{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.032550758839565444,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016275379419782723,
      "eval_loss": 1.5723884105682373,
      "eval_runtime": 196.8327,
      "eval_samples_per_second": 13.148,
      "eval_steps_per_second": 6.574,
      "step": 1
    },
    {
      "epoch": 0.0008137689709891362,
      "grad_norm": 0.35386717319488525,
      "learning_rate": 5e-05,
      "loss": 1.3648,
      "step": 5
    },
    {
      "epoch": 0.0016275379419782724,
      "grad_norm": 0.4674012064933777,
      "learning_rate": 0.0001,
      "loss": 1.3267,
      "step": 10
    },
    {
      "epoch": 0.0024413069129674086,
      "grad_norm": 0.5329536199569702,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.2973,
      "step": 15
    },
    {
      "epoch": 0.0032550758839565447,
      "grad_norm": 0.6087198257446289,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2921,
      "step": 20
    },
    {
      "epoch": 0.0040688448549456805,
      "grad_norm": 0.714724600315094,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.2832,
      "step": 25
    },
    {
      "epoch": 0.004882613825934817,
      "grad_norm": 1.2130167484283447,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.3753,
      "step": 30
    },
    {
      "epoch": 0.005696382796923953,
      "grad_norm": 1.649317979812622,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.4577,
      "step": 35
    },
    {
      "epoch": 0.0065101517679130895,
      "grad_norm": 2.20588755607605,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.0042,
      "step": 40
    },
    {
      "epoch": 0.007323920738902225,
      "grad_norm": 2.594423294067383,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.1798,
      "step": 45
    },
    {
      "epoch": 0.008137689709891361,
      "grad_norm": 9.170083045959473,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.7771,
      "step": 50
    },
    {
      "epoch": 0.008137689709891361,
      "eval_loss": 1.2270060777664185,
      "eval_runtime": 198.1221,
      "eval_samples_per_second": 13.063,
      "eval_steps_per_second": 6.531,
      "step": 50
    },
    {
      "epoch": 0.008951458680880498,
      "grad_norm": 0.6143898963928223,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2446,
      "step": 55
    },
    {
      "epoch": 0.009765227651869634,
      "grad_norm": 0.5476758480072021,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.1483,
      "step": 60
    },
    {
      "epoch": 0.01057899662285877,
      "grad_norm": 0.5872772932052612,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.1986,
      "step": 65
    },
    {
      "epoch": 0.011392765593847906,
      "grad_norm": 0.6223112940788269,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.1515,
      "step": 70
    },
    {
      "epoch": 0.012206534564837043,
      "grad_norm": 0.7705265879631042,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.1816,
      "step": 75
    },
    {
      "epoch": 0.013020303535826179,
      "grad_norm": 1.007130742073059,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.1561,
      "step": 80
    },
    {
      "epoch": 0.013834072506815315,
      "grad_norm": 1.347641110420227,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.1284,
      "step": 85
    },
    {
      "epoch": 0.01464784147780445,
      "grad_norm": 1.3472156524658203,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.9544,
      "step": 90
    },
    {
      "epoch": 0.015461610448793588,
      "grad_norm": 1.9317922592163086,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9731,
      "step": 95
    },
    {
      "epoch": 0.016275379419782722,
      "grad_norm": 6.384594917297363,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.7312,
      "step": 100
    },
    {
      "epoch": 0.016275379419782722,
      "eval_loss": 1.1505261659622192,
      "eval_runtime": 198.1408,
      "eval_samples_per_second": 13.061,
      "eval_steps_per_second": 6.531,
      "step": 100
    },
    {
      "epoch": 0.01708914839077186,
      "grad_norm": 0.4909661114215851,
      "learning_rate": 5e-05,
      "loss": 1.1048,
      "step": 105
    },
    {
      "epoch": 0.017902917361760997,
      "grad_norm": 0.476285845041275,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.1538,
      "step": 110
    },
    {
      "epoch": 0.018716686332750133,
      "grad_norm": 0.5974850058555603,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.0978,
      "step": 115
    },
    {
      "epoch": 0.01953045530373927,
      "grad_norm": 0.7488738894462585,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.1489,
      "step": 120
    },
    {
      "epoch": 0.020344224274728404,
      "grad_norm": 0.8442608118057251,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.1564,
      "step": 125
    },
    {
      "epoch": 0.02115799324571754,
      "grad_norm": 1.2696480751037598,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.0814,
      "step": 130
    },
    {
      "epoch": 0.021971762216706676,
      "grad_norm": 1.3110004663467407,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.1289,
      "step": 135
    },
    {
      "epoch": 0.02278553118769581,
      "grad_norm": 2.1278111934661865,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.0119,
      "step": 140
    },
    {
      "epoch": 0.02359930015868495,
      "grad_norm": 3.1425962448120117,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.0978,
      "step": 145
    },
    {
      "epoch": 0.024413069129674086,
      "grad_norm": 5.378885746002197,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.4381,
      "step": 150
    },
    {
      "epoch": 0.024413069129674086,
      "eval_loss": 1.1307651996612549,
      "eval_runtime": 198.058,
      "eval_samples_per_second": 13.067,
      "eval_steps_per_second": 6.533,
      "step": 150
    },
    {
      "epoch": 0.025226838100663222,
      "grad_norm": 0.4325559437274933,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.1082,
      "step": 155
    },
    {
      "epoch": 0.026040607071652358,
      "grad_norm": 0.5688928961753845,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.2067,
      "step": 160
    },
    {
      "epoch": 0.026854376042641494,
      "grad_norm": 0.5977354049682617,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.0986,
      "step": 165
    },
    {
      "epoch": 0.02766814501363063,
      "grad_norm": 0.7392883896827698,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.1662,
      "step": 170
    },
    {
      "epoch": 0.028481913984619765,
      "grad_norm": 0.9673829674720764,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.2514,
      "step": 175
    },
    {
      "epoch": 0.0292956829556089,
      "grad_norm": 1.3040239810943604,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.0292,
      "step": 180
    },
    {
      "epoch": 0.03010945192659804,
      "grad_norm": 1.7316601276397705,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.1521,
      "step": 185
    },
    {
      "epoch": 0.030923220897587176,
      "grad_norm": 1.573816180229187,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.0154,
      "step": 190
    },
    {
      "epoch": 0.03173698986857631,
      "grad_norm": 1.919352412223816,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.0903,
      "step": 195
    },
    {
      "epoch": 0.032550758839565444,
      "grad_norm": 5.344688892364502,
      "learning_rate": 0.0,
      "loss": 1.415,
      "step": 200
    },
    {
      "epoch": 0.032550758839565444,
      "eval_loss": 1.125679612159729,
      "eval_runtime": 198.0669,
      "eval_samples_per_second": 13.066,
      "eval_steps_per_second": 6.533,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.53121987501097e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}