{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017052721330112264,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005684240443370755,
      "eval_loss": 10.375810623168945,
      "eval_runtime": 2.409,
      "eval_samples_per_second": 307.6,
      "eval_steps_per_second": 154.008,
      "step": 1
    },
    {
      "epoch": 0.0017052721330112265,
      "grad_norm": 0.04671907424926758,
      "learning_rate": 6e-05,
      "loss": 10.3748,
      "step": 3
    },
    {
      "epoch": 0.003410544266022453,
      "grad_norm": 0.03484569489955902,
      "learning_rate": 0.00012,
      "loss": 10.3753,
      "step": 6
    },
    {
      "epoch": 0.004547392354696604,
      "eval_loss": 10.375182151794434,
      "eval_runtime": 2.4457,
      "eval_samples_per_second": 302.975,
      "eval_steps_per_second": 151.692,
      "step": 8
    },
    {
      "epoch": 0.005115816399033679,
      "grad_norm": 0.03888724371790886,
      "learning_rate": 0.00018,
      "loss": 10.3758,
      "step": 9
    },
    {
      "epoch": 0.006821088532044906,
      "grad_norm": 0.04945020750164986,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.3754,
      "step": 12
    },
    {
      "epoch": 0.008526360665056132,
      "grad_norm": 0.049591515213251114,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.3742,
      "step": 15
    },
    {
      "epoch": 0.009094784709393207,
      "eval_loss": 10.3734769821167,
      "eval_runtime": 2.4224,
      "eval_samples_per_second": 305.896,
      "eval_steps_per_second": 153.154,
      "step": 16
    },
    {
      "epoch": 0.010231632798067358,
      "grad_norm": 0.039638299494981766,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.3758,
      "step": 18
    },
    {
      "epoch": 0.011936904931078584,
      "grad_norm": 0.05505520850419998,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.3725,
      "step": 21
    },
    {
      "epoch": 0.013642177064089812,
      "grad_norm": 0.05461163446307182,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.3733,
      "step": 24
    },
    {
      "epoch": 0.013642177064089812,
      "eval_loss": 10.372425079345703,
      "eval_runtime": 2.4429,
      "eval_samples_per_second": 303.324,
      "eval_steps_per_second": 151.867,
      "step": 24
    },
    {
      "epoch": 0.015347449197101038,
      "grad_norm": 0.05005059391260147,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 10.3728,
      "step": 27
    },
    {
      "epoch": 0.017052721330112264,
      "grad_norm": 0.04543205350637436,
      "learning_rate": 0.0,
      "loss": 10.3697,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 810687922176.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}