{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0970716712506067,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006471444750040447,
      "eval_loss": 11.117074966430664,
      "eval_runtime": 2.8477,
      "eval_samples_per_second": 228.602,
      "eval_steps_per_second": 114.476,
      "step": 1
    },
    {
      "epoch": 0.006471444750040446,
      "grad_norm": 2.144629955291748,
      "learning_rate": 0.00019967573081342103,
      "loss": 44.4509,
      "step": 10
    },
    {
      "epoch": 0.012942889500080892,
      "grad_norm": 2.5519111156463623,
      "learning_rate": 0.0001970941817426052,
      "loss": 44.3761,
      "step": 20
    },
    {
      "epoch": 0.01941433425012134,
      "grad_norm": 2.718752145767212,
      "learning_rate": 0.00019199794436588243,
      "loss": 44.2671,
      "step": 30
    },
    {
      "epoch": 0.025885779000161785,
      "grad_norm": 3.347476005554199,
      "learning_rate": 0.0001845190085543795,
      "loss": 44.0327,
      "step": 40
    },
    {
      "epoch": 0.03235722375020223,
      "grad_norm": 4.187604904174805,
      "learning_rate": 0.00017485107481711012,
      "loss": 43.8064,
      "step": 50
    },
    {
      "epoch": 0.03235722375020223,
      "eval_loss": 10.912104606628418,
      "eval_runtime": 1.7736,
      "eval_samples_per_second": 367.054,
      "eval_steps_per_second": 183.809,
      "step": 50
    },
    {
      "epoch": 0.03882866850024268,
      "grad_norm": 2.7762553691864014,
      "learning_rate": 0.00016324453755953773,
      "loss": 43.5101,
      "step": 60
    },
    {
      "epoch": 0.045300113250283124,
      "grad_norm": 2.4906129837036133,
      "learning_rate": 0.00015000000000000001,
      "loss": 43.3468,
      "step": 70
    },
    {
      "epoch": 0.05177155800032357,
      "grad_norm": 2.6845226287841797,
      "learning_rate": 0.00013546048870425356,
      "loss": 43.1958,
      "step": 80
    },
    {
      "epoch": 0.058243002750364016,
      "grad_norm": 2.6942412853240967,
      "learning_rate": 0.00012000256937760445,
      "loss": 43.1406,
      "step": 90
    },
    {
      "epoch": 0.06471444750040446,
      "grad_norm": 2.7743167877197266,
      "learning_rate": 0.00010402659401094152,
      "loss": 43.1343,
      "step": 100
    },
    {
      "epoch": 0.06471444750040446,
      "eval_loss": 10.77874755859375,
      "eval_runtime": 1.7761,
      "eval_samples_per_second": 366.527,
      "eval_steps_per_second": 183.545,
      "step": 100
    },
    {
      "epoch": 0.07118589225044492,
      "grad_norm": 2.3358705043792725,
      "learning_rate": 8.79463319744677e-05,
      "loss": 43.053,
      "step": 110
    },
    {
      "epoch": 0.07765733700048535,
      "grad_norm": 2.3423330783843994,
      "learning_rate": 7.217825360835473e-05,
      "loss": 43.1263,
      "step": 120
    },
    {
      "epoch": 0.08412878175052581,
      "grad_norm": 2.8382058143615723,
      "learning_rate": 5.713074385969457e-05,
      "loss": 43.1134,
      "step": 130
    },
    {
      "epoch": 0.09060022650056625,
      "grad_norm": 2.147097587585449,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 43.1149,
      "step": 140
    },
    {
      "epoch": 0.0970716712506067,
      "grad_norm": 2.8335659503936768,
      "learning_rate": 3.072756464904006e-05,
      "loss": 43.1158,
      "step": 150
    },
    {
      "epoch": 0.0970716712506067,
      "eval_loss": 10.772127151489258,
      "eval_runtime": 1.7825,
      "eval_samples_per_second": 365.22,
      "eval_steps_per_second": 182.89,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2249650077696.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}