{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 60.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.099515914916992,
      "learning_rate": 0.0,
      "loss": 2.6549,
      "step": 1
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.1028008460998535,
      "learning_rate": 4e-05,
      "loss": 2.6566,
      "step": 2
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.096004009246826,
      "learning_rate": 8e-05,
      "loss": 2.6172,
      "step": 3
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.2220966815948486,
      "learning_rate": 0.00012,
      "loss": 2.4567,
      "step": 4
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.1684439182281494,
      "learning_rate": 0.00016,
      "loss": 2.0182,
      "step": 5
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.1147849559783936,
      "learning_rate": 0.0002,
      "loss": 1.4709,
      "step": 6
    },
    {
      "epoch": 7.0,
      "grad_norm": 5.454170227050781,
      "learning_rate": 0.00019636363636363636,
      "loss": 1.0252,
      "step": 7
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.096377372741699,
      "learning_rate": 0.00019272727272727274,
      "loss": 0.7436,
      "step": 8
    },
    {
      "epoch": 9.0,
      "grad_norm": 1.4990514516830444,
      "learning_rate": 0.0001890909090909091,
      "loss": 0.4376,
      "step": 9
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.6785975098609924,
      "learning_rate": 0.00018545454545454545,
      "loss": 0.3168,
      "step": 10
    },
    {
      "epoch": 11.0,
      "grad_norm": 0.8837186098098755,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.2594,
      "step": 11
    },
    {
      "epoch": 12.0,
      "grad_norm": 0.6441168189048767,
      "learning_rate": 0.0001781818181818182,
      "loss": 0.2084,
      "step": 12
    },
    {
      "epoch": 13.0,
      "grad_norm": 0.7236498594284058,
      "learning_rate": 0.00017454545454545454,
      "loss": 0.1832,
      "step": 13
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.7865864038467407,
      "learning_rate": 0.0001709090909090909,
      "loss": 0.1614,
      "step": 14
    },
    {
      "epoch": 15.0,
      "grad_norm": 0.8386063575744629,
      "learning_rate": 0.00016727272727272728,
      "loss": 0.145,
      "step": 15
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.9354585409164429,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.1331,
      "step": 16
    },
    {
      "epoch": 17.0,
      "grad_norm": 1.0136165618896484,
      "learning_rate": 0.00016,
      "loss": 0.119,
      "step": 17
    },
    {
      "epoch": 18.0,
      "grad_norm": 1.152154564857483,
      "learning_rate": 0.00015636363636363637,
      "loss": 0.1078,
      "step": 18
    },
    {
      "epoch": 19.0,
      "grad_norm": 1.3258788585662842,
      "learning_rate": 0.00015272727272727275,
      "loss": 0.0945,
      "step": 19
    },
    {
      "epoch": 20.0,
      "grad_norm": 1.4479986429214478,
      "learning_rate": 0.0001490909090909091,
      "loss": 0.0782,
      "step": 20
    },
    {
      "epoch": 21.0,
      "grad_norm": 1.5057014226913452,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.0627,
      "step": 21
    },
    {
      "epoch": 22.0,
      "grad_norm": 1.353816270828247,
      "learning_rate": 0.00014181818181818184,
      "loss": 0.0479,
      "step": 22
    },
    {
      "epoch": 23.0,
      "grad_norm": 0.9007766842842102,
      "learning_rate": 0.0001381818181818182,
      "loss": 0.037,
      "step": 23
    },
    {
      "epoch": 24.0,
      "grad_norm": 0.44463616609573364,
      "learning_rate": 0.00013454545454545455,
      "loss": 0.0317,
      "step": 24
    },
    {
      "epoch": 25.0,
      "grad_norm": 0.15833492577075958,
      "learning_rate": 0.00013090909090909093,
      "loss": 0.0279,
      "step": 25
    },
    {
      "epoch": 26.0,
      "grad_norm": 0.11187602579593658,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.0279,
      "step": 26
    },
    {
      "epoch": 27.0,
      "grad_norm": 0.07458829134702682,
      "learning_rate": 0.00012363636363636364,
      "loss": 0.0274,
      "step": 27
    },
    {
      "epoch": 28.0,
      "grad_norm": 0.05743066221475601,
      "learning_rate": 0.00012,
      "loss": 0.0271,
      "step": 28
    },
    {
      "epoch": 29.0,
      "grad_norm": 0.08287172019481659,
      "learning_rate": 0.00011636363636363636,
      "loss": 0.0273,
      "step": 29
    },
    {
      "epoch": 30.0,
      "grad_norm": 0.06937997788190842,
      "learning_rate": 0.00011272727272727272,
      "loss": 0.027,
      "step": 30
    },
    {
      "epoch": 31.0,
      "grad_norm": 0.04856820032000542,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.027,
      "step": 31
    },
    {
      "epoch": 32.0,
      "grad_norm": 0.07065649330615997,
      "learning_rate": 0.00010545454545454545,
      "loss": 0.027,
      "step": 32
    },
    {
      "epoch": 33.0,
      "grad_norm": 0.0560951754450798,
      "learning_rate": 0.00010181818181818181,
      "loss": 0.0268,
      "step": 33
    },
    {
      "epoch": 34.0,
      "grad_norm": 0.06166462227702141,
      "learning_rate": 9.818181818181818e-05,
      "loss": 0.0268,
      "step": 34
    },
    {
      "epoch": 35.0,
      "grad_norm": 0.06152236461639404,
      "learning_rate": 9.454545454545455e-05,
      "loss": 0.0269,
      "step": 35
    },
    {
      "epoch": 36.0,
      "grad_norm": 0.045099712908267975,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.0268,
      "step": 36
    },
    {
      "epoch": 37.0,
      "grad_norm": 0.01705729216337204,
      "learning_rate": 8.727272727272727e-05,
      "loss": 0.0267,
      "step": 37
    },
    {
      "epoch": 38.0,
      "grad_norm": 0.05170425772666931,
      "learning_rate": 8.363636363636364e-05,
      "loss": 0.0266,
      "step": 38
    },
    {
      "epoch": 39.0,
      "grad_norm": 0.06034626066684723,
      "learning_rate": 8e-05,
      "loss": 0.0269,
      "step": 39
    },
    {
      "epoch": 40.0,
      "grad_norm": 0.03125019744038582,
      "learning_rate": 7.636363636363637e-05,
      "loss": 0.0268,
      "step": 40
    },
    {
      "epoch": 41.0,
      "grad_norm": 0.03972804546356201,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.0266,
      "step": 41
    },
    {
      "epoch": 42.0,
      "grad_norm": 0.05231940746307373,
      "learning_rate": 6.90909090909091e-05,
      "loss": 0.0267,
      "step": 42
    },
    {
      "epoch": 43.0,
      "grad_norm": 0.03405136987566948,
      "learning_rate": 6.545454545454546e-05,
      "loss": 0.0265,
      "step": 43
    },
    {
      "epoch": 44.0,
      "grad_norm": 0.010633698664605618,
      "learning_rate": 6.181818181818182e-05,
      "loss": 0.0265,
      "step": 44
    },
    {
      "epoch": 45.0,
      "grad_norm": 0.03109440766274929,
      "learning_rate": 5.818181818181818e-05,
      "loss": 0.0267,
      "step": 45
    },
    {
      "epoch": 46.0,
      "grad_norm": 0.027693096548318863,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.0267,
      "step": 46
    },
    {
      "epoch": 47.0,
      "grad_norm": 0.03655220940709114,
      "learning_rate": 5.090909090909091e-05,
      "loss": 0.0266,
      "step": 47
    },
    {
      "epoch": 48.0,
      "grad_norm": 0.022899532690644264,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 0.0268,
      "step": 48
    },
    {
      "epoch": 49.0,
      "grad_norm": 0.01907823234796524,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 0.0265,
      "step": 49
    },
    {
      "epoch": 50.0,
      "grad_norm": 0.03373124822974205,
      "learning_rate": 4e-05,
      "loss": 0.0263,
      "step": 50
    },
    {
      "epoch": 51.0,
      "grad_norm": 0.03454992547631264,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.0266,
      "step": 51
    },
    {
      "epoch": 52.0,
      "grad_norm": 0.019019270315766335,
      "learning_rate": 3.272727272727273e-05,
      "loss": 0.0267,
      "step": 52
    },
    {
      "epoch": 53.0,
      "grad_norm": 0.0051805428229272366,
      "learning_rate": 2.909090909090909e-05,
      "loss": 0.0266,
      "step": 53
    },
    {
      "epoch": 54.0,
      "grad_norm": 0.005404070485383272,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 0.0266,
      "step": 54
    },
    {
      "epoch": 55.0,
      "grad_norm": 0.012555314227938652,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 0.0264,
      "step": 55
    },
    {
      "epoch": 56.0,
      "grad_norm": 0.02643151953816414,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.0266,
      "step": 56
    },
    {
      "epoch": 57.0,
      "grad_norm": 0.015639500692486763,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 0.0269,
      "step": 57
    },
    {
      "epoch": 58.0,
      "grad_norm": 0.032283101230859756,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 0.0264,
      "step": 58
    },
    {
      "epoch": 59.0,
      "grad_norm": 0.016383344307541847,
      "learning_rate": 7.272727272727272e-06,
      "loss": 0.0266,
      "step": 59
    },
    {
      "epoch": 60.0,
      "grad_norm": 0.005381885915994644,
      "learning_rate": 3.636363636363636e-06,
      "loss": 0.0267,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 60,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 886560737599488.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}