{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6745362563237775,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003372681281618887,
      "eval_loss": 2.7467381954193115,
      "eval_runtime": 6.59,
      "eval_samples_per_second": 18.968,
      "eval_steps_per_second": 9.56,
      "step": 1
    },
    {
      "epoch": 0.016863406408094434,
      "grad_norm": 0.8390719294548035,
      "learning_rate": 5e-05,
      "loss": 2.2411,
      "step": 5
    },
    {
      "epoch": 0.03372681281618887,
      "grad_norm": 1.8118478059768677,
      "learning_rate": 0.0001,
      "loss": 2.2443,
      "step": 10
    },
    {
      "epoch": 0.050590219224283306,
      "grad_norm": 1.3352593183517456,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.2468,
      "step": 15
    },
    {
      "epoch": 0.06745362563237774,
      "grad_norm": 1.8893016576766968,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.0888,
      "step": 20
    },
    {
      "epoch": 0.08431703204047218,
      "grad_norm": 1.4422814846038818,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.1951,
      "step": 25
    },
    {
      "epoch": 0.10118043844856661,
      "grad_norm": 1.4987432956695557,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.8629,
      "step": 30
    },
    {
      "epoch": 0.11804384485666104,
      "grad_norm": 1.5730533599853516,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.9293,
      "step": 35
    },
    {
      "epoch": 0.13490725126475547,
      "grad_norm": 2.024653434753418,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.8794,
      "step": 40
    },
    {
      "epoch": 0.15177065767284992,
      "grad_norm": 2.605868339538574,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.174,
      "step": 45
    },
    {
      "epoch": 0.16863406408094436,
      "grad_norm": 2.602346420288086,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.948,
      "step": 50
    },
    {
      "epoch": 0.16863406408094436,
      "eval_loss": 1.816723108291626,
      "eval_runtime": 6.6117,
      "eval_samples_per_second": 18.906,
      "eval_steps_per_second": 9.529,
      "step": 50
    },
    {
      "epoch": 0.18549747048903878,
      "grad_norm": 1.2885977029800415,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.6797,
      "step": 55
    },
    {
      "epoch": 0.20236087689713322,
      "grad_norm": 1.0659314393997192,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.6388,
      "step": 60
    },
    {
      "epoch": 0.21922428330522767,
      "grad_norm": 1.2482647895812988,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.7191,
      "step": 65
    },
    {
      "epoch": 0.23608768971332209,
      "grad_norm": 1.048137903213501,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.7558,
      "step": 70
    },
    {
      "epoch": 0.25295109612141653,
      "grad_norm": 1.2993953227996826,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.7659,
      "step": 75
    },
    {
      "epoch": 0.26981450252951095,
      "grad_norm": 1.7078555822372437,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.8161,
      "step": 80
    },
    {
      "epoch": 0.2866779089376054,
      "grad_norm": 1.5305366516113281,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.633,
      "step": 85
    },
    {
      "epoch": 0.30354131534569984,
      "grad_norm": 1.6731135845184326,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.6672,
      "step": 90
    },
    {
      "epoch": 0.32040472175379425,
      "grad_norm": 2.150664806365967,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.7481,
      "step": 95
    },
    {
      "epoch": 0.3372681281618887,
      "grad_norm": 2.901634693145752,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.9348,
      "step": 100
    },
    {
      "epoch": 0.3372681281618887,
      "eval_loss": 1.6634008884429932,
      "eval_runtime": 6.6225,
      "eval_samples_per_second": 18.875,
      "eval_steps_per_second": 9.513,
      "step": 100
    },
    {
      "epoch": 0.35413153456998314,
      "grad_norm": 1.0495014190673828,
      "learning_rate": 5e-05,
      "loss": 1.5314,
      "step": 105
    },
    {
      "epoch": 0.37099494097807756,
      "grad_norm": 1.1185582876205444,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.6625,
      "step": 110
    },
    {
      "epoch": 0.38785834738617203,
      "grad_norm": 1.3425679206848145,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.5669,
      "step": 115
    },
    {
      "epoch": 0.40472175379426645,
      "grad_norm": 1.3050974607467651,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.737,
      "step": 120
    },
    {
      "epoch": 0.42158516020236086,
      "grad_norm": 1.4126721620559692,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.7391,
      "step": 125
    },
    {
      "epoch": 0.43844856661045534,
      "grad_norm": 1.44622802734375,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.6446,
      "step": 130
    },
    {
      "epoch": 0.45531197301854975,
      "grad_norm": 1.229062795639038,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.5655,
      "step": 135
    },
    {
      "epoch": 0.47217537942664417,
      "grad_norm": 1.9458297491073608,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.6729,
      "step": 140
    },
    {
      "epoch": 0.48903878583473864,
      "grad_norm": 1.9462506771087646,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.6649,
      "step": 145
    },
    {
      "epoch": 0.5059021922428331,
      "grad_norm": 2.5057289600372314,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.8469,
      "step": 150
    },
    {
      "epoch": 0.5059021922428331,
      "eval_loss": 1.6358802318572998,
      "eval_runtime": 6.623,
      "eval_samples_per_second": 18.874,
      "eval_steps_per_second": 9.512,
      "step": 150
    },
    {
      "epoch": 0.5227655986509275,
      "grad_norm": 0.9636170864105225,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.6495,
      "step": 155
    },
    {
      "epoch": 0.5396290050590219,
      "grad_norm": 1.2069531679153442,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.6654,
      "step": 160
    },
    {
      "epoch": 0.5564924114671164,
      "grad_norm": 1.2224812507629395,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.6404,
      "step": 165
    },
    {
      "epoch": 0.5733558178752108,
      "grad_norm": 1.1555508375167847,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.6415,
      "step": 170
    },
    {
      "epoch": 0.5902192242833052,
      "grad_norm": 1.5007044076919556,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.7765,
      "step": 175
    },
    {
      "epoch": 0.6070826306913997,
      "grad_norm": 1.7452291250228882,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.777,
      "step": 180
    },
    {
      "epoch": 0.6239460370994941,
      "grad_norm": 1.972568154335022,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.7634,
      "step": 185
    },
    {
      "epoch": 0.6408094435075885,
      "grad_norm": 2.2312941551208496,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.7681,
      "step": 190
    },
    {
      "epoch": 0.657672849915683,
      "grad_norm": 1.7280540466308594,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.8057,
      "step": 195
    },
    {
      "epoch": 0.6745362563237775,
      "grad_norm": 2.960195302963257,
      "learning_rate": 0.0,
      "loss": 1.8119,
      "step": 200
    },
    {
      "epoch": 0.6745362563237775,
      "eval_loss": 1.6357028484344482,
      "eval_runtime": 6.6191,
      "eval_samples_per_second": 18.885,
      "eval_steps_per_second": 9.518,
      "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": 2.74242654437376e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}