{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11379800853485064,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005689900426742532,
      "eval_loss": 1.4702181816101074,
      "eval_runtime": 97.6278,
      "eval_samples_per_second": 7.58,
      "eval_steps_per_second": 3.79,
      "step": 1
    },
    {
      "epoch": 0.002844950213371266,
      "grad_norm": 0.15776292979717255,
      "learning_rate": 5e-05,
      "loss": 1.5423,
      "step": 5
    },
    {
      "epoch": 0.005689900426742532,
      "grad_norm": 0.3180772662162781,
      "learning_rate": 0.0001,
      "loss": 1.5495,
      "step": 10
    },
    {
      "epoch": 0.008534850640113799,
      "grad_norm": 0.2475329339504242,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.4748,
      "step": 15
    },
    {
      "epoch": 0.011379800853485065,
      "grad_norm": 0.23491647839546204,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.4243,
      "step": 20
    },
    {
      "epoch": 0.01422475106685633,
      "grad_norm": 0.156405970454216,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.349,
      "step": 25
    },
    {
      "epoch": 0.017069701280227598,
      "grad_norm": 0.1800297200679779,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.334,
      "step": 30
    },
    {
      "epoch": 0.01991465149359886,
      "grad_norm": 0.1841624230146408,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.3211,
      "step": 35
    },
    {
      "epoch": 0.02275960170697013,
      "grad_norm": 0.18861369788646698,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.3624,
      "step": 40
    },
    {
      "epoch": 0.025604551920341393,
      "grad_norm": 0.20811361074447632,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.2135,
      "step": 45
    },
    {
      "epoch": 0.02844950213371266,
      "grad_norm": 0.49080491065979004,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.0109,
      "step": 50
    },
    {
      "epoch": 0.02844950213371266,
      "eval_loss": 1.2867763042449951,
      "eval_runtime": 98.9605,
      "eval_samples_per_second": 7.478,
      "eval_steps_per_second": 3.739,
      "step": 50
    },
    {
      "epoch": 0.031294452347083924,
      "grad_norm": 0.28847643733024597,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.3137,
      "step": 55
    },
    {
      "epoch": 0.034139402560455195,
      "grad_norm": 0.1672595888376236,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.2642,
      "step": 60
    },
    {
      "epoch": 0.03698435277382646,
      "grad_norm": 0.20153048634529114,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.3451,
      "step": 65
    },
    {
      "epoch": 0.03982930298719772,
      "grad_norm": 0.18182030320167542,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.2577,
      "step": 70
    },
    {
      "epoch": 0.04267425320056899,
      "grad_norm": 0.18567194044589996,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.3163,
      "step": 75
    },
    {
      "epoch": 0.04551920341394026,
      "grad_norm": 0.19859260320663452,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.2875,
      "step": 80
    },
    {
      "epoch": 0.04836415362731152,
      "grad_norm": 0.19528040289878845,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.2905,
      "step": 85
    },
    {
      "epoch": 0.051209103840682786,
      "grad_norm": 0.2310878038406372,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.3571,
      "step": 90
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 0.27197933197021484,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.1707,
      "step": 95
    },
    {
      "epoch": 0.05689900426742532,
      "grad_norm": 0.5292563438415527,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9571,
      "step": 100
    },
    {
      "epoch": 0.05689900426742532,
      "eval_loss": 1.2389965057373047,
      "eval_runtime": 98.9658,
      "eval_samples_per_second": 7.477,
      "eval_steps_per_second": 3.739,
      "step": 100
    },
    {
      "epoch": 0.059743954480796585,
      "grad_norm": 0.25443074107170105,
      "learning_rate": 5e-05,
      "loss": 1.2893,
      "step": 105
    },
    {
      "epoch": 0.06258890469416785,
      "grad_norm": 0.2228810042142868,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.2617,
      "step": 110
    },
    {
      "epoch": 0.06543385490753911,
      "grad_norm": 0.27687934041023254,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.2612,
      "step": 115
    },
    {
      "epoch": 0.06827880512091039,
      "grad_norm": 0.21604830026626587,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.3271,
      "step": 120
    },
    {
      "epoch": 0.07112375533428165,
      "grad_norm": 0.22077901661396027,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.2858,
      "step": 125
    },
    {
      "epoch": 0.07396870554765292,
      "grad_norm": 0.20174729824066162,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.2405,
      "step": 130
    },
    {
      "epoch": 0.07681365576102418,
      "grad_norm": 0.22198493778705597,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.2382,
      "step": 135
    },
    {
      "epoch": 0.07965860597439545,
      "grad_norm": 0.2763294577598572,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.3044,
      "step": 140
    },
    {
      "epoch": 0.08250355618776671,
      "grad_norm": 0.22474978864192963,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.1803,
      "step": 145
    },
    {
      "epoch": 0.08534850640113797,
      "grad_norm": 0.5697594881057739,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.9433,
      "step": 150
    },
    {
      "epoch": 0.08534850640113797,
      "eval_loss": 1.222001314163208,
      "eval_runtime": 98.9441,
      "eval_samples_per_second": 7.479,
      "eval_steps_per_second": 3.739,
      "step": 150
    },
    {
      "epoch": 0.08819345661450925,
      "grad_norm": 0.22383780777454376,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.2384,
      "step": 155
    },
    {
      "epoch": 0.09103840682788052,
      "grad_norm": 0.23186904191970825,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.2749,
      "step": 160
    },
    {
      "epoch": 0.09388335704125178,
      "grad_norm": 0.2378578633069992,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.3229,
      "step": 165
    },
    {
      "epoch": 0.09672830725462304,
      "grad_norm": 0.2523314356803894,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2946,
      "step": 170
    },
    {
      "epoch": 0.09957325746799431,
      "grad_norm": 0.22312402725219727,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.2379,
      "step": 175
    },
    {
      "epoch": 0.10241820768136557,
      "grad_norm": 0.2241775393486023,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.2604,
      "step": 180
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.2440503090620041,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.2162,
      "step": 185
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 0.25313878059387207,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.2753,
      "step": 190
    },
    {
      "epoch": 0.11095305832147938,
      "grad_norm": 0.25487780570983887,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.0624,
      "step": 195
    },
    {
      "epoch": 0.11379800853485064,
      "grad_norm": 0.5397162437438965,
      "learning_rate": 0.0,
      "loss": 0.9448,
      "step": 200
    },
    {
      "epoch": 0.11379800853485064,
      "eval_loss": 1.2195565700531006,
      "eval_runtime": 98.8875,
      "eval_samples_per_second": 7.483,
      "eval_steps_per_second": 3.742,
      "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": 1.1865438228263731e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}