{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008452013692262181,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016904027384524362,
      "eval_loss": 10.364038467407227,
      "eval_runtime": 14.2365,
      "eval_samples_per_second": 174.972,
      "eval_steps_per_second": 87.521,
      "step": 1
    },
    {
      "epoch": 0.0008452013692262181,
      "grad_norm": 0.0941619798541069,
      "learning_rate": 5e-05,
      "loss": 10.3613,
      "step": 5
    },
    {
      "epoch": 0.0016904027384524363,
      "grad_norm": 0.10301538556814194,
      "learning_rate": 0.0001,
      "loss": 10.3623,
      "step": 10
    },
    {
      "epoch": 0.0016904027384524363,
      "eval_loss": 10.363155364990234,
      "eval_runtime": 14.1323,
      "eval_samples_per_second": 176.263,
      "eval_steps_per_second": 88.167,
      "step": 10
    },
    {
      "epoch": 0.0025356041076786545,
      "grad_norm": 0.11786334216594696,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3614,
      "step": 15
    },
    {
      "epoch": 0.0033808054769048725,
      "grad_norm": 0.10351554304361343,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3634,
      "step": 20
    },
    {
      "epoch": 0.0033808054769048725,
      "eval_loss": 10.361242294311523,
      "eval_runtime": 14.1251,
      "eval_samples_per_second": 176.353,
      "eval_steps_per_second": 88.212,
      "step": 20
    },
    {
      "epoch": 0.004226006846131091,
      "grad_norm": 0.10456075519323349,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3622,
      "step": 25
    },
    {
      "epoch": 0.005071208215357309,
      "grad_norm": 0.0968402698636055,
      "learning_rate": 5e-05,
      "loss": 10.3647,
      "step": 30
    },
    {
      "epoch": 0.005071208215357309,
      "eval_loss": 10.359764099121094,
      "eval_runtime": 14.2703,
      "eval_samples_per_second": 174.559,
      "eval_steps_per_second": 87.314,
      "step": 30
    },
    {
      "epoch": 0.005916409584583527,
      "grad_norm": 0.10970701277256012,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3625,
      "step": 35
    },
    {
      "epoch": 0.006761610953809745,
      "grad_norm": 0.11446528136730194,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3597,
      "step": 40
    },
    {
      "epoch": 0.006761610953809745,
      "eval_loss": 10.359040260314941,
      "eval_runtime": 14.3392,
      "eval_samples_per_second": 173.719,
      "eval_steps_per_second": 86.895,
      "step": 40
    },
    {
      "epoch": 0.0076068123230359636,
      "grad_norm": 0.10877200216054916,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3589,
      "step": 45
    },
    {
      "epoch": 0.008452013692262181,
      "grad_norm": 0.11139176040887833,
      "learning_rate": 0.0,
      "loss": 10.3584,
      "step": 50
    },
    {
      "epoch": 0.008452013692262181,
      "eval_loss": 10.358901023864746,
      "eval_runtime": 14.1036,
      "eval_samples_per_second": 176.622,
      "eval_steps_per_second": 88.347,
      "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": 808181760000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}