{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.350109409190372,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00175054704595186,
      "eval_loss": 3.942631959915161,
      "eval_runtime": 6.5116,
      "eval_samples_per_second": 37.011,
      "eval_steps_per_second": 18.582,
      "step": 1
    },
    {
      "epoch": 0.0175054704595186,
      "grad_norm": 4.979578971862793,
      "learning_rate": 0.00019967573081342103,
      "loss": 2.0182,
      "step": 10
    },
    {
      "epoch": 0.0350109409190372,
      "grad_norm": 1.4861304759979248,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.3124,
      "step": 20
    },
    {
      "epoch": 0.0525164113785558,
      "grad_norm": 3.228330612182617,
      "learning_rate": 0.00019199794436588243,
      "loss": 0.2282,
      "step": 30
    },
    {
      "epoch": 0.0700218818380744,
      "grad_norm": 1.115767478942871,
      "learning_rate": 0.0001845190085543795,
      "loss": 0.1118,
      "step": 40
    },
    {
      "epoch": 0.087527352297593,
      "grad_norm": 2.745464563369751,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.1915,
      "step": 50
    },
    {
      "epoch": 0.087527352297593,
      "eval_loss": 0.15154829621315002,
      "eval_runtime": 6.5631,
      "eval_samples_per_second": 36.721,
      "eval_steps_per_second": 18.437,
      "step": 50
    },
    {
      "epoch": 0.1050328227571116,
      "grad_norm": 1.6342604160308838,
      "learning_rate": 0.00016324453755953773,
      "loss": 0.0955,
      "step": 60
    },
    {
      "epoch": 0.12253829321663019,
      "grad_norm": 1.03786039352417,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.1122,
      "step": 70
    },
    {
      "epoch": 0.1400437636761488,
      "grad_norm": 0.6428198218345642,
      "learning_rate": 0.00013546048870425356,
      "loss": 0.0688,
      "step": 80
    },
    {
      "epoch": 0.1575492341356674,
      "grad_norm": 0.3404603898525238,
      "learning_rate": 0.00012000256937760445,
      "loss": 0.1697,
      "step": 90
    },
    {
      "epoch": 0.175054704595186,
      "grad_norm": 1.3271960020065308,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.1069,
      "step": 100
    },
    {
      "epoch": 0.175054704595186,
      "eval_loss": 0.1051642894744873,
      "eval_runtime": 6.6187,
      "eval_samples_per_second": 36.412,
      "eval_steps_per_second": 18.282,
      "step": 100
    },
    {
      "epoch": 0.1925601750547046,
      "grad_norm": 0.5494540929794312,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.139,
      "step": 110
    },
    {
      "epoch": 0.2100656455142232,
      "grad_norm": 1.3071264028549194,
      "learning_rate": 7.217825360835473e-05,
      "loss": 0.1121,
      "step": 120
    },
    {
      "epoch": 0.2275711159737418,
      "grad_norm": 0.791406512260437,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.0977,
      "step": 130
    },
    {
      "epoch": 0.24507658643326038,
      "grad_norm": 0.7328794002532959,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 0.0691,
      "step": 140
    },
    {
      "epoch": 0.26258205689277897,
      "grad_norm": 2.1033480167388916,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.0896,
      "step": 150
    },
    {
      "epoch": 0.26258205689277897,
      "eval_loss": 0.08178930729627609,
      "eval_runtime": 6.5966,
      "eval_samples_per_second": 36.534,
      "eval_steps_per_second": 18.343,
      "step": 150
    },
    {
      "epoch": 0.2800875273522976,
      "grad_norm": 0.6359676122665405,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 0.0679,
      "step": 160
    },
    {
      "epoch": 0.2975929978118162,
      "grad_norm": 1.084639072418213,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 0.0587,
      "step": 170
    },
    {
      "epoch": 0.3150984682713348,
      "grad_norm": 0.6518976092338562,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.0666,
      "step": 180
    },
    {
      "epoch": 0.33260393873085337,
      "grad_norm": 2.068160057067871,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 0.075,
      "step": 190
    },
    {
      "epoch": 0.350109409190372,
      "grad_norm": 1.11619234085083,
      "learning_rate": 0.0,
      "loss": 0.102,
      "step": 200
    },
    {
      "epoch": 0.350109409190372,
      "eval_loss": 0.07777100801467896,
      "eval_runtime": 6.6104,
      "eval_samples_per_second": 36.458,
      "eval_steps_per_second": 18.304,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.00019466141696e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}