{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03827751196172249,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 0.35444825887680054,
      "learning_rate": 2e-05,
      "loss": 1.6478,
      "step": 1
    },
    {
      "epoch": 0.003827751196172249,
      "eval_loss": 1.7360095977783203,
      "eval_runtime": 10.914,
      "eval_samples_per_second": 10.079,
      "eval_steps_per_second": 5.039,
      "step": 1
    },
    {
      "epoch": 0.007655502392344498,
      "grad_norm": 0.3351192772388458,
      "learning_rate": 4e-05,
      "loss": 1.5945,
      "step": 2
    },
    {
      "epoch": 0.011483253588516746,
      "grad_norm": 0.3338252902030945,
      "learning_rate": 6e-05,
      "loss": 1.6237,
      "step": 3
    },
    {
      "epoch": 0.011483253588516746,
      "eval_loss": 1.7348536252975464,
      "eval_runtime": 10.3015,
      "eval_samples_per_second": 10.678,
      "eval_steps_per_second": 5.339,
      "step": 3
    },
    {
      "epoch": 0.015311004784688996,
      "grad_norm": 0.36520257592201233,
      "learning_rate": 8e-05,
      "loss": 1.7918,
      "step": 4
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 0.3350614309310913,
      "learning_rate": 0.0001,
      "loss": 1.4927,
      "step": 5
    },
    {
      "epoch": 0.022966507177033493,
      "grad_norm": 0.37864962220191956,
      "learning_rate": 0.00012,
      "loss": 1.5385,
      "step": 6
    },
    {
      "epoch": 0.022966507177033493,
      "eval_loss": 1.7223966121673584,
      "eval_runtime": 10.3008,
      "eval_samples_per_second": 10.679,
      "eval_steps_per_second": 5.339,
      "step": 6
    },
    {
      "epoch": 0.026794258373205742,
      "grad_norm": 0.4997591972351074,
      "learning_rate": 0.00014,
      "loss": 1.7189,
      "step": 7
    },
    {
      "epoch": 0.03062200956937799,
      "grad_norm": 0.4674946367740631,
      "learning_rate": 0.00016,
      "loss": 1.6419,
      "step": 8
    },
    {
      "epoch": 0.03444976076555024,
      "grad_norm": 0.5153182744979858,
      "learning_rate": 0.00018,
      "loss": 1.5711,
      "step": 9
    },
    {
      "epoch": 0.03444976076555024,
      "eval_loss": 1.6457775831222534,
      "eval_runtime": 10.3222,
      "eval_samples_per_second": 10.657,
      "eval_steps_per_second": 5.328,
      "step": 9
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 0.44957005977630615,
      "learning_rate": 0.0002,
      "loss": 1.3155,
      "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": 6332410861977600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}