{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.7199999999999998,
  "eval_steps": 500,
  "global_step": 48,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 4.588487741146127,
      "learning_rate": 0.0,
      "loss": 0.9552,
      "step": 1
    },
    {
      "epoch": 0.16,
      "grad_norm": 5.278651172218827,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.0373,
      "step": 2
    },
    {
      "epoch": 0.24,
      "grad_norm": 4.700417275531306,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.0133,
      "step": 3
    },
    {
      "epoch": 0.32,
      "grad_norm": 3.585647769729563,
      "learning_rate": 5e-06,
      "loss": 1.0446,
      "step": 4
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.418839191857467,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.861,
      "step": 5
    },
    {
      "epoch": 0.48,
      "grad_norm": 4.940696238019213,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.9019,
      "step": 6
    },
    {
      "epoch": 0.56,
      "grad_norm": 3.380420711362513,
      "learning_rate": 1e-05,
      "loss": 0.9194,
      "step": 7
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.0959103464052995,
      "learning_rate": 9.991540791356342e-06,
      "loss": 0.9513,
      "step": 8
    },
    {
      "epoch": 0.72,
      "grad_norm": 3.403254422563401,
      "learning_rate": 9.966191788709716e-06,
      "loss": 0.9037,
      "step": 9
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.7712079671523178,
      "learning_rate": 9.924038765061042e-06,
      "loss": 0.9189,
      "step": 10
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.9733187537050423,
      "learning_rate": 9.86522435289912e-06,
      "loss": 0.7993,
      "step": 11
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.2342106045506966,
      "learning_rate": 9.789947561577445e-06,
      "loss": 0.8955,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.2342106045506966,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.8155,
      "step": 13
    },
    {
      "epoch": 1.08,
      "grad_norm": 2.7617228928368696,
      "learning_rate": 9.591080534401371e-06,
      "loss": 0.837,
      "step": 14
    },
    {
      "epoch": 1.16,
      "grad_norm": 1.6858690209498897,
      "learning_rate": 9.468163201617063e-06,
      "loss": 0.7037,
      "step": 15
    },
    {
      "epoch": 1.24,
      "grad_norm": 1.4938576453902597,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.7349,
      "step": 16
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.585805875732363,
      "learning_rate": 9.177439057064684e-06,
      "loss": 0.751,
      "step": 17
    },
    {
      "epoch": 1.4,
      "grad_norm": 1.747488569612483,
      "learning_rate": 9.01061596377522e-06,
      "loss": 0.7524,
      "step": 18
    },
    {
      "epoch": 1.48,
      "grad_norm": 1.548946084936831,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.6874,
      "step": 19
    },
    {
      "epoch": 1.56,
      "grad_norm": 1.4061280751886749,
      "learning_rate": 8.636868207865244e-06,
      "loss": 0.7096,
      "step": 20
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 1.3033317777782518,
      "learning_rate": 8.43120818934367e-06,
      "loss": 0.6643,
      "step": 21
    },
    {
      "epoch": 1.72,
      "grad_norm": 1.5560223455632005,
      "learning_rate": 8.213938048432697e-06,
      "loss": 0.7414,
      "step": 22
    },
    {
      "epoch": 1.8,
      "grad_norm": 1.5948398210022794,
      "learning_rate": 7.985792958513932e-06,
      "loss": 0.7951,
      "step": 23
    },
    {
      "epoch": 1.88,
      "grad_norm": 1.522600719548368,
      "learning_rate": 7.747544890354031e-06,
      "loss": 0.7152,
      "step": 24
    },
    {
      "epoch": 1.96,
      "grad_norm": 1.5363608477190935,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.7072,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.38093780060039,
      "learning_rate": 7.243995901002312e-06,
      "loss": 0.7415,
      "step": 26
    },
    {
      "epoch": 2.08,
      "grad_norm": 1.202779248276888,
      "learning_rate": 6.980398830195785e-06,
      "loss": 0.6274,
      "step": 27
    },
    {
      "epoch": 2.16,
      "grad_norm": 1.2344129473013965,
      "learning_rate": 6.710100716628345e-06,
      "loss": 0.576,
      "step": 28
    },
    {
      "epoch": 2.24,
      "grad_norm": 1.187181720989279,
      "learning_rate": 6.434016163555452e-06,
      "loss": 0.6489,
      "step": 29
    },
    {
      "epoch": 2.32,
      "grad_norm": 1.3041016151831586,
      "learning_rate": 6.153079353712201e-06,
      "loss": 0.6642,
      "step": 30
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.2305212817046478,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.6459,
      "step": 31
    },
    {
      "epoch": 2.48,
      "grad_norm": 1.2718381519426567,
      "learning_rate": 5.5804645706261515e-06,
      "loss": 0.6272,
      "step": 32
    },
    {
      "epoch": 2.56,
      "grad_norm": 1.2028562170282764,
      "learning_rate": 5.290724144552379e-06,
      "loss": 0.6313,
      "step": 33
    },
    {
      "epoch": 2.64,
      "grad_norm": 1.308076555324806,
      "learning_rate": 5e-06,
      "loss": 0.5964,
      "step": 34
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 1.185274169744774,
      "learning_rate": 4.7092758554476215e-06,
      "loss": 0.6236,
      "step": 35
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.1496574013808962,
      "learning_rate": 4.4195354293738484e-06,
      "loss": 0.6016,
      "step": 36
    },
    {
      "epoch": 2.88,
      "grad_norm": 1.2543301145276173,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.6176,
      "step": 37
    },
    {
      "epoch": 2.96,
      "grad_norm": 1.2179432229704832,
      "learning_rate": 3.8469206462878e-06,
      "loss": 0.5984,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2179432229704832,
      "learning_rate": 3.5659838364445505e-06,
      "loss": 0.6634,
      "step": 39
    },
    {
      "epoch": 3.08,
      "grad_norm": 1.8452931147367213,
      "learning_rate": 3.289899283371657e-06,
      "loss": 0.5032,
      "step": 40
    },
    {
      "epoch": 3.16,
      "grad_norm": 1.198860684147975,
      "learning_rate": 3.019601169804216e-06,
      "loss": 0.5665,
      "step": 41
    },
    {
      "epoch": 3.24,
      "grad_norm": 1.1317870772663245,
      "learning_rate": 2.7560040989976894e-06,
      "loss": 0.5091,
      "step": 42
    },
    {
      "epoch": 3.32,
      "grad_norm": 1.1681601212288482,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.5782,
      "step": 43
    },
    {
      "epoch": 3.4,
      "grad_norm": 1.180114633886334,
      "learning_rate": 2.2524551096459703e-06,
      "loss": 0.5224,
      "step": 44
    },
    {
      "epoch": 3.48,
      "grad_norm": 1.112122581870263,
      "learning_rate": 2.0142070414860704e-06,
      "loss": 0.61,
      "step": 45
    },
    {
      "epoch": 3.56,
      "grad_norm": 1.1582389179134673,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.5418,
      "step": 46
    },
    {
      "epoch": 3.64,
      "grad_norm": 1.0852894725247233,
      "learning_rate": 1.5687918106563326e-06,
      "loss": 0.5716,
      "step": 47
    },
    {
      "epoch": 3.7199999999999998,
      "grad_norm": 1.1147340893020965,
      "learning_rate": 1.3631317921347564e-06,
      "loss": 0.4747,
      "step": 48
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 12,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5501311893504.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}