{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016485328058028353,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003297065611605671,
      "eval_loss": 1.7371102571487427,
      "eval_runtime": 107.3446,
      "eval_samples_per_second": 11.896,
      "eval_steps_per_second": 5.953,
      "step": 1
    },
    {
      "epoch": 0.0016485328058028356,
      "grad_norm": 2.65769100189209,
      "learning_rate": 5e-05,
      "loss": 1.6975,
      "step": 5
    },
    {
      "epoch": 0.003297065611605671,
      "grad_norm": 0.8702275156974792,
      "learning_rate": 0.0001,
      "loss": 1.7031,
      "step": 10
    },
    {
      "epoch": 0.003297065611605671,
      "eval_loss": 1.6398742198944092,
      "eval_runtime": 108.2988,
      "eval_samples_per_second": 11.791,
      "eval_steps_per_second": 5.9,
      "step": 10
    },
    {
      "epoch": 0.004945598417408506,
      "grad_norm": 1.2809540033340454,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5345,
      "step": 15
    },
    {
      "epoch": 0.006594131223211342,
      "grad_norm": 1.4522932767868042,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4649,
      "step": 20
    },
    {
      "epoch": 0.006594131223211342,
      "eval_loss": 1.5140254497528076,
      "eval_runtime": 108.128,
      "eval_samples_per_second": 11.81,
      "eval_steps_per_second": 5.91,
      "step": 20
    },
    {
      "epoch": 0.008242664029014177,
      "grad_norm": 0.8049747943878174,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5008,
      "step": 25
    },
    {
      "epoch": 0.009891196834817012,
      "grad_norm": 1.0200544595718384,
      "learning_rate": 5e-05,
      "loss": 1.4498,
      "step": 30
    },
    {
      "epoch": 0.009891196834817012,
      "eval_loss": 1.4782603979110718,
      "eval_runtime": 108.2909,
      "eval_samples_per_second": 11.792,
      "eval_steps_per_second": 5.901,
      "step": 30
    },
    {
      "epoch": 0.01153972964061985,
      "grad_norm": 0.7654266357421875,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.4747,
      "step": 35
    },
    {
      "epoch": 0.013188262446422684,
      "grad_norm": 1.2618045806884766,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.5433,
      "step": 40
    },
    {
      "epoch": 0.013188262446422684,
      "eval_loss": 1.465818166732788,
      "eval_runtime": 108.4313,
      "eval_samples_per_second": 11.777,
      "eval_steps_per_second": 5.893,
      "step": 40
    },
    {
      "epoch": 0.01483679525222552,
      "grad_norm": 1.133446216583252,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.4862,
      "step": 45
    },
    {
      "epoch": 0.016485328058028353,
      "grad_norm": 0.9988188743591309,
      "learning_rate": 0.0,
      "loss": 1.443,
      "step": 50
    },
    {
      "epoch": 0.016485328058028353,
      "eval_loss": 1.4631625413894653,
      "eval_runtime": 108.1377,
      "eval_samples_per_second": 11.809,
      "eval_steps_per_second": 5.909,
      "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": 1.2299602250170368e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}