{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06501950585175553,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006501950585175553,
      "eval_loss": 2.716893434524536,
      "eval_runtime": 127.2628,
      "eval_samples_per_second": 20.359,
      "eval_steps_per_second": 2.546,
      "step": 1
    },
    {
      "epoch": 0.0019505851755526658,
      "grad_norm": 1.2305755615234375,
      "learning_rate": 3e-05,
      "loss": 2.6768,
      "step": 3
    },
    {
      "epoch": 0.0039011703511053317,
      "grad_norm": 1.1447694301605225,
      "learning_rate": 6e-05,
      "loss": 2.6829,
      "step": 6
    },
    {
      "epoch": 0.005851755526657998,
      "grad_norm": 1.6053861379623413,
      "learning_rate": 9e-05,
      "loss": 2.5318,
      "step": 9
    },
    {
      "epoch": 0.005851755526657998,
      "eval_loss": 2.5240445137023926,
      "eval_runtime": 128.2682,
      "eval_samples_per_second": 20.2,
      "eval_steps_per_second": 2.526,
      "step": 9
    },
    {
      "epoch": 0.007802340702210663,
      "grad_norm": 1.5919204950332642,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.5246,
      "step": 12
    },
    {
      "epoch": 0.00975292587776333,
      "grad_norm": 0.8021125197410583,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4804,
      "step": 15
    },
    {
      "epoch": 0.011703511053315995,
      "grad_norm": 0.49364081025123596,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.342,
      "step": 18
    },
    {
      "epoch": 0.011703511053315995,
      "eval_loss": 2.315553665161133,
      "eval_runtime": 128.3129,
      "eval_samples_per_second": 20.193,
      "eval_steps_per_second": 2.525,
      "step": 18
    },
    {
      "epoch": 0.013654096228868661,
      "grad_norm": 0.6552979946136475,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.2865,
      "step": 21
    },
    {
      "epoch": 0.015604681404421327,
      "grad_norm": 0.5036161541938782,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.2539,
      "step": 24
    },
    {
      "epoch": 0.017555266579973992,
      "grad_norm": 0.6181878447532654,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.1404,
      "step": 27
    },
    {
      "epoch": 0.017555266579973992,
      "eval_loss": 2.18123722076416,
      "eval_runtime": 128.2503,
      "eval_samples_per_second": 20.203,
      "eval_steps_per_second": 2.526,
      "step": 27
    },
    {
      "epoch": 0.01950585175552666,
      "grad_norm": 0.6002896428108215,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.1997,
      "step": 30
    },
    {
      "epoch": 0.021456436931079324,
      "grad_norm": 0.4967464506626129,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.142,
      "step": 33
    },
    {
      "epoch": 0.02340702210663199,
      "grad_norm": 0.6285478472709656,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.0268,
      "step": 36
    },
    {
      "epoch": 0.02340702210663199,
      "eval_loss": 2.051860809326172,
      "eval_runtime": 128.3402,
      "eval_samples_per_second": 20.189,
      "eval_steps_per_second": 2.525,
      "step": 36
    },
    {
      "epoch": 0.025357607282184655,
      "grad_norm": 0.5662192106246948,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.0315,
      "step": 39
    },
    {
      "epoch": 0.027308192457737322,
      "grad_norm": 0.5459537506103516,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.9887,
      "step": 42
    },
    {
      "epoch": 0.029258777633289986,
      "grad_norm": 0.6652224659919739,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.0131,
      "step": 45
    },
    {
      "epoch": 0.029258777633289986,
      "eval_loss": 1.9418777227401733,
      "eval_runtime": 128.204,
      "eval_samples_per_second": 20.21,
      "eval_steps_per_second": 2.527,
      "step": 45
    },
    {
      "epoch": 0.031209362808842653,
      "grad_norm": 0.5966594219207764,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.8722,
      "step": 48
    },
    {
      "epoch": 0.03315994798439532,
      "grad_norm": 0.6166629791259766,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.878,
      "step": 51
    },
    {
      "epoch": 0.035110533159947985,
      "grad_norm": 0.8119226694107056,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.8638,
      "step": 54
    },
    {
      "epoch": 0.035110533159947985,
      "eval_loss": 1.8589894771575928,
      "eval_runtime": 128.2878,
      "eval_samples_per_second": 20.197,
      "eval_steps_per_second": 2.526,
      "step": 54
    },
    {
      "epoch": 0.03706111833550065,
      "grad_norm": 0.8477824330329895,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.7807,
      "step": 57
    },
    {
      "epoch": 0.03901170351105332,
      "grad_norm": 0.7622452974319458,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.8423,
      "step": 60
    },
    {
      "epoch": 0.04096228868660598,
      "grad_norm": 0.8412714600563049,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.7728,
      "step": 63
    },
    {
      "epoch": 0.04096228868660598,
      "eval_loss": 1.8006987571716309,
      "eval_runtime": 128.2766,
      "eval_samples_per_second": 20.199,
      "eval_steps_per_second": 2.526,
      "step": 63
    },
    {
      "epoch": 0.04291287386215865,
      "grad_norm": 0.7138541340827942,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.8166,
      "step": 66
    },
    {
      "epoch": 0.044863459037711315,
      "grad_norm": 0.6844710111618042,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.7404,
      "step": 69
    },
    {
      "epoch": 0.04681404421326398,
      "grad_norm": 0.6851016879081726,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.7623,
      "step": 72
    },
    {
      "epoch": 0.04681404421326398,
      "eval_loss": 1.7613475322723389,
      "eval_runtime": 128.255,
      "eval_samples_per_second": 20.202,
      "eval_steps_per_second": 2.526,
      "step": 72
    },
    {
      "epoch": 0.04876462938881664,
      "grad_norm": 0.6973990797996521,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.7611,
      "step": 75
    },
    {
      "epoch": 0.05071521456436931,
      "grad_norm": 0.7886289954185486,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.7711,
      "step": 78
    },
    {
      "epoch": 0.05266579973992198,
      "grad_norm": 0.690682053565979,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.7513,
      "step": 81
    },
    {
      "epoch": 0.05266579973992198,
      "eval_loss": 1.7403463125228882,
      "eval_runtime": 128.2107,
      "eval_samples_per_second": 20.209,
      "eval_steps_per_second": 2.527,
      "step": 81
    },
    {
      "epoch": 0.054616384915474644,
      "grad_norm": 0.7332757115364075,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.7384,
      "step": 84
    },
    {
      "epoch": 0.056566970091027305,
      "grad_norm": 0.7919108867645264,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.7371,
      "step": 87
    },
    {
      "epoch": 0.05851755526657997,
      "grad_norm": 0.713351309299469,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.7632,
      "step": 90
    },
    {
      "epoch": 0.05851755526657997,
      "eval_loss": 1.7311739921569824,
      "eval_runtime": 128.3077,
      "eval_samples_per_second": 20.194,
      "eval_steps_per_second": 2.525,
      "step": 90
    },
    {
      "epoch": 0.06046814044213264,
      "grad_norm": 0.6719050407409668,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.6705,
      "step": 93
    },
    {
      "epoch": 0.06241872561768531,
      "grad_norm": 0.7176926136016846,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.6458,
      "step": 96
    },
    {
      "epoch": 0.06436931079323797,
      "grad_norm": 0.6143832206726074,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.6889,
      "step": 99
    },
    {
      "epoch": 0.06436931079323797,
      "eval_loss": 1.7293328046798706,
      "eval_runtime": 128.2744,
      "eval_samples_per_second": 20.199,
      "eval_steps_per_second": 2.526,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.774412598588211e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}