{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.996996996996997,
  "eval_steps": 500,
  "global_step": 166,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006006006006006006,
      "grad_norm": 4.622050762176514,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 2.2096,
      "step": 1
    },
    {
      "epoch": 0.03003003003003003,
      "grad_norm": 4.466672420501709,
      "learning_rate": 5.882352941176471e-05,
      "loss": 2.1887,
      "step": 5
    },
    {
      "epoch": 0.06006006006006006,
      "grad_norm": 2.914835214614868,
      "learning_rate": 0.00011764705882352942,
      "loss": 2.089,
      "step": 10
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 2.6984052658081055,
      "learning_rate": 0.00017647058823529413,
      "loss": 1.9548,
      "step": 15
    },
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 2.9828903675079346,
      "learning_rate": 0.00019980001615408228,
      "loss": 1.8137,
      "step": 20
    },
    {
      "epoch": 0.15015015015015015,
      "grad_norm": 1.9843279123306274,
      "learning_rate": 0.00019858078810097002,
      "loss": 1.6709,
      "step": 25
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 1.2187334299087524,
      "learning_rate": 0.00019626695552163578,
      "loss": 1.5917,
      "step": 30
    },
    {
      "epoch": 0.21021021021021022,
      "grad_norm": 1.0200163125991821,
      "learning_rate": 0.00019288421035528028,
      "loss": 1.585,
      "step": 35
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 1.0672650337219238,
      "learning_rate": 0.00018847011335021449,
      "loss": 1.5534,
      "step": 40
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 1.100464940071106,
      "learning_rate": 0.0001830736770032341,
      "loss": 1.5358,
      "step": 45
    },
    {
      "epoch": 0.3003003003003003,
      "grad_norm": 0.978142499923706,
      "learning_rate": 0.000176754821343025,
      "loss": 1.526,
      "step": 50
    },
    {
      "epoch": 0.3303303303303303,
      "grad_norm": 1.1280028820037842,
      "learning_rate": 0.00016958370860037717,
      "loss": 1.519,
      "step": 55
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.9044827222824097,
      "learning_rate": 0.00016163996415278424,
      "loss": 1.5143,
      "step": 60
    },
    {
      "epoch": 0.39039039039039036,
      "grad_norm": 0.949729323387146,
      "learning_rate": 0.00015301179239376938,
      "loss": 1.5115,
      "step": 65
    },
    {
      "epoch": 0.42042042042042044,
      "grad_norm": 0.9165012836456299,
      "learning_rate": 0.00014379499734399798,
      "loss": 1.5074,
      "step": 70
    },
    {
      "epoch": 0.45045045045045046,
      "grad_norm": 0.8735723495483398,
      "learning_rate": 0.0001340919188789477,
      "loss": 1.496,
      "step": 75
    },
    {
      "epoch": 0.4804804804804805,
      "grad_norm": 0.8276928663253784,
      "learning_rate": 0.00012401029638486953,
      "loss": 1.4897,
      "step": 80
    },
    {
      "epoch": 0.5105105105105106,
      "grad_norm": 0.8228772282600403,
      "learning_rate": 0.0001136620724605827,
      "loss": 1.4963,
      "step": 85
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.8163589835166931,
      "learning_rate": 0.0001031621499483559,
      "loss": 1.4858,
      "step": 90
    },
    {
      "epoch": 0.5705705705705706,
      "grad_norm": 0.9330477118492126,
      "learning_rate": 9.26271160953421e-05,
      "loss": 1.4865,
      "step": 95
    },
    {
      "epoch": 0.6006006006006006,
      "grad_norm": 0.8192353248596191,
      "learning_rate": 8.217394801200631e-05,
      "loss": 1.476,
      "step": 100
    },
    {
      "epoch": 0.6306306306306306,
      "grad_norm": 0.8679515719413757,
      "learning_rate": 7.191871380165538e-05,
      "loss": 1.4751,
      "step": 105
    },
    {
      "epoch": 0.6606606606606606,
      "grad_norm": 0.9080681800842285,
      "learning_rate": 6.197528378324665e-05,
      "loss": 1.4706,
      "step": 110
    },
    {
      "epoch": 0.6906906906906907,
      "grad_norm": 0.8363797664642334,
      "learning_rate": 5.2454066117578815e-05,
      "loss": 1.4791,
      "step": 115
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.865535318851471,
      "learning_rate": 4.346078087600412e-05,
      "loss": 1.475,
      "step": 120
    },
    {
      "epoch": 0.7507507507507507,
      "grad_norm": 0.8175177574157715,
      "learning_rate": 3.509528616394716e-05,
      "loss": 1.4816,
      "step": 125
    },
    {
      "epoch": 0.7807807807807807,
      "grad_norm": 0.8171746134757996,
      "learning_rate": 2.7450469333520855e-05,
      "loss": 1.4713,
      "step": 130
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 0.8764714002609253,
      "learning_rate": 2.06112155968028e-05,
      "loss": 1.4671,
      "step": 135
    },
    {
      "epoch": 0.8408408408408409,
      "grad_norm": 0.856728732585907,
      "learning_rate": 1.4653465491908003e-05,
      "loss": 1.4823,
      "step": 140
    },
    {
      "epoch": 0.8708708708708709,
      "grad_norm": 0.8493318557739258,
      "learning_rate": 9.643371667405698e-06,
      "loss": 1.469,
      "step": 145
    },
    {
      "epoch": 0.9009009009009009,
      "grad_norm": 0.8912323117256165,
      "learning_rate": 5.636564347832907e-06,
      "loss": 1.4737,
      "step": 150
    },
    {
      "epoch": 0.9309309309309309,
      "grad_norm": 0.9049487113952637,
      "learning_rate": 2.677533636303964e-06,
      "loss": 1.4727,
      "step": 155
    },
    {
      "epoch": 0.960960960960961,
      "grad_norm": 0.8411799669265747,
      "learning_rate": 7.991355128984079e-07,
      "loss": 1.4699,
      "step": 160
    },
    {
      "epoch": 0.990990990990991,
      "grad_norm": 0.885953426361084,
      "learning_rate": 2.222701403818972e-08,
      "loss": 1.4745,
      "step": 165
    },
    {
      "epoch": 0.996996996996997,
      "eval_loss": 2.1457931995391846,
      "eval_runtime": 0.6019,
      "eval_samples_per_second": 39.873,
      "eval_steps_per_second": 1.661,
      "step": 166
    },
    {
      "epoch": 0.996996996996997,
      "step": 166,
      "total_flos": 6.968531416388731e+17,
      "train_loss": 1.56508505703455,
      "train_runtime": 590.2519,
      "train_samples_per_second": 54.006,
      "train_steps_per_second": 0.281
    }
  ],
  "logging_steps": 5,
  "max_steps": 166,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.968531416388731e+17,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}