{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3040668947168377,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015203344735841885,
      "eval_loss": 1.6278578042984009,
      "eval_runtime": 18.3215,
      "eval_samples_per_second": 15.119,
      "eval_steps_per_second": 7.587,
      "step": 1
    },
    {
      "epoch": 0.007601672367920942,
      "grad_norm": 2.8419041633605957,
      "learning_rate": 5e-05,
      "loss": 6.2872,
      "step": 5
    },
    {
      "epoch": 0.015203344735841885,
      "grad_norm": 3.7919328212738037,
      "learning_rate": 0.0001,
      "loss": 6.6235,
      "step": 10
    },
    {
      "epoch": 0.02280501710376283,
      "grad_norm": 4.106075286865234,
      "learning_rate": 9.98292246503335e-05,
      "loss": 6.0087,
      "step": 15
    },
    {
      "epoch": 0.03040668947168377,
      "grad_norm": 4.366232872009277,
      "learning_rate": 9.931806517013612e-05,
      "loss": 5.5816,
      "step": 20
    },
    {
      "epoch": 0.03800836183960471,
      "grad_norm": 4.517504692077637,
      "learning_rate": 9.847001329696653e-05,
      "loss": 5.3499,
      "step": 25
    },
    {
      "epoch": 0.04561003420752566,
      "grad_norm": 4.5565056800842285,
      "learning_rate": 9.729086208503174e-05,
      "loss": 5.2733,
      "step": 30
    },
    {
      "epoch": 0.0532117065754466,
      "grad_norm": 5.580263137817383,
      "learning_rate": 9.578866633275288e-05,
      "loss": 5.524,
      "step": 35
    },
    {
      "epoch": 0.06081337894336754,
      "grad_norm": 5.095555305480957,
      "learning_rate": 9.397368756032445e-05,
      "loss": 5.3861,
      "step": 40
    },
    {
      "epoch": 0.06841505131128849,
      "grad_norm": 4.752811908721924,
      "learning_rate": 9.185832391312644e-05,
      "loss": 4.8127,
      "step": 45
    },
    {
      "epoch": 0.07601672367920942,
      "grad_norm": 4.146973609924316,
      "learning_rate": 8.945702546981969e-05,
      "loss": 4.823,
      "step": 50
    },
    {
      "epoch": 0.07601672367920942,
      "eval_loss": 1.2947298288345337,
      "eval_runtime": 18.6608,
      "eval_samples_per_second": 14.844,
      "eval_steps_per_second": 7.449,
      "step": 50
    },
    {
      "epoch": 0.08361839604713037,
      "grad_norm": 3.1643850803375244,
      "learning_rate": 8.678619553365659e-05,
      "loss": 5.1643,
      "step": 55
    },
    {
      "epoch": 0.09122006841505131,
      "grad_norm": 3.623185396194458,
      "learning_rate": 8.386407858128706e-05,
      "loss": 5.3021,
      "step": 60
    },
    {
      "epoch": 0.09882174078297225,
      "grad_norm": 3.887627363204956,
      "learning_rate": 8.07106356344834e-05,
      "loss": 5.0388,
      "step": 65
    },
    {
      "epoch": 0.1064234131508932,
      "grad_norm": 3.948063611984253,
      "learning_rate": 7.734740790612136e-05,
      "loss": 4.7955,
      "step": 70
    },
    {
      "epoch": 0.11402508551881414,
      "grad_norm": 4.431191921234131,
      "learning_rate": 7.379736965185368e-05,
      "loss": 4.9352,
      "step": 75
    },
    {
      "epoch": 0.12162675788673508,
      "grad_norm": 5.341444969177246,
      "learning_rate": 7.008477123264848e-05,
      "loss": 5.0125,
      "step": 80
    },
    {
      "epoch": 0.12922843025465602,
      "grad_norm": 6.127177715301514,
      "learning_rate": 6.623497346023418e-05,
      "loss": 5.4098,
      "step": 85
    },
    {
      "epoch": 0.13683010262257697,
      "grad_norm": 6.2046003341674805,
      "learning_rate": 6.227427435703997e-05,
      "loss": 5.6714,
      "step": 90
    },
    {
      "epoch": 0.14443177499049792,
      "grad_norm": 4.405932903289795,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 4.1382,
      "step": 95
    },
    {
      "epoch": 0.15203344735841884,
      "grad_norm": 5.398401260375977,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 4.5947,
      "step": 100
    },
    {
      "epoch": 0.15203344735841884,
      "eval_loss": 1.2560712099075317,
      "eval_runtime": 18.7243,
      "eval_samples_per_second": 14.794,
      "eval_steps_per_second": 7.423,
      "step": 100
    },
    {
      "epoch": 0.15963511972633979,
      "grad_norm": 3.5515384674072266,
      "learning_rate": 5e-05,
      "loss": 5.1294,
      "step": 105
    },
    {
      "epoch": 0.16723679209426073,
      "grad_norm": 4.03835916519165,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 4.9121,
      "step": 110
    },
    {
      "epoch": 0.17483846446218168,
      "grad_norm": 4.950424671173096,
      "learning_rate": 4.17702704859633e-05,
      "loss": 4.8445,
      "step": 115
    },
    {
      "epoch": 0.18244013683010263,
      "grad_norm": 4.728461742401123,
      "learning_rate": 3.772572564296005e-05,
      "loss": 4.9264,
      "step": 120
    },
    {
      "epoch": 0.19004180919802358,
      "grad_norm": 4.832426071166992,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 4.8889,
      "step": 125
    },
    {
      "epoch": 0.1976434815659445,
      "grad_norm": 4.8872246742248535,
      "learning_rate": 2.991522876735154e-05,
      "loss": 5.0373,
      "step": 130
    },
    {
      "epoch": 0.20524515393386544,
      "grad_norm": 6.422519683837891,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 4.7572,
      "step": 135
    },
    {
      "epoch": 0.2128468263017864,
      "grad_norm": 4.094095230102539,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 5.3434,
      "step": 140
    },
    {
      "epoch": 0.22044849866970734,
      "grad_norm": 4.752438068389893,
      "learning_rate": 1.928936436551661e-05,
      "loss": 4.3029,
      "step": 145
    },
    {
      "epoch": 0.22805017103762829,
      "grad_norm": 5.265185356140137,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 4.6294,
      "step": 150
    },
    {
      "epoch": 0.22805017103762829,
      "eval_loss": 1.2389527559280396,
      "eval_runtime": 18.6786,
      "eval_samples_per_second": 14.83,
      "eval_steps_per_second": 7.442,
      "step": 150
    },
    {
      "epoch": 0.23565184340554923,
      "grad_norm": 3.934525728225708,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 5.4618,
      "step": 155
    },
    {
      "epoch": 0.24325351577347015,
      "grad_norm": 4.324830532073975,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 5.2351,
      "step": 160
    },
    {
      "epoch": 0.2508551881413911,
      "grad_norm": 4.316155910491943,
      "learning_rate": 8.141676086873572e-06,
      "loss": 5.0412,
      "step": 165
    },
    {
      "epoch": 0.25845686050931205,
      "grad_norm": 4.710128307342529,
      "learning_rate": 6.026312439675552e-06,
      "loss": 4.7803,
      "step": 170
    },
    {
      "epoch": 0.26605853287723297,
      "grad_norm": 4.378386497497559,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 4.6198,
      "step": 175
    },
    {
      "epoch": 0.27366020524515394,
      "grad_norm": 5.698144912719727,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 4.9306,
      "step": 180
    },
    {
      "epoch": 0.28126187761307486,
      "grad_norm": 6.138612747192383,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 5.137,
      "step": 185
    },
    {
      "epoch": 0.28886354998099584,
      "grad_norm": 7.554653167724609,
      "learning_rate": 6.819348298638839e-07,
      "loss": 5.3823,
      "step": 190
    },
    {
      "epoch": 0.29646522234891676,
      "grad_norm": 4.520476341247559,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 4.8598,
      "step": 195
    },
    {
      "epoch": 0.3040668947168377,
      "grad_norm": 5.928419589996338,
      "learning_rate": 0.0,
      "loss": 4.24,
      "step": 200
    },
    {
      "epoch": 0.3040668947168377,
      "eval_loss": 1.2346287965774536,
      "eval_runtime": 18.7192,
      "eval_samples_per_second": 14.798,
      "eval_steps_per_second": 7.426,
      "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": 4.75347107708928e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}