{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01046517712312281,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020930354246245618,
      "eval_loss": 1.8958899974822998,
      "eval_runtime": 207.7108,
      "eval_samples_per_second": 9.687,
      "eval_steps_per_second": 4.843,
      "step": 1
    },
    {
      "epoch": 0.0010465177123122808,
      "grad_norm": 0.45888450741767883,
      "learning_rate": 5e-05,
      "loss": 1.9233,
      "step": 5
    },
    {
      "epoch": 0.0020930354246245617,
      "grad_norm": 0.573957085609436,
      "learning_rate": 0.0001,
      "loss": 1.8975,
      "step": 10
    },
    {
      "epoch": 0.0020930354246245617,
      "eval_loss": 1.7665126323699951,
      "eval_runtime": 208.423,
      "eval_samples_per_second": 9.653,
      "eval_steps_per_second": 4.827,
      "step": 10
    },
    {
      "epoch": 0.0031395531369368427,
      "grad_norm": 0.41039520502090454,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.636,
      "step": 15
    },
    {
      "epoch": 0.004186070849249123,
      "grad_norm": 0.44465190172195435,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.6819,
      "step": 20
    },
    {
      "epoch": 0.004186070849249123,
      "eval_loss": 1.6750926971435547,
      "eval_runtime": 208.5267,
      "eval_samples_per_second": 9.649,
      "eval_steps_per_second": 4.824,
      "step": 20
    },
    {
      "epoch": 0.005232588561561405,
      "grad_norm": 0.39231956005096436,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6586,
      "step": 25
    },
    {
      "epoch": 0.0062791062738736855,
      "grad_norm": 0.327115535736084,
      "learning_rate": 5e-05,
      "loss": 1.6449,
      "step": 30
    },
    {
      "epoch": 0.0062791062738736855,
      "eval_loss": 1.6352941989898682,
      "eval_runtime": 208.9401,
      "eval_samples_per_second": 9.63,
      "eval_steps_per_second": 4.815,
      "step": 30
    },
    {
      "epoch": 0.007325623986185966,
      "grad_norm": 0.39810481667518616,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6028,
      "step": 35
    },
    {
      "epoch": 0.008372141698498247,
      "grad_norm": 0.3222658634185791,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.6317,
      "step": 40
    },
    {
      "epoch": 0.008372141698498247,
      "eval_loss": 1.6276148557662964,
      "eval_runtime": 208.3143,
      "eval_samples_per_second": 9.658,
      "eval_steps_per_second": 4.829,
      "step": 40
    },
    {
      "epoch": 0.009418659410810527,
      "grad_norm": 0.3134675920009613,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.6246,
      "step": 45
    },
    {
      "epoch": 0.01046517712312281,
      "grad_norm": 0.3996317684650421,
      "learning_rate": 0.0,
      "loss": 1.6149,
      "step": 50
    },
    {
      "epoch": 0.01046517712312281,
      "eval_loss": 1.626073956489563,
      "eval_runtime": 208.6223,
      "eval_samples_per_second": 9.644,
      "eval_steps_per_second": 4.822,
      "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": 1.581910006431744e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}