{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008595680670463093,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.595680670463093e-05,
      "grad_norm": 20.272014617919922,
      "learning_rate": 2e-05,
      "loss": 16.756,
      "step": 1
    },
    {
      "epoch": 0.00017191361340926185,
      "grad_norm": 19.457138061523438,
      "learning_rate": 4e-05,
      "loss": 17.2255,
      "step": 2
    },
    {
      "epoch": 0.0002578704201138928,
      "grad_norm": 16.550790786743164,
      "learning_rate": 6e-05,
      "loss": 15.8336,
      "step": 3
    },
    {
      "epoch": 0.0002578704201138928,
      "eval_loss": 4.113801956176758,
      "eval_runtime": 146.8718,
      "eval_samples_per_second": 33.356,
      "eval_steps_per_second": 16.681,
      "step": 3
    },
    {
      "epoch": 0.0003438272268185237,
      "grad_norm": 20.95903205871582,
      "learning_rate": 8e-05,
      "loss": 18.2993,
      "step": 4
    },
    {
      "epoch": 0.00042978403352315463,
      "grad_norm": 17.93225860595703,
      "learning_rate": 0.0001,
      "loss": 16.4708,
      "step": 5
    },
    {
      "epoch": 0.0005157408402277856,
      "grad_norm": 20.221960067749023,
      "learning_rate": 0.00012,
      "loss": 17.6026,
      "step": 6
    },
    {
      "epoch": 0.0005157408402277856,
      "eval_loss": 3.6323037147521973,
      "eval_runtime": 149.1064,
      "eval_samples_per_second": 32.856,
      "eval_steps_per_second": 16.431,
      "step": 6
    },
    {
      "epoch": 0.0006016976469324165,
      "grad_norm": 17.98997688293457,
      "learning_rate": 0.00014,
      "loss": 14.4988,
      "step": 7
    },
    {
      "epoch": 0.0006876544536370474,
      "grad_norm": 21.785926818847656,
      "learning_rate": 0.00016,
      "loss": 14.1824,
      "step": 8
    },
    {
      "epoch": 0.0007736112603416783,
      "grad_norm": 17.540714263916016,
      "learning_rate": 0.00018,
      "loss": 11.676,
      "step": 9
    },
    {
      "epoch": 0.0007736112603416783,
      "eval_loss": 2.6782336235046387,
      "eval_runtime": 150.7345,
      "eval_samples_per_second": 32.501,
      "eval_steps_per_second": 16.254,
      "step": 9
    },
    {
      "epoch": 0.0008595680670463093,
      "grad_norm": 23.379283905029297,
      "learning_rate": 0.0002,
      "loss": 11.8631,
      "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": 298765642629120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}