{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005365310584416455,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.365310584416455e-05,
      "grad_norm": 0.8277385234832764,
      "learning_rate": 2e-05,
      "loss": 41.4857,
      "step": 1
    },
    {
      "epoch": 5.365310584416455e-05,
      "eval_loss": 10.372055053710938,
      "eval_runtime": 84.9007,
      "eval_samples_per_second": 46.219,
      "eval_steps_per_second": 46.219,
      "step": 1
    },
    {
      "epoch": 0.0001073062116883291,
      "grad_norm": 0.6603090763092041,
      "learning_rate": 4e-05,
      "loss": 41.5089,
      "step": 2
    },
    {
      "epoch": 0.00016095931753249367,
      "grad_norm": 0.7006505727767944,
      "learning_rate": 6e-05,
      "loss": 41.5087,
      "step": 3
    },
    {
      "epoch": 0.00016095931753249367,
      "eval_loss": 10.371822357177734,
      "eval_runtime": 85.4377,
      "eval_samples_per_second": 45.928,
      "eval_steps_per_second": 45.928,
      "step": 3
    },
    {
      "epoch": 0.0002146124233766582,
      "grad_norm": 0.6972599625587463,
      "learning_rate": 8e-05,
      "loss": 41.5419,
      "step": 4
    },
    {
      "epoch": 0.00026826552922082277,
      "grad_norm": 0.7561557292938232,
      "learning_rate": 0.0001,
      "loss": 41.4951,
      "step": 5
    },
    {
      "epoch": 0.00032191863506498734,
      "grad_norm": 0.7340295910835266,
      "learning_rate": 0.00012,
      "loss": 41.5246,
      "step": 6
    },
    {
      "epoch": 0.00032191863506498734,
      "eval_loss": 10.3707857131958,
      "eval_runtime": 83.871,
      "eval_samples_per_second": 46.786,
      "eval_steps_per_second": 46.786,
      "step": 6
    },
    {
      "epoch": 0.0003755717409091519,
      "grad_norm": 1.1356993913650513,
      "learning_rate": 0.00014,
      "loss": 41.4939,
      "step": 7
    },
    {
      "epoch": 0.0004292248467533164,
      "grad_norm": 0.7849339246749878,
      "learning_rate": 0.00016,
      "loss": 41.5194,
      "step": 8
    },
    {
      "epoch": 0.000482877952597481,
      "grad_norm": 0.8372148275375366,
      "learning_rate": 0.00018,
      "loss": 41.5192,
      "step": 9
    },
    {
      "epoch": 0.000482877952597481,
      "eval_loss": 10.368990898132324,
      "eval_runtime": 84.8908,
      "eval_samples_per_second": 46.224,
      "eval_steps_per_second": 46.224,
      "step": 9
    },
    {
      "epoch": 0.0005365310584416455,
      "grad_norm": 0.8866844773292542,
      "learning_rate": 0.0002,
      "loss": 41.4751,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1033371648000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}