{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7897334649555775,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003948667324777887,
      "eval_loss": 1.3262379169464111,
      "eval_runtime": 10.8176,
      "eval_samples_per_second": 9.891,
      "eval_steps_per_second": 4.992,
      "step": 1
    },
    {
      "epoch": 0.039486673247778874,
      "grad_norm": 0.5493721961975098,
      "learning_rate": 0.00019967573081342103,
      "loss": 1.3172,
      "step": 10
    },
    {
      "epoch": 0.07897334649555775,
      "grad_norm": 0.333873450756073,
      "learning_rate": 0.0001970941817426052,
      "loss": 0.9606,
      "step": 20
    },
    {
      "epoch": 0.11846001974333663,
      "grad_norm": 0.2658039927482605,
      "learning_rate": 0.00019199794436588243,
      "loss": 0.9031,
      "step": 30
    },
    {
      "epoch": 0.1579466929911155,
      "grad_norm": 0.3002346456050873,
      "learning_rate": 0.0001845190085543795,
      "loss": 0.969,
      "step": 40
    },
    {
      "epoch": 0.19743336623889438,
      "grad_norm": 0.3597181439399719,
      "learning_rate": 0.00017485107481711012,
      "loss": 0.8895,
      "step": 50
    },
    {
      "epoch": 0.19743336623889438,
      "eval_loss": 0.8028691411018372,
      "eval_runtime": 9.3102,
      "eval_samples_per_second": 11.493,
      "eval_steps_per_second": 5.8,
      "step": 50
    },
    {
      "epoch": 0.23692003948667326,
      "grad_norm": 0.3202034533023834,
      "learning_rate": 0.00016324453755953773,
      "loss": 0.7775,
      "step": 60
    },
    {
      "epoch": 0.2764067127344521,
      "grad_norm": 0.3071410655975342,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8543,
      "step": 70
    },
    {
      "epoch": 0.315893385982231,
      "grad_norm": 0.3607846200466156,
      "learning_rate": 0.00013546048870425356,
      "loss": 0.8547,
      "step": 80
    },
    {
      "epoch": 0.35538005923000987,
      "grad_norm": 0.395982027053833,
      "learning_rate": 0.00012000256937760445,
      "loss": 0.837,
      "step": 90
    },
    {
      "epoch": 0.39486673247778875,
      "grad_norm": 0.31234902143478394,
      "learning_rate": 0.00010402659401094152,
      "loss": 0.7726,
      "step": 100
    },
    {
      "epoch": 0.39486673247778875,
      "eval_loss": 0.7650652527809143,
      "eval_runtime": 9.3013,
      "eval_samples_per_second": 11.504,
      "eval_steps_per_second": 5.806,
      "step": 100
    },
    {
      "epoch": 0.43435340572556763,
      "grad_norm": 0.47384631633758545,
      "learning_rate": 8.79463319744677e-05,
      "loss": 0.8675,
      "step": 110
    },
    {
      "epoch": 0.4738400789733465,
      "grad_norm": 0.28773367404937744,
      "learning_rate": 7.217825360835473e-05,
      "loss": 0.7179,
      "step": 120
    },
    {
      "epoch": 0.5133267522211253,
      "grad_norm": 0.3070705235004425,
      "learning_rate": 5.713074385969457e-05,
      "loss": 0.7997,
      "step": 130
    },
    {
      "epoch": 0.5528134254689042,
      "grad_norm": 0.31054243445396423,
      "learning_rate": 4.3193525326884435e-05,
      "loss": 0.7867,
      "step": 140
    },
    {
      "epoch": 0.5923000987166831,
      "grad_norm": 0.3447147607803345,
      "learning_rate": 3.072756464904006e-05,
      "loss": 0.8358,
      "step": 150
    },
    {
      "epoch": 0.5923000987166831,
      "eval_loss": 0.7506125569343567,
      "eval_runtime": 9.3055,
      "eval_samples_per_second": 11.499,
      "eval_steps_per_second": 5.803,
      "step": 150
    },
    {
      "epoch": 0.631786771964462,
      "grad_norm": 0.335482656955719,
      "learning_rate": 2.0055723659649904e-05,
      "loss": 0.7052,
      "step": 160
    },
    {
      "epoch": 0.6712734452122409,
      "grad_norm": 0.3157788813114166,
      "learning_rate": 1.1454397434679021e-05,
      "loss": 0.7612,
      "step": 170
    },
    {
      "epoch": 0.7107601184600197,
      "grad_norm": 0.35480332374572754,
      "learning_rate": 5.146355805285452e-06,
      "loss": 0.8409,
      "step": 180
    },
    {
      "epoch": 0.7502467917077986,
      "grad_norm": 0.5036816596984863,
      "learning_rate": 1.2949737362087156e-06,
      "loss": 0.792,
      "step": 190
    },
    {
      "epoch": 0.7897334649555775,
      "grad_norm": 0.3984379470348358,
      "learning_rate": 0.0,
      "loss": 0.8132,
      "step": 200
    },
    {
      "epoch": 0.7897334649555775,
      "eval_loss": 0.7477403879165649,
      "eval_runtime": 9.3074,
      "eval_samples_per_second": 11.496,
      "eval_steps_per_second": 5.802,
      "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": 1.2023660345819136e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}