{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9975786924939467,
  "eval_steps": 100,
  "global_step": 206,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004842615012106538,
      "grad_norm": Infinity,
      "learning_rate": 0.0,
      "loss": 3.4324,
      "step": 1
    },
    {
      "epoch": 0.024213075060532687,
      "grad_norm": Infinity,
      "learning_rate": 3.80952380952381e-06,
      "loss": 3.4709,
      "step": 5
    },
    {
      "epoch": 0.048426150121065374,
      "grad_norm": Infinity,
      "learning_rate": 8.571428571428571e-06,
      "loss": 3.4332,
      "step": 10
    },
    {
      "epoch": 0.07263922518159806,
      "grad_norm": 2265.912353515625,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 3.3653,
      "step": 15
    },
    {
      "epoch": 0.09685230024213075,
      "grad_norm": 26.441295623779297,
      "learning_rate": 1.8095238095238097e-05,
      "loss": 2.7973,
      "step": 20
    },
    {
      "epoch": 0.12106537530266344,
      "grad_norm": 10.009239196777344,
      "learning_rate": 1.998702597080545e-05,
      "loss": 2.4954,
      "step": 25
    },
    {
      "epoch": 0.14527845036319612,
      "grad_norm": 8.63729476928711,
      "learning_rate": 1.990786211874702e-05,
      "loss": 2.2779,
      "step": 30
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 5.256661415100098,
      "learning_rate": 1.9757311893084887e-05,
      "loss": 2.0884,
      "step": 35
    },
    {
      "epoch": 0.1937046004842615,
      "grad_norm": 4.025212287902832,
      "learning_rate": 1.9536460011644788e-05,
      "loss": 1.9802,
      "step": 40
    },
    {
      "epoch": 0.2179176755447942,
      "grad_norm": 5.298352241516113,
      "learning_rate": 1.9246897717293316e-05,
      "loss": 1.931,
      "step": 45
    },
    {
      "epoch": 0.24213075060532688,
      "grad_norm": 6.026552677154541,
      "learning_rate": 1.889071131299657e-05,
      "loss": 1.8533,
      "step": 50
    },
    {
      "epoch": 0.26634382566585957,
      "grad_norm": 3.0896716117858887,
      "learning_rate": 1.847046712995951e-05,
      "loss": 1.8141,
      "step": 55
    },
    {
      "epoch": 0.29055690072639223,
      "grad_norm": 2.5661978721618652,
      "learning_rate": 1.7989193037150785e-05,
      "loss": 1.7359,
      "step": 60
    },
    {
      "epoch": 0.31476997578692495,
      "grad_norm": 2.811737537384033,
      "learning_rate": 1.7450356625437454e-05,
      "loss": 1.7127,
      "step": 65
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 2.3320705890655518,
      "learning_rate": 1.6857840223513315e-05,
      "loss": 1.6917,
      "step": 70
    },
    {
      "epoch": 0.36319612590799033,
      "grad_norm": 2.211479902267456,
      "learning_rate": 1.6215912925631724e-05,
      "loss": 1.686,
      "step": 75
    },
    {
      "epoch": 0.387409200968523,
      "grad_norm": 2.2482082843780518,
      "learning_rate": 1.5529199832683634e-05,
      "loss": 1.692,
      "step": 80
    },
    {
      "epoch": 0.4116222760290557,
      "grad_norm": 2.042475700378418,
      "learning_rate": 1.4802648728239743e-05,
      "loss": 1.6433,
      "step": 85
    },
    {
      "epoch": 0.4358353510895884,
      "grad_norm": 2.3130321502685547,
      "learning_rate": 1.4041494429656442e-05,
      "loss": 1.6453,
      "step": 90
    },
    {
      "epoch": 0.4600484261501211,
      "grad_norm": 2.4371917247772217,
      "learning_rate": 1.3251221071096836e-05,
      "loss": 1.6349,
      "step": 95
    },
    {
      "epoch": 0.48426150121065376,
      "grad_norm": 2.372549295425415,
      "learning_rate": 1.2437522590218418e-05,
      "loss": 1.6483,
      "step": 100
    },
    {
      "epoch": 0.48426150121065376,
      "eval_loss": 1.6258821487426758,
      "eval_runtime": 4.1048,
      "eval_samples_per_second": 181.737,
      "eval_steps_per_second": 5.847,
      "step": 100
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 2.1148526668548584,
      "learning_rate": 1.1606261703221773e-05,
      "loss": 1.6039,
      "step": 105
    },
    {
      "epoch": 0.5326876513317191,
      "grad_norm": 2.0148227214813232,
      "learning_rate": 1.0763427663846016e-05,
      "loss": 1.5947,
      "step": 110
    },
    {
      "epoch": 0.5569007263922519,
      "grad_norm": 2.198960542678833,
      "learning_rate": 9.915093110658348e-06,
      "loss": 1.5819,
      "step": 115
    },
    {
      "epoch": 0.5811138014527845,
      "grad_norm": 2.183297872543335,
      "learning_rate": 9.067370313554016e-06,
      "loss": 1.5687,
      "step": 120
    },
    {
      "epoch": 0.6053268765133172,
      "grad_norm": 2.1050634384155273,
      "learning_rate": 8.226367134711692e-06,
      "loss": 1.5507,
      "step": 125
    },
    {
      "epoch": 0.6295399515738499,
      "grad_norm": 1.7153900861740112,
      "learning_rate": 7.3981430213064705e-06,
      "loss": 1.5402,
      "step": 130
    },
    {
      "epoch": 0.6537530266343826,
      "grad_norm": 1.8903272151947021,
      "learning_rate": 6.588665347054153e-06,
      "loss": 1.5173,
      "step": 135
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 2.001927137374878,
      "learning_rate": 5.80376641714686e-06,
      "loss": 1.5396,
      "step": 140
    },
    {
      "epoch": 0.7021791767554479,
      "grad_norm": 1.7133185863494873,
      "learning_rate": 5.049101446360498e-06,
      "loss": 1.5002,
      "step": 145
    },
    {
      "epoch": 0.7263922518159807,
      "grad_norm": 1.8695131540298462,
      "learning_rate": 4.330107813102683e-06,
      "loss": 1.4823,
      "step": 150
    },
    {
      "epoch": 0.7506053268765133,
      "grad_norm": 1.7020870447158813,
      "learning_rate": 3.6519658829767455e-06,
      "loss": 1.4927,
      "step": 155
    },
    {
      "epoch": 0.774818401937046,
      "grad_norm": 1.737141728401184,
      "learning_rate": 3.0195616841288233e-06,
      "loss": 1.4795,
      "step": 160
    },
    {
      "epoch": 0.7990314769975787,
      "grad_norm": 1.6748268604278564,
      "learning_rate": 2.4374517033031287e-06,
      "loss": 1.4877,
      "step": 165
    },
    {
      "epoch": 0.8232445520581114,
      "grad_norm": 1.7021381855010986,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 1.4742,
      "step": 170
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 1.6568330526351929,
      "learning_rate": 1.4404982690284575e-06,
      "loss": 1.453,
      "step": 175
    },
    {
      "epoch": 0.8716707021791767,
      "grad_norm": 1.783124566078186,
      "learning_rate": 1.032837887918564e-06,
      "loss": 1.4709,
      "step": 180
    },
    {
      "epoch": 0.8958837772397095,
      "grad_norm": 1.6369842290878296,
      "learning_rate": 6.897861153082619e-07,
      "loss": 1.4668,
      "step": 185
    },
    {
      "epoch": 0.9200968523002422,
      "grad_norm": 1.5924932956695557,
      "learning_rate": 4.138146470802218e-07,
      "loss": 1.4795,
      "step": 190
    },
    {
      "epoch": 0.9443099273607748,
      "grad_norm": 1.7220604419708252,
      "learning_rate": 2.0691186398689945e-07,
      "loss": 1.4583,
      "step": 195
    },
    {
      "epoch": 0.9685230024213075,
      "grad_norm": 1.5856201648712158,
      "learning_rate": 7.05685053216465e-08,
      "loss": 1.4519,
      "step": 200
    },
    {
      "epoch": 0.9685230024213075,
      "eval_loss": 1.4829782247543335,
      "eval_runtime": 4.0889,
      "eval_samples_per_second": 182.444,
      "eval_steps_per_second": 5.87,
      "step": 200
    },
    {
      "epoch": 0.9927360774818402,
      "grad_norm": 1.6917001008987427,
      "learning_rate": 5.7669281079475446e-09,
      "loss": 1.4502,
      "step": 205
    },
    {
      "epoch": 0.9975786924939467,
      "step": 206,
      "total_flos": 7.598970652485222e+16,
      "train_loss": 1.8085910475369795,
      "train_runtime": 916.9479,
      "train_samples_per_second": 14.402,
      "train_steps_per_second": 0.225
    }
  ],
  "logging_steps": 5,
  "max_steps": 206,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.598970652485222e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}