{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 219,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0045662100456621,
      "grad_norm": 6.815864086151123,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.7729,
      "step": 1
    },
    {
      "epoch": 0.0228310502283105,
      "grad_norm": 5.818741798400879,
      "learning_rate": 4.545454545454546e-05,
      "loss": 1.7132,
      "step": 5
    },
    {
      "epoch": 0.045662100456621,
      "grad_norm": 2.6188273429870605,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.4372,
      "step": 10
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 1.4498921632766724,
      "learning_rate": 0.00013636363636363637,
      "loss": 1.2124,
      "step": 15
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 1.0618371963500977,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.0648,
      "step": 20
    },
    {
      "epoch": 0.1141552511415525,
      "grad_norm": 0.8222594857215881,
      "learning_rate": 0.00019988558131018186,
      "loss": 0.9718,
      "step": 25
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.621496856212616,
      "learning_rate": 0.00019918730395931649,
      "loss": 0.9004,
      "step": 30
    },
    {
      "epoch": 0.1598173515981735,
      "grad_norm": 0.3935670554637909,
      "learning_rate": 0.00019785874696801202,
      "loss": 0.8609,
      "step": 35
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 0.37850192189216614,
      "learning_rate": 0.00019590835257019714,
      "loss": 0.8519,
      "step": 40
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 0.33678698539733887,
      "learning_rate": 0.00019334851442746664,
      "loss": 0.8249,
      "step": 45
    },
    {
      "epoch": 0.228310502283105,
      "grad_norm": 0.5497208833694458,
      "learning_rate": 0.00019019549887431877,
      "loss": 0.8155,
      "step": 50
    },
    {
      "epoch": 0.2511415525114155,
      "grad_norm": 0.4304714798927307,
      "learning_rate": 0.00018646934155473022,
      "loss": 0.8072,
      "step": 55
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.3267618417739868,
      "learning_rate": 0.00018219372010688515,
      "loss": 0.792,
      "step": 60
    },
    {
      "epoch": 0.2968036529680365,
      "grad_norm": 0.5633127689361572,
      "learning_rate": 0.00017739580370507532,
      "loss": 0.7879,
      "step": 65
    },
    {
      "epoch": 0.319634703196347,
      "grad_norm": 0.39324459433555603,
      "learning_rate": 0.0001721060804148482,
      "loss": 0.7944,
      "step": 70
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 0.3261910080909729,
      "learning_rate": 0.0001663581634584641,
      "loss": 0.7872,
      "step": 75
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 0.3310278356075287,
      "learning_rate": 0.0001601885776217367,
      "loss": 0.7789,
      "step": 80
    },
    {
      "epoch": 0.3881278538812785,
      "grad_norm": 0.356475830078125,
      "learning_rate": 0.0001536365271595212,
      "loss": 0.7805,
      "step": 85
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 0.6090440154075623,
      "learning_rate": 0.0001467436466746814,
      "loss": 0.7725,
      "step": 90
    },
    {
      "epoch": 0.4337899543378995,
      "grad_norm": 0.648769736289978,
      "learning_rate": 0.0001395537365535585,
      "loss": 0.7696,
      "step": 95
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 0.3896843492984772,
      "learning_rate": 0.00013211248463910262,
      "loss": 0.7703,
      "step": 100
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 0.40256544947624207,
      "learning_rate": 0.00012446717591027624,
      "loss": 0.7577,
      "step": 105
    },
    {
      "epoch": 0.502283105022831,
      "grad_norm": 0.3406723141670227,
      "learning_rate": 0.00011666639201255506,
      "loss": 0.7572,
      "step": 110
    },
    {
      "epoch": 0.5251141552511416,
      "grad_norm": 0.4368165135383606,
      "learning_rate": 0.0001087597025488413,
      "loss": 0.7578,
      "step": 115
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.45874515175819397,
      "learning_rate": 0.00010079735009246167,
      "loss": 0.7593,
      "step": 120
    },
    {
      "epoch": 0.5707762557077626,
      "grad_norm": 0.44529327750205994,
      "learning_rate": 9.282993092381625e-05,
      "loss": 0.7479,
      "step": 125
    },
    {
      "epoch": 0.593607305936073,
      "grad_norm": 0.40876489877700806,
      "learning_rate": 8.490807351941753e-05,
      "loss": 0.7486,
      "step": 130
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": 0.3738647699356079,
      "learning_rate": 7.708211683634112e-05,
      "loss": 0.7478,
      "step": 135
    },
    {
      "epoch": 0.639269406392694,
      "grad_norm": 0.3480348587036133,
      "learning_rate": 6.940179043641005e-05,
      "loss": 0.7401,
      "step": 140
    },
    {
      "epoch": 0.6621004566210046,
      "grad_norm": 0.3515714108943939,
      "learning_rate": 6.191589848274368e-05,
      "loss": 0.7477,
      "step": 145
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.4522218108177185,
      "learning_rate": 5.467200961669619e-05,
      "loss": 0.7447,
      "step": 150
    },
    {
      "epoch": 0.7077625570776256,
      "grad_norm": 0.331890344619751,
      "learning_rate": 4.7716154685841944e-05,
      "loss": 0.746,
      "step": 155
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 0.4267323613166809,
      "learning_rate": 4.109253424377772e-05,
      "loss": 0.7525,
      "step": 160
    },
    {
      "epoch": 0.7534246575342466,
      "grad_norm": 0.34801220893859863,
      "learning_rate": 3.4843237680415156e-05,
      "loss": 0.7408,
      "step": 165
    },
    {
      "epoch": 0.776255707762557,
      "grad_norm": 0.3299520015716553,
      "learning_rate": 2.9007975767533714e-05,
      "loss": 0.7324,
      "step": 170
    },
    {
      "epoch": 0.7990867579908676,
      "grad_norm": 0.3563040494918823,
      "learning_rate": 2.3623828319116748e-05,
      "loss": 0.7487,
      "step": 175
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.355241984128952,
      "learning_rate": 1.8725008569947365e-05,
      "loss": 0.7521,
      "step": 180
    },
    {
      "epoch": 0.8447488584474886,
      "grad_norm": 0.32830801606178284,
      "learning_rate": 1.4342645769705977e-05,
      "loss": 0.737,
      "step": 185
    },
    {
      "epoch": 0.867579908675799,
      "grad_norm": 0.32326367497444153,
      "learning_rate": 1.0504587374062391e-05,
      "loss": 0.7397,
      "step": 190
    },
    {
      "epoch": 0.8904109589041096,
      "grad_norm": 0.33771994709968567,
      "learning_rate": 7.235222089726279e-06,
      "loss": 0.7373,
      "step": 195
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 0.33751899003982544,
      "learning_rate": 4.555324897906132e-06,
      "loss": 0.7426,
      "step": 200
    },
    {
      "epoch": 0.9360730593607306,
      "grad_norm": 0.34009331464767456,
      "learning_rate": 2.4819250409651607e-06,
      "loss": 0.7403,
      "step": 205
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": 0.3508203327655792,
      "learning_rate": 1.0281978111449375e-06,
      "loss": 0.7469,
      "step": 210
    },
    {
      "epoch": 0.9817351598173516,
      "grad_norm": 0.3122396469116211,
      "learning_rate": 2.0338082897886079e-07,
      "loss": 0.742,
      "step": 215
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.8227200508117676,
      "eval_runtime": 1.5688,
      "eval_samples_per_second": 7.649,
      "eval_steps_per_second": 0.637,
      "step": 219
    },
    {
      "epoch": 1.0,
      "step": 219,
      "total_flos": 6.128945867501076e+17,
      "train_loss": 0.8279621209183784,
      "train_runtime": 2699.8939,
      "train_samples_per_second": 5.187,
      "train_steps_per_second": 0.081
    }
  ],
  "logging_steps": 5,
  "max_steps": 219,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.128945867501076e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}