{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002391629297458894,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002391629297458894,
      "grad_norm": 1.466945767402649,
      "learning_rate": 2e-05,
      "loss": 44.3552,
      "step": 1
    },
    {
      "epoch": 0.0002391629297458894,
      "eval_loss": 11.093308448791504,
      "eval_runtime": 4.4049,
      "eval_samples_per_second": 399.779,
      "eval_steps_per_second": 200.003,
      "step": 1
    },
    {
      "epoch": 0.0004783258594917788,
      "grad_norm": 1.5820708274841309,
      "learning_rate": 4e-05,
      "loss": 44.3894,
      "step": 2
    },
    {
      "epoch": 0.0007174887892376681,
      "grad_norm": 1.4892654418945312,
      "learning_rate": 6e-05,
      "loss": 44.4284,
      "step": 3
    },
    {
      "epoch": 0.0007174887892376681,
      "eval_loss": 11.09329605102539,
      "eval_runtime": 3.5866,
      "eval_samples_per_second": 490.995,
      "eval_steps_per_second": 245.637,
      "step": 3
    },
    {
      "epoch": 0.0009566517189835576,
      "grad_norm": 1.304399847984314,
      "learning_rate": 8e-05,
      "loss": 44.3973,
      "step": 4
    },
    {
      "epoch": 0.001195814648729447,
      "grad_norm": 1.4158371686935425,
      "learning_rate": 0.0001,
      "loss": 44.4088,
      "step": 5
    },
    {
      "epoch": 0.0014349775784753362,
      "grad_norm": 1.4809318780899048,
      "learning_rate": 0.00012,
      "loss": 44.4101,
      "step": 6
    },
    {
      "epoch": 0.0014349775784753362,
      "eval_loss": 11.092947959899902,
      "eval_runtime": 3.6509,
      "eval_samples_per_second": 482.341,
      "eval_steps_per_second": 241.307,
      "step": 6
    },
    {
      "epoch": 0.0016741405082212257,
      "grad_norm": 1.3704959154129028,
      "learning_rate": 0.00014,
      "loss": 44.3932,
      "step": 7
    },
    {
      "epoch": 0.0019133034379671151,
      "grad_norm": 1.4836734533309937,
      "learning_rate": 0.00016,
      "loss": 44.3278,
      "step": 8
    },
    {
      "epoch": 0.0021524663677130046,
      "grad_norm": 1.3619009256362915,
      "learning_rate": 0.00018,
      "loss": 44.4139,
      "step": 9
    },
    {
      "epoch": 0.0021524663677130046,
      "eval_loss": 11.09217643737793,
      "eval_runtime": 3.6561,
      "eval_samples_per_second": 481.655,
      "eval_steps_per_second": 240.964,
      "step": 9
    },
    {
      "epoch": 0.002391629297458894,
      "grad_norm": 1.4670937061309814,
      "learning_rate": 0.0002,
      "loss": 44.374,
      "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": 7471104000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}