{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009723685276719877,
  "eval_steps": 9,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010804094751910974,
      "eval_loss": 2.5258078575134277,
      "eval_runtime": 2238.4222,
      "eval_samples_per_second": 6.964,
      "eval_steps_per_second": 0.871,
      "step": 1
    },
    {
      "epoch": 0.00032412284255732923,
      "grad_norm": 1.1297039985656738,
      "learning_rate": 3e-05,
      "loss": 2.515,
      "step": 3
    },
    {
      "epoch": 0.0006482456851146585,
      "grad_norm": 1.1249927282333374,
      "learning_rate": 6e-05,
      "loss": 2.5009,
      "step": 6
    },
    {
      "epoch": 0.0009723685276719876,
      "grad_norm": 0.8865611553192139,
      "learning_rate": 9e-05,
      "loss": 2.2655,
      "step": 9
    },
    {
      "epoch": 0.0009723685276719876,
      "eval_loss": 2.278886318206787,
      "eval_runtime": 2249.6428,
      "eval_samples_per_second": 6.93,
      "eval_steps_per_second": 0.866,
      "step": 9
    },
    {
      "epoch": 0.001296491370229317,
      "grad_norm": 0.9525989294052124,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.2622,
      "step": 12
    },
    {
      "epoch": 0.0016206142127866462,
      "grad_norm": 1.1120753288269043,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.1307,
      "step": 15
    },
    {
      "epoch": 0.0019447370553439753,
      "grad_norm": 0.7698648571968079,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.0609,
      "step": 18
    },
    {
      "epoch": 0.0019447370553439753,
      "eval_loss": 2.0205132961273193,
      "eval_runtime": 2249.0212,
      "eval_samples_per_second": 6.931,
      "eval_steps_per_second": 0.867,
      "step": 18
    },
    {
      "epoch": 0.0022688598979013048,
      "grad_norm": 0.8526450395584106,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.0765,
      "step": 21
    },
    {
      "epoch": 0.002592982740458634,
      "grad_norm": 0.7029660940170288,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.0004,
      "step": 24
    },
    {
      "epoch": 0.002917105583015963,
      "grad_norm": 0.7902804613113403,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.9568,
      "step": 27
    },
    {
      "epoch": 0.002917105583015963,
      "eval_loss": 1.9333840608596802,
      "eval_runtime": 2246.1817,
      "eval_samples_per_second": 6.94,
      "eval_steps_per_second": 0.868,
      "step": 27
    },
    {
      "epoch": 0.0032412284255732924,
      "grad_norm": 0.6563200950622559,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.8499,
      "step": 30
    },
    {
      "epoch": 0.0035653512681306215,
      "grad_norm": 0.7679675817489624,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.9908,
      "step": 33
    },
    {
      "epoch": 0.0038894741106879505,
      "grad_norm": 0.7943200469017029,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.8507,
      "step": 36
    },
    {
      "epoch": 0.0038894741106879505,
      "eval_loss": 1.880576252937317,
      "eval_runtime": 2247.2974,
      "eval_samples_per_second": 6.937,
      "eval_steps_per_second": 0.867,
      "step": 36
    },
    {
      "epoch": 0.00421359695324528,
      "grad_norm": 0.7065563201904297,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.7901,
      "step": 39
    },
    {
      "epoch": 0.0045377197958026095,
      "grad_norm": 0.7974684834480286,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.8999,
      "step": 42
    },
    {
      "epoch": 0.004861842638359939,
      "grad_norm": 0.7784953713417053,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.829,
      "step": 45
    },
    {
      "epoch": 0.004861842638359939,
      "eval_loss": 1.8407630920410156,
      "eval_runtime": 2249.9599,
      "eval_samples_per_second": 6.929,
      "eval_steps_per_second": 0.866,
      "step": 45
    },
    {
      "epoch": 0.005185965480917268,
      "grad_norm": 0.8616397976875305,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.9082,
      "step": 48
    },
    {
      "epoch": 0.005510088323474597,
      "grad_norm": 0.7725919485092163,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.7656,
      "step": 51
    },
    {
      "epoch": 0.005834211166031926,
      "grad_norm": 0.819065511226654,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.7582,
      "step": 54
    },
    {
      "epoch": 0.005834211166031926,
      "eval_loss": 1.81401526927948,
      "eval_runtime": 2248.0076,
      "eval_samples_per_second": 6.935,
      "eval_steps_per_second": 0.867,
      "step": 54
    },
    {
      "epoch": 0.006158334008589256,
      "grad_norm": 0.875109851360321,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.7555,
      "step": 57
    },
    {
      "epoch": 0.006482456851146585,
      "grad_norm": 0.8733634352684021,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.7831,
      "step": 60
    },
    {
      "epoch": 0.006806579693703914,
      "grad_norm": 0.8158807754516602,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.7586,
      "step": 63
    },
    {
      "epoch": 0.006806579693703914,
      "eval_loss": 1.7938640117645264,
      "eval_runtime": 2248.2668,
      "eval_samples_per_second": 6.934,
      "eval_steps_per_second": 0.867,
      "step": 63
    },
    {
      "epoch": 0.007130702536261243,
      "grad_norm": 0.8544221520423889,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.843,
      "step": 66
    },
    {
      "epoch": 0.007454825378818572,
      "grad_norm": 0.8683554530143738,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.7293,
      "step": 69
    },
    {
      "epoch": 0.007778948221375901,
      "grad_norm": 0.8561265468597412,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.704,
      "step": 72
    },
    {
      "epoch": 0.007778948221375901,
      "eval_loss": 1.780623435974121,
      "eval_runtime": 2250.299,
      "eval_samples_per_second": 6.928,
      "eval_steps_per_second": 0.866,
      "step": 72
    },
    {
      "epoch": 0.00810307106393323,
      "grad_norm": 0.8314185738563538,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.7721,
      "step": 75
    },
    {
      "epoch": 0.00842719390649056,
      "grad_norm": 0.8383832573890686,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.6971,
      "step": 78
    },
    {
      "epoch": 0.00875131674904789,
      "grad_norm": 0.9128426313400269,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.804,
      "step": 81
    },
    {
      "epoch": 0.00875131674904789,
      "eval_loss": 1.773253321647644,
      "eval_runtime": 2250.4544,
      "eval_samples_per_second": 6.927,
      "eval_steps_per_second": 0.866,
      "step": 81
    },
    {
      "epoch": 0.009075439591605219,
      "grad_norm": 0.8182294964790344,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.7684,
      "step": 84
    },
    {
      "epoch": 0.009399562434162548,
      "grad_norm": 0.8671604990959167,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.8174,
      "step": 87
    },
    {
      "epoch": 0.009723685276719877,
      "grad_norm": 0.8588350415229797,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.7666,
      "step": 90
    },
    {
      "epoch": 0.009723685276719877,
      "eval_loss": 1.7697868347167969,
      "eval_runtime": 2249.367,
      "eval_samples_per_second": 6.93,
      "eval_steps_per_second": 0.866,
      "step": 90
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3732317461676032e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}