    },
    {
      "epoch": 0.03890489913544669,
      "eval_loss": 1.4996883869171143,
      "eval_runtime": 56.2351,
      "eval_samples_per_second": 20.788,
      "eval_steps_per_second": 2.614,
      "step": 27
    },
    {
      "epoch": 0.043227665706051875,
      "grad_norm": 0.1262870728969574,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.4807,
      "step": 30
    },
    {
      "epoch": 0.04755043227665706,
      "grad_norm": 0.10848761349916458,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.5181,
      "step": 33
    },
    {
      "epoch": 0.05187319884726225,
      "grad_norm": 0.10502011328935623,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.5181,
      "step": 36
    },
    {
      "epoch": 0.05187319884726225,
      "eval_loss": 1.4906489849090576,
      "eval_runtime": 56.2372,
      "eval_samples_per_second": 20.787,
      "eval_steps_per_second": 2.614,
      "step": 36
    },
    {
      "epoch": 0.056195965417867436,
      "grad_norm": 0.10323812067508698,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.5119,
      "step": 39
    },
    {
      "epoch": 0.06051873198847262,
      "grad_norm": 0.11017448455095291,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.44,
      "step": 42
    },
    {
      "epoch": 0.06484149855907781,
      "grad_norm": 0.10729548335075378,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5126,
      "step": 45
    },
    {
      "epoch": 0.06484149855907781,
      "eval_loss": 1.4857927560806274,
      "eval_runtime": 56.2437,
      "eval_samples_per_second": 20.785,
      "eval_steps_per_second": 2.614,
      "step": 45
    },
    {
      "epoch": 0.069164265129683,
      "grad_norm": 0.11548104137182236,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.5458,
      "step": 48
    },
    {
      "epoch": 0.07348703170028818,
      "grad_norm": 0.10168987512588501,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.4353,
      "step": 51
    },
    {
      "epoch": 0.07780979827089338,
      "grad_norm": 0.11101020127534866,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.5098,
      "step": 54
    },
    {
      "epoch": 0.07780979827089338,
      "eval_loss": 1.4827865362167358,
      "eval_runtime": 56.237,
      "eval_samples_per_second": 20.787,
      "eval_steps_per_second": 2.614,
      "step": 54
    },
    {
      "epoch": 0.08213256484149856,
      "grad_norm": 0.1119261384010315,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.436,
      "step": 57
    },
    {
      "epoch": 0.08645533141210375,
      "grad_norm": 0.1154652088880539,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.4412,
      "step": 60
    },
    {
      "epoch": 0.09077809798270893,
      "grad_norm": 0.11799252033233643,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.4983,
      "step": 63
    },
    {
      "epoch": 0.09077809798270893,
      "eval_loss": 1.4808632135391235,
      "eval_runtime": 56.2266,
      "eval_samples_per_second": 20.791,
      "eval_steps_per_second": 2.614,
      "step": 63
    },
    {
      "epoch": 0.09510086455331412,
      "grad_norm": 0.11385373771190643,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.5018,
      "step": 66
    },
    {
      "epoch": 0.0994236311239193,
      "grad_norm": 0.11354786902666092,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.4578,
      "step": 69
    },
    {
      "epoch": 0.1037463976945245,
      "grad_norm": 0.1059083342552185,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.4835,
      "step": 72
    },
    {
      "epoch": 0.1037463976945245,
      "eval_loss": 1.4797608852386475,
      "eval_runtime": 56.2608,
      "eval_samples_per_second": 20.778,
      "eval_steps_per_second": 2.613,
      "step": 72
    },
    {
      "epoch": 0.10806916426512968,
      "grad_norm": 0.12281151115894318,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.5053,
      "step": 75
    },
    {
      "epoch": 0.11239193083573487,
      "grad_norm": 0.11293952167034149,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.4949,
      "step": 78
    },
    {
      "epoch": 0.11671469740634005,
      "grad_norm": 0.11945235729217529,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.4645,
      "step": 81
    },
    {
      "epoch": 0.11671469740634005,
      "eval_loss": 1.4791374206542969,
      "eval_runtime": 56.3199,
      "eval_samples_per_second": 20.756,
      "eval_steps_per_second": 2.61,
      "step": 81
    },
    {
      "epoch": 0.12103746397694524,
      "grad_norm": 0.11825215816497803,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.4994,
      "step": 84
    },
    {
      "epoch": 0.12536023054755044,
      "grad_norm": 0.11532819271087646,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.4706,
      "step": 87
    },
    {
      "epoch": 0.12968299711815562,
      "grad_norm": 0.11403844505548477,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.4625,
      "step": 90
    },
    {
      "epoch": 0.12968299711815562,
      "eval_loss": 1.4788661003112793,
      "eval_runtime": 56.2481,
      "eval_samples_per_second": 20.783,
      "eval_steps_per_second": 2.613,
      "step": 90
    },
    {
      "epoch": 0.1340057636887608,
      "grad_norm": 0.11964377015829086,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.4932,
      "step": 93
    },
    {
      "epoch": 0.138328530259366,
      "grad_norm": 0.113527812063694,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.4576,
      "step": 96
    },
    {
      "epoch": 0.14265129682997119,
      "grad_norm": 0.11093898117542267,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.4974,
      "step": 99
    },
    {
      "epoch": 0.14265129682997119,
      "eval_loss": 1.4787828922271729,
      "eval_runtime": 56.177,
      "eval_samples_per_second": 20.809,
      "eval_steps_per_second": 2.617,
      "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": 5.690535079575552e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}