{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0001293259531322746,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2932595313227458e-05,
      "grad_norm": 3.7563729286193848,
      "learning_rate": 2e-05,
      "loss": 4.0778,
      "step": 1
    },
    {
      "epoch": 1.2932595313227458e-05,
      "eval_loss": 4.393791675567627,
      "eval_runtime": 1116.2276,
      "eval_samples_per_second": 29.168,
      "eval_steps_per_second": 14.584,
      "step": 1
    },
    {
      "epoch": 2.5865190626454916e-05,
      "grad_norm": 3.8288331031799316,
      "learning_rate": 4e-05,
      "loss": 4.0814,
      "step": 2
    },
    {
      "epoch": 3.8797785939682375e-05,
      "grad_norm": 4.589884281158447,
      "learning_rate": 6e-05,
      "loss": 3.8386,
      "step": 3
    },
    {
      "epoch": 3.8797785939682375e-05,
      "eval_loss": 4.3694987297058105,
      "eval_runtime": 1114.9309,
      "eval_samples_per_second": 29.202,
      "eval_steps_per_second": 14.601,
      "step": 3
    },
    {
      "epoch": 5.173038125290983e-05,
      "grad_norm": 4.058362007141113,
      "learning_rate": 8e-05,
      "loss": 4.2735,
      "step": 4
    },
    {
      "epoch": 6.46629765661373e-05,
      "grad_norm": 3.612135648727417,
      "learning_rate": 0.0001,
      "loss": 3.8166,
      "step": 5
    },
    {
      "epoch": 7.759557187936475e-05,
      "grad_norm": 4.7833123207092285,
      "learning_rate": 0.00012,
      "loss": 4.5292,
      "step": 6
    },
    {
      "epoch": 7.759557187936475e-05,
      "eval_loss": 4.090203285217285,
      "eval_runtime": 1115.6645,
      "eval_samples_per_second": 29.183,
      "eval_steps_per_second": 14.591,
      "step": 6
    },
    {
      "epoch": 9.052816719259221e-05,
      "grad_norm": 3.1701056957244873,
      "learning_rate": 0.00014,
      "loss": 3.5155,
      "step": 7
    },
    {
      "epoch": 0.00010346076250581966,
      "grad_norm": 7.336368083953857,
      "learning_rate": 0.00016,
      "loss": 3.4763,
      "step": 8
    },
    {
      "epoch": 0.00011639335781904713,
      "grad_norm": 5.934755802154541,
      "learning_rate": 0.00018,
      "loss": 3.289,
      "step": 9
    },
    {
      "epoch": 0.00011639335781904713,
      "eval_loss": 3.7894675731658936,
      "eval_runtime": 1116.3162,
      "eval_samples_per_second": 29.166,
      "eval_steps_per_second": 14.583,
      "step": 9
    },
    {
      "epoch": 0.0001293259531322746,
      "grad_norm": 9.112296104431152,
      "learning_rate": 0.0002,
      "loss": 3.3518,
      "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": 1911091416268800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}