{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7366482504604052,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003683241252302026,
      "eval_loss": 5.6406402587890625,
      "eval_runtime": 9.0694,
      "eval_samples_per_second": 12.68,
      "eval_steps_per_second": 6.395,
      "step": 1
    },
    {
      "epoch": 0.01841620626151013,
      "grad_norm": 4.560856819152832,
      "learning_rate": 5e-05,
      "loss": 5.0809,
      "step": 5
    },
    {
      "epoch": 0.03683241252302026,
      "grad_norm": 5.448482036590576,
      "learning_rate": 0.0001,
      "loss": 4.9864,
      "step": 10
    },
    {
      "epoch": 0.055248618784530384,
      "grad_norm": 4.187519550323486,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.5351,
      "step": 15
    },
    {
      "epoch": 0.07366482504604052,
      "grad_norm": 3.5520455837249756,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.344,
      "step": 20
    },
    {
      "epoch": 0.09208103130755065,
      "grad_norm": 2.697782516479492,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.4744,
      "step": 25
    },
    {
      "epoch": 0.11049723756906077,
      "grad_norm": 3.3176934719085693,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.3054,
      "step": 30
    },
    {
      "epoch": 0.1289134438305709,
      "grad_norm": 3.820105791091919,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.3323,
      "step": 35
    },
    {
      "epoch": 0.14732965009208104,
      "grad_norm": 2.9278311729431152,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.0648,
      "step": 40
    },
    {
      "epoch": 0.16574585635359115,
      "grad_norm": 2.7499992847442627,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.3064,
      "step": 45
    },
    {
      "epoch": 0.1841620626151013,
      "grad_norm": 4.014856815338135,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.5323,
      "step": 50
    },
    {
      "epoch": 0.1841620626151013,
      "eval_loss": 3.4378182888031006,
      "eval_runtime": 9.2333,
      "eval_samples_per_second": 12.455,
      "eval_steps_per_second": 6.282,
      "step": 50
    },
    {
      "epoch": 0.20257826887661143,
      "grad_norm": 2.92960524559021,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.1583,
      "step": 55
    },
    {
      "epoch": 0.22099447513812154,
      "grad_norm": 3.0507895946502686,
      "learning_rate": 8.386407858128706e-05,
      "loss": 3.1401,
      "step": 60
    },
    {
      "epoch": 0.23941068139963168,
      "grad_norm": 3.3862218856811523,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.152,
      "step": 65
    },
    {
      "epoch": 0.2578268876611418,
      "grad_norm": 2.807326316833496,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.14,
      "step": 70
    },
    {
      "epoch": 0.27624309392265195,
      "grad_norm": 2.922556161880493,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.2062,
      "step": 75
    },
    {
      "epoch": 0.2946593001841621,
      "grad_norm": 2.8641202449798584,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.1225,
      "step": 80
    },
    {
      "epoch": 0.31307550644567217,
      "grad_norm": 2.468834161758423,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.1949,
      "step": 85
    },
    {
      "epoch": 0.3314917127071823,
      "grad_norm": 3.6921591758728027,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.3629,
      "step": 90
    },
    {
      "epoch": 0.34990791896869244,
      "grad_norm": 2.8918163776397705,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.2509,
      "step": 95
    },
    {
      "epoch": 0.3683241252302026,
      "grad_norm": 3.6392602920532227,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.5068,
      "step": 100
    },
    {
      "epoch": 0.3683241252302026,
      "eval_loss": 3.3434040546417236,
      "eval_runtime": 9.2445,
      "eval_samples_per_second": 12.44,
      "eval_steps_per_second": 6.274,
      "step": 100
    },
    {
      "epoch": 0.3867403314917127,
      "grad_norm": 3.290396213531494,
      "learning_rate": 5e-05,
      "loss": 3.1451,
      "step": 105
    },
    {
      "epoch": 0.40515653775322286,
      "grad_norm": 2.741856098175049,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.9364,
      "step": 110
    },
    {
      "epoch": 0.42357274401473294,
      "grad_norm": 3.248924732208252,
      "learning_rate": 4.17702704859633e-05,
      "loss": 3.2139,
      "step": 115
    },
    {
      "epoch": 0.4419889502762431,
      "grad_norm": 2.51607084274292,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.1467,
      "step": 120
    },
    {
      "epoch": 0.4604051565377532,
      "grad_norm": 2.6266937255859375,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 3.0902,
      "step": 125
    },
    {
      "epoch": 0.47882136279926335,
      "grad_norm": 2.418804883956909,
      "learning_rate": 2.991522876735154e-05,
      "loss": 3.0592,
      "step": 130
    },
    {
      "epoch": 0.4972375690607735,
      "grad_norm": 2.5460476875305176,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.0991,
      "step": 135
    },
    {
      "epoch": 0.5156537753222836,
      "grad_norm": 3.1187572479248047,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 3.2016,
      "step": 140
    },
    {
      "epoch": 0.5340699815837937,
      "grad_norm": 3.156820297241211,
      "learning_rate": 1.928936436551661e-05,
      "loss": 3.1849,
      "step": 145
    },
    {
      "epoch": 0.5524861878453039,
      "grad_norm": 3.3207755088806152,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.3894,
      "step": 150
    },
    {
      "epoch": 0.5524861878453039,
      "eval_loss": 3.305239200592041,
      "eval_runtime": 9.2382,
      "eval_samples_per_second": 12.448,
      "eval_steps_per_second": 6.278,
      "step": 150
    },
    {
      "epoch": 0.570902394106814,
      "grad_norm": 2.5012712478637695,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 3.1551,
      "step": 155
    },
    {
      "epoch": 0.5893186003683242,
      "grad_norm": 3.0041964054107666,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 3.0452,
      "step": 160
    },
    {
      "epoch": 0.6077348066298343,
      "grad_norm": 2.9641096591949463,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.1571,
      "step": 165
    },
    {
      "epoch": 0.6261510128913443,
      "grad_norm": 2.683532476425171,
      "learning_rate": 6.026312439675552e-06,
      "loss": 3.0513,
      "step": 170
    },
    {
      "epoch": 0.6445672191528545,
      "grad_norm": 2.901531934738159,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 3.1693,
      "step": 175
    },
    {
      "epoch": 0.6629834254143646,
      "grad_norm": 2.9755866527557373,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.0856,
      "step": 180
    },
    {
      "epoch": 0.6813996316758748,
      "grad_norm": 2.6626925468444824,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 3.1288,
      "step": 185
    },
    {
      "epoch": 0.6998158379373849,
      "grad_norm": 2.3551111221313477,
      "learning_rate": 6.819348298638839e-07,
      "loss": 3.0157,
      "step": 190
    },
    {
      "epoch": 0.7182320441988951,
      "grad_norm": 3.0756149291992188,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 3.2371,
      "step": 195
    },
    {
      "epoch": 0.7366482504604052,
      "grad_norm": 4.0646185874938965,
      "learning_rate": 0.0,
      "loss": 3.426,
      "step": 200
    },
    {
      "epoch": 0.7366482504604052,
      "eval_loss": 3.308279514312744,
      "eval_runtime": 9.2262,
      "eval_samples_per_second": 12.465,
      "eval_steps_per_second": 6.286,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 7.39825699258368e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}