{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011974613818704347,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011974613818704346,
      "grad_norm": 2.251413106918335,
      "learning_rate": 2e-05,
      "loss": 3.5934,
      "step": 1
    },
    {
      "epoch": 0.00011974613818704346,
      "eval_loss": 4.004216194152832,
      "eval_runtime": 71.5033,
      "eval_samples_per_second": 49.187,
      "eval_steps_per_second": 24.6,
      "step": 1
    },
    {
      "epoch": 0.00023949227637408692,
      "grad_norm": 1.485583782196045,
      "learning_rate": 4e-05,
      "loss": 3.1619,
      "step": 2
    },
    {
      "epoch": 0.0003592384145611304,
      "grad_norm": 2.3061623573303223,
      "learning_rate": 6e-05,
      "loss": 4.671,
      "step": 3
    },
    {
      "epoch": 0.0003592384145611304,
      "eval_loss": 3.9957385063171387,
      "eval_runtime": 71.3319,
      "eval_samples_per_second": 49.305,
      "eval_steps_per_second": 24.659,
      "step": 3
    },
    {
      "epoch": 0.00047898455274817384,
      "grad_norm": 1.844711184501648,
      "learning_rate": 8e-05,
      "loss": 3.3148,
      "step": 4
    },
    {
      "epoch": 0.0005987306909352174,
      "grad_norm": 1.8286521434783936,
      "learning_rate": 0.0001,
      "loss": 3.9424,
      "step": 5
    },
    {
      "epoch": 0.0007184768291222608,
      "grad_norm": 1.9494376182556152,
      "learning_rate": 0.00012,
      "loss": 4.0819,
      "step": 6
    },
    {
      "epoch": 0.0007184768291222608,
      "eval_loss": 3.870119571685791,
      "eval_runtime": 71.1094,
      "eval_samples_per_second": 49.459,
      "eval_steps_per_second": 24.737,
      "step": 6
    },
    {
      "epoch": 0.0008382229673093043,
      "grad_norm": 2.0741891860961914,
      "learning_rate": 0.00014,
      "loss": 4.1838,
      "step": 7
    },
    {
      "epoch": 0.0009579691054963477,
      "grad_norm": 1.8809219598770142,
      "learning_rate": 0.00016,
      "loss": 3.7116,
      "step": 8
    },
    {
      "epoch": 0.0010777152436833913,
      "grad_norm": 2.2756588459014893,
      "learning_rate": 0.00018,
      "loss": 3.7514,
      "step": 9
    },
    {
      "epoch": 0.0010777152436833913,
      "eval_loss": 3.5219669342041016,
      "eval_runtime": 69.6767,
      "eval_samples_per_second": 50.476,
      "eval_steps_per_second": 25.245,
      "step": 9
    },
    {
      "epoch": 0.0011974613818704347,
      "grad_norm": 2.215054750442505,
      "learning_rate": 0.0002,
      "loss": 3.0007,
      "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": 324298258513920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}