{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 3000,
  "global_step": 9064,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13241379310344828,
      "grad_norm": 0.2709992527961731,
      "learning_rate": 6.604189636163176e-05,
      "loss": 0.4358,
      "step": 600
    },
    {
      "epoch": 0.26482758620689656,
      "grad_norm": 0.17993643879890442,
      "learning_rate": 9.968414572743643e-05,
      "loss": 0.0466,
      "step": 1200
    },
    {
      "epoch": 0.3972413793103448,
      "grad_norm": 0.17993822693824768,
      "learning_rate": 9.70783181950037e-05,
      "loss": 0.0417,
      "step": 1800
    },
    {
      "epoch": 0.5296551724137931,
      "grad_norm": 0.2322826236486435,
      "learning_rate": 9.19696754273079e-05,
      "loss": 0.0389,
      "step": 2400
    },
    {
      "epoch": 0.6620689655172414,
      "grad_norm": 0.16364118456840515,
      "learning_rate": 8.462980718032852e-05,
      "loss": 0.0393,
      "step": 3000
    },
    {
      "epoch": 0.6620689655172414,
      "eval_loss": 0.03762035071849823,
      "eval_runtime": 92.878,
      "eval_samples_per_second": 323.004,
      "eval_steps_per_second": 20.188,
      "step": 3000
    },
    {
      "epoch": 0.7944827586206896,
      "grad_norm": 0.1851811707019806,
      "learning_rate": 7.544892140493736e-05,
      "loss": 0.0375,
      "step": 3600
    },
    {
      "epoch": 0.926896551724138,
      "grad_norm": 0.17068427801132202,
      "learning_rate": 6.49150996994762e-05,
      "loss": 0.0373,
      "step": 4200
    },
    {
      "epoch": 1.059144827586207,
      "grad_norm": 0.1241922676563263,
      "learning_rate": 5.358834952514551e-05,
      "loss": 0.0332,
      "step": 4800
    },
    {
      "epoch": 1.1915586206896551,
      "grad_norm": 0.13463670015335083,
      "learning_rate": 4.2070832641099686e-05,
      "loss": 0.0303,
      "step": 5400
    },
    {
      "epoch": 1.3239724137931035,
      "grad_norm": 0.20478974282741547,
      "learning_rate": 3.097485249901231e-05,
      "loss": 0.031,
      "step": 6000
    },
    {
      "epoch": 1.3239724137931035,
      "eval_loss": 0.035575784742832184,
      "eval_runtime": 93.0574,
      "eval_samples_per_second": 322.382,
      "eval_steps_per_second": 20.149,
      "step": 6000
    },
    {
      "epoch": 1.4563862068965516,
      "grad_norm": 0.22410421073436737,
      "learning_rate": 2.089030247686608e-05,
      "loss": 0.0301,
      "step": 6600
    },
    {
      "epoch": 1.5888,
      "grad_norm": 0.23571571707725525,
      "learning_rate": 1.2353305495017958e-05,
      "loss": 0.0297,
      "step": 7200
    },
    {
      "epoch": 1.7212137931034484,
      "grad_norm": 0.1075667217373848,
      "learning_rate": 5.817712220372823e-06,
      "loss": 0.029,
      "step": 7800
    },
    {
      "epoch": 1.8536275862068967,
      "grad_norm": 0.11598219722509384,
      "learning_rate": 1.6309730939492506e-06,
      "loss": 0.0296,
      "step": 8400
    },
    {
      "epoch": 1.9860413793103449,
      "grad_norm": 0.23589642345905304,
      "learning_rate": 1.56668924206127e-08,
      "loss": 0.0297,
      "step": 9000
    },
    {
      "epoch": 1.9860413793103449,
      "eval_loss": 0.03463894873857498,
      "eval_runtime": 93.0156,
      "eval_samples_per_second": 322.526,
      "eval_steps_per_second": 20.158,
      "step": 9000
    },
    {
      "epoch": 2.0,
      "step": 9064,
      "total_flos": 2.252979556375855e+18,
      "train_loss": 0.06108480966785579,
      "train_runtime": 11818.6761,
      "train_samples_per_second": 98.15,
      "train_steps_per_second": 0.767
    }
  ],
  "logging_steps": 600,
  "max_steps": 9064,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 3000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.252979556375855e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}