{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06416168745238,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012832337490476,
      "eval_loss": 8.74209976196289,
      "eval_runtime": 358.1544,
      "eval_samples_per_second": 7.737,
      "eval_steps_per_second": 7.737,
      "step": 1
    },
    {
      "epoch": 0.006416168745238,
      "grad_norm": 13.014253616333008,
      "learning_rate": 9.903926402016153e-05,
      "loss": 7.8911,
      "step": 5
    },
    {
      "epoch": 0.012832337490476,
      "grad_norm": 6.818251609802246,
      "learning_rate": 9.330127018922194e-05,
      "loss": 4.3451,
      "step": 10
    },
    {
      "epoch": 0.019248506235714,
      "grad_norm": 3.329972505569458,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.4424,
      "step": 15
    },
    {
      "epoch": 0.025664674980952,
      "grad_norm": 2.9790332317352295,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8727,
      "step": 20
    },
    {
      "epoch": 0.03208084372619,
      "grad_norm": 3.4033408164978027,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.5326,
      "step": 25
    },
    {
      "epoch": 0.03208084372619,
      "eval_loss": 1.582451343536377,
      "eval_runtime": 349.2215,
      "eval_samples_per_second": 7.935,
      "eval_steps_per_second": 7.935,
      "step": 25
    },
    {
      "epoch": 0.038497012471428,
      "grad_norm": 3.7447290420532227,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.4539,
      "step": 30
    },
    {
      "epoch": 0.044913181216666,
      "grad_norm": 3.3202221393585205,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.4218,
      "step": 35
    },
    {
      "epoch": 0.051329349961904,
      "grad_norm": 3.2296829223632812,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.4064,
      "step": 40
    },
    {
      "epoch": 0.057745518707142,
      "grad_norm": 2.998584270477295,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.405,
      "step": 45
    },
    {
      "epoch": 0.06416168745238,
      "grad_norm": 3.7719151973724365,
      "learning_rate": 0.0,
      "loss": 1.3559,
      "step": 50
    },
    {
      "epoch": 0.06416168745238,
      "eval_loss": 1.4145891666412354,
      "eval_runtime": 349.8696,
      "eval_samples_per_second": 7.92,
      "eval_steps_per_second": 7.92,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.93544513912832e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}