{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15417228753131623,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007708614376565812,
      "eval_loss": 1.93642258644104,
      "eval_runtime": 19.6115,
      "eval_samples_per_second": 27.892,
      "eval_steps_per_second": 13.971,
      "step": 1
    },
    {
      "epoch": 0.003854307188282906,
      "grad_norm": 0.3921183943748474,
      "learning_rate": 5e-05,
      "loss": 1.8552,
      "step": 5
    },
    {
      "epoch": 0.007708614376565812,
      "grad_norm": 0.3953486979007721,
      "learning_rate": 0.0001,
      "loss": 1.8702,
      "step": 10
    },
    {
      "epoch": 0.011562921564848718,
      "grad_norm": 0.4515380263328552,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.8064,
      "step": 15
    },
    {
      "epoch": 0.015417228753131625,
      "grad_norm": 0.4705100357532501,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.7484,
      "step": 20
    },
    {
      "epoch": 0.01927153594141453,
      "grad_norm": 0.39429208636283875,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.6814,
      "step": 25
    },
    {
      "epoch": 0.023125843129697437,
      "grad_norm": 0.4658222794532776,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7042,
      "step": 30
    },
    {
      "epoch": 0.02698015031798034,
      "grad_norm": 0.42470604181289673,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.8004,
      "step": 35
    },
    {
      "epoch": 0.03083445750626325,
      "grad_norm": 0.46693292260169983,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.7758,
      "step": 40
    },
    {
      "epoch": 0.034688764694546154,
      "grad_norm": 0.5165051221847534,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.7589,
      "step": 45
    },
    {
      "epoch": 0.03854307188282906,
      "grad_norm": 0.6815525889396667,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.7989,
      "step": 50
    },
    {
      "epoch": 0.03854307188282906,
      "eval_loss": 1.7452771663665771,
      "eval_runtime": 19.5862,
      "eval_samples_per_second": 27.928,
      "eval_steps_per_second": 13.989,
      "step": 50
    },
    {
      "epoch": 0.04239737907111197,
      "grad_norm": 0.4037501811981201,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.6684,
      "step": 55
    },
    {
      "epoch": 0.046251686259394874,
      "grad_norm": 0.3763955235481262,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.7082,
      "step": 60
    },
    {
      "epoch": 0.05010599344767778,
      "grad_norm": 0.395406574010849,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6552,
      "step": 65
    },
    {
      "epoch": 0.05396030063596068,
      "grad_norm": 0.388625830411911,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.6673,
      "step": 70
    },
    {
      "epoch": 0.057814607824243594,
      "grad_norm": 0.406642347574234,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.6961,
      "step": 75
    },
    {
      "epoch": 0.0616689150125265,
      "grad_norm": 0.43869659304618835,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.7054,
      "step": 80
    },
    {
      "epoch": 0.0655232222008094,
      "grad_norm": 0.43835821747779846,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.7415,
      "step": 85
    },
    {
      "epoch": 0.06937752938909231,
      "grad_norm": 0.48997819423675537,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.7053,
      "step": 90
    },
    {
      "epoch": 0.07323183657737521,
      "grad_norm": 0.5548950433731079,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.7036,
      "step": 95
    },
    {
      "epoch": 0.07708614376565812,
      "grad_norm": 0.7339133024215698,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.7519,
      "step": 100
    },
    {
      "epoch": 0.07708614376565812,
      "eval_loss": 1.6988989114761353,
      "eval_runtime": 19.596,
      "eval_samples_per_second": 27.914,
      "eval_steps_per_second": 13.982,
      "step": 100
    },
    {
      "epoch": 0.08094045095394103,
      "grad_norm": 0.3857652544975281,
      "learning_rate": 5e-05,
      "loss": 1.622,
      "step": 105
    },
    {
      "epoch": 0.08479475814222394,
      "grad_norm": 0.4023033380508423,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.6608,
      "step": 110
    },
    {
      "epoch": 0.08864906533050684,
      "grad_norm": 0.4008744955062866,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.6583,
      "step": 115
    },
    {
      "epoch": 0.09250337251878975,
      "grad_norm": 0.4787733256816864,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.6919,
      "step": 120
    },
    {
      "epoch": 0.09635767970707265,
      "grad_norm": 0.45529553294181824,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.6907,
      "step": 125
    },
    {
      "epoch": 0.10021198689535556,
      "grad_norm": 0.4510851502418518,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.6872,
      "step": 130
    },
    {
      "epoch": 0.10406629408363846,
      "grad_norm": 0.5126768946647644,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.7454,
      "step": 135
    },
    {
      "epoch": 0.10792060127192137,
      "grad_norm": 0.5258253216743469,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.6834,
      "step": 140
    },
    {
      "epoch": 0.11177490846020428,
      "grad_norm": 0.5813694000244141,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.7246,
      "step": 145
    },
    {
      "epoch": 0.11562921564848719,
      "grad_norm": 0.7048178911209106,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.6672,
      "step": 150
    },
    {
      "epoch": 0.11562921564848719,
      "eval_loss": 1.6832927465438843,
      "eval_runtime": 19.6112,
      "eval_samples_per_second": 27.892,
      "eval_steps_per_second": 13.972,
      "step": 150
    },
    {
      "epoch": 0.11948352283677009,
      "grad_norm": 0.3784642219543457,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.6921,
      "step": 155
    },
    {
      "epoch": 0.123337830025053,
      "grad_norm": 0.41113045811653137,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.6152,
      "step": 160
    },
    {
      "epoch": 0.12719213721333592,
      "grad_norm": 0.3924788534641266,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.6103,
      "step": 165
    },
    {
      "epoch": 0.1310464444016188,
      "grad_norm": 0.4522091746330261,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.6584,
      "step": 170
    },
    {
      "epoch": 0.13490075158990172,
      "grad_norm": 0.4569909870624542,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.6299,
      "step": 175
    },
    {
      "epoch": 0.13875505877818461,
      "grad_norm": 0.508297324180603,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.6383,
      "step": 180
    },
    {
      "epoch": 0.14260936596646753,
      "grad_norm": 0.514383852481842,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.6979,
      "step": 185
    },
    {
      "epoch": 0.14646367315475042,
      "grad_norm": 0.5534428954124451,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.7065,
      "step": 190
    },
    {
      "epoch": 0.15031798034303334,
      "grad_norm": 0.5994581580162048,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.7204,
      "step": 195
    },
    {
      "epoch": 0.15417228753131623,
      "grad_norm": 0.742976188659668,
      "learning_rate": 0.0,
      "loss": 1.7759,
      "step": 200
    },
    {
      "epoch": 0.15417228753131623,
      "eval_loss": 1.6809499263763428,
      "eval_runtime": 19.6009,
      "eval_samples_per_second": 27.907,
      "eval_steps_per_second": 13.979,
      "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": 1.29719303405568e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}