{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008001760387285202,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.000880193642601e-05,
      "eval_loss": 2.4036967754364014,
      "eval_runtime": 372.1489,
      "eval_samples_per_second": 28.279,
      "eval_steps_per_second": 14.14,
      "step": 1
    },
    {
      "epoch": 0.00020004400968213007,
      "grad_norm": 0.3941716253757477,
      "learning_rate": 5e-05,
      "loss": 2.1884,
      "step": 5
    },
    {
      "epoch": 0.00040008801936426014,
      "grad_norm": 0.3325437307357788,
      "learning_rate": 0.0001,
      "loss": 2.2752,
      "step": 10
    },
    {
      "epoch": 0.0006001320290463903,
      "grad_norm": 0.41570574045181274,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.2577,
      "step": 15
    },
    {
      "epoch": 0.0008001760387285203,
      "grad_norm": 0.4321326017379761,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.0802,
      "step": 20
    },
    {
      "epoch": 0.0010002200484106503,
      "grad_norm": 0.4277919828891754,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.1825,
      "step": 25
    },
    {
      "epoch": 0.0012002640580927805,
      "grad_norm": 0.483686238527298,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.0701,
      "step": 30
    },
    {
      "epoch": 0.0014003080677749105,
      "grad_norm": 0.5232543349266052,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.1452,
      "step": 35
    },
    {
      "epoch": 0.0016003520774570405,
      "grad_norm": 0.5410364866256714,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.1417,
      "step": 40
    },
    {
      "epoch": 0.0018003960871391706,
      "grad_norm": 1.1716076135635376,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.3531,
      "step": 45
    },
    {
      "epoch": 0.0020004400968213006,
      "grad_norm": 1.5886939764022827,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.6566,
      "step": 50
    },
    {
      "epoch": 0.0020004400968213006,
      "eval_loss": 2.205503225326538,
      "eval_runtime": 372.6133,
      "eval_samples_per_second": 28.244,
      "eval_steps_per_second": 14.122,
      "step": 50
    },
    {
      "epoch": 0.0022004841065034306,
      "grad_norm": 0.3893168270587921,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.1022,
      "step": 55
    },
    {
      "epoch": 0.002400528116185561,
      "grad_norm": 0.43030819296836853,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.2793,
      "step": 60
    },
    {
      "epoch": 0.002600572125867691,
      "grad_norm": 0.4663585424423218,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.1999,
      "step": 65
    },
    {
      "epoch": 0.002800616135549821,
      "grad_norm": 0.48781827092170715,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.1089,
      "step": 70
    },
    {
      "epoch": 0.003000660145231951,
      "grad_norm": 0.4673335552215576,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.0021,
      "step": 75
    },
    {
      "epoch": 0.003200704154914081,
      "grad_norm": 0.4960269331932068,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.0213,
      "step": 80
    },
    {
      "epoch": 0.003400748164596211,
      "grad_norm": 0.5341992974281311,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.0587,
      "step": 85
    },
    {
      "epoch": 0.003600792174278341,
      "grad_norm": 0.5136911273002625,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0624,
      "step": 90
    },
    {
      "epoch": 0.003800836183960471,
      "grad_norm": 1.49290931224823,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.3095,
      "step": 95
    },
    {
      "epoch": 0.004000880193642601,
      "grad_norm": 1.463133454322815,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.6053,
      "step": 100
    },
    {
      "epoch": 0.004000880193642601,
      "eval_loss": 2.144451379776001,
      "eval_runtime": 372.8153,
      "eval_samples_per_second": 28.228,
      "eval_steps_per_second": 14.114,
      "step": 100
    },
    {
      "epoch": 0.004200924203324731,
      "grad_norm": 0.37830111384391785,
      "learning_rate": 5e-05,
      "loss": 2.0165,
      "step": 105
    },
    {
      "epoch": 0.004400968213006861,
      "grad_norm": 0.42449793219566345,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.0493,
      "step": 110
    },
    {
      "epoch": 0.004601012222688991,
      "grad_norm": 0.4341510832309723,
      "learning_rate": 4.17702704859633e-05,
      "loss": 2.1133,
      "step": 115
    },
    {
      "epoch": 0.004801056232371122,
      "grad_norm": 0.5186764001846313,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.0889,
      "step": 120
    },
    {
      "epoch": 0.005001100242053252,
      "grad_norm": 0.4976426064968109,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.9287,
      "step": 125
    },
    {
      "epoch": 0.005201144251735382,
      "grad_norm": 0.5073955059051514,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.9609,
      "step": 130
    },
    {
      "epoch": 0.005401188261417512,
      "grad_norm": 0.5879153609275818,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.0563,
      "step": 135
    },
    {
      "epoch": 0.005601232271099642,
      "grad_norm": 0.5693666338920593,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.0088,
      "step": 140
    },
    {
      "epoch": 0.005801276280781772,
      "grad_norm": 1.250598430633545,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.2689,
      "step": 145
    },
    {
      "epoch": 0.006001320290463902,
      "grad_norm": 2.0096569061279297,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.6503,
      "step": 150
    },
    {
      "epoch": 0.006001320290463902,
      "eval_loss": 2.1339821815490723,
      "eval_runtime": 373.1288,
      "eval_samples_per_second": 28.205,
      "eval_steps_per_second": 14.102,
      "step": 150
    },
    {
      "epoch": 0.006201364300146032,
      "grad_norm": 0.40820667147636414,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.0262,
      "step": 155
    },
    {
      "epoch": 0.006401408309828162,
      "grad_norm": 0.4335764944553375,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.1589,
      "step": 160
    },
    {
      "epoch": 0.006601452319510292,
      "grad_norm": 0.47537532448768616,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.088,
      "step": 165
    },
    {
      "epoch": 0.006801496329192422,
      "grad_norm": 0.48711931705474854,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.9989,
      "step": 170
    },
    {
      "epoch": 0.007001540338874552,
      "grad_norm": 0.5092854499816895,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.9105,
      "step": 175
    },
    {
      "epoch": 0.007201584348556682,
      "grad_norm": 0.5382518172264099,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.0732,
      "step": 180
    },
    {
      "epoch": 0.007401628358238812,
      "grad_norm": 0.5413632988929749,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.0295,
      "step": 185
    },
    {
      "epoch": 0.007601672367920942,
      "grad_norm": 0.574699878692627,
      "learning_rate": 6.819348298638839e-07,
      "loss": 2.0224,
      "step": 190
    },
    {
      "epoch": 0.007801716377603072,
      "grad_norm": 0.9957907795906067,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.2395,
      "step": 195
    },
    {
      "epoch": 0.008001760387285202,
      "grad_norm": 1.8401072025299072,
      "learning_rate": 0.0,
      "loss": 2.6691,
      "step": 200
    },
    {
      "epoch": 0.008001760387285202,
      "eval_loss": 2.1284902095794678,
      "eval_runtime": 372.8479,
      "eval_samples_per_second": 28.226,
      "eval_steps_per_second": 14.113,
      "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": 1.2988145253482496e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}