{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07017543859649122,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014035087719298245,
      "eval_loss": 11.166300773620605,
      "eval_runtime": 1.7265,
      "eval_samples_per_second": 173.758,
      "eval_steps_per_second": 86.879,
      "step": 1
    },
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 4.016921043395996,
      "learning_rate": 5e-05,
      "loss": 44.6916,
      "step": 5
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 4.227939605712891,
      "learning_rate": 0.0001,
      "loss": 44.5734,
      "step": 10
    },
    {
      "epoch": 0.014035087719298246,
      "eval_loss": 11.1311674118042,
      "eval_runtime": 1.3958,
      "eval_samples_per_second": 214.926,
      "eval_steps_per_second": 107.463,
      "step": 10
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 4.580113410949707,
      "learning_rate": 9.619397662556435e-05,
      "loss": 44.4809,
      "step": 15
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 5.107155799865723,
      "learning_rate": 8.535533905932738e-05,
      "loss": 44.2651,
      "step": 20
    },
    {
      "epoch": 0.028070175438596492,
      "eval_loss": 11.03613567352295,
      "eval_runtime": 1.4299,
      "eval_samples_per_second": 209.812,
      "eval_steps_per_second": 104.906,
      "step": 20
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 5.350675106048584,
      "learning_rate": 6.91341716182545e-05,
      "loss": 44.0636,
      "step": 25
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 5.687300682067871,
      "learning_rate": 5e-05,
      "loss": 43.8965,
      "step": 30
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 10.94633960723877,
      "eval_runtime": 1.4322,
      "eval_samples_per_second": 209.472,
      "eval_steps_per_second": 104.736,
      "step": 30
    },
    {
      "epoch": 0.04912280701754386,
      "grad_norm": 5.789061069488525,
      "learning_rate": 3.086582838174551e-05,
      "loss": 43.7472,
      "step": 35
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 5.840606689453125,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 43.6562,
      "step": 40
    },
    {
      "epoch": 0.056140350877192984,
      "eval_loss": 10.899812698364258,
      "eval_runtime": 1.4235,
      "eval_samples_per_second": 210.752,
      "eval_steps_per_second": 105.376,
      "step": 40
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 5.924816608428955,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 43.5953,
      "step": 45
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 5.921303749084473,
      "learning_rate": 0.0,
      "loss": 43.5959,
      "step": 50
    },
    {
      "epoch": 0.07017543859649122,
      "eval_loss": 10.889740943908691,
      "eval_runtime": 1.4388,
      "eval_samples_per_second": 208.502,
      "eval_steps_per_second": 104.251,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 482240102400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}