{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014712643678160919,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.35632183908046e-05,
      "eval_loss": 2.3851115703582764,
      "eval_runtime": 592.4759,
      "eval_samples_per_second": 9.661,
      "eval_steps_per_second": 4.831,
      "step": 1
    },
    {
      "epoch": 0.000367816091954023,
      "grad_norm": 3.2054150104522705,
      "learning_rate": 5e-05,
      "loss": 2.3289,
      "step": 5
    },
    {
      "epoch": 0.000735632183908046,
      "grad_norm": 2.5026473999023438,
      "learning_rate": 0.0001,
      "loss": 2.0213,
      "step": 10
    },
    {
      "epoch": 0.001103448275862069,
      "grad_norm": 1.4173187017440796,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7658,
      "step": 15
    },
    {
      "epoch": 0.001471264367816092,
      "grad_norm": 1.2474634647369385,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5871,
      "step": 20
    },
    {
      "epoch": 0.0018390804597701149,
      "grad_norm": 1.3965306282043457,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5578,
      "step": 25
    },
    {
      "epoch": 0.002206896551724138,
      "grad_norm": 1.4394673109054565,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.5593,
      "step": 30
    },
    {
      "epoch": 0.002574712643678161,
      "grad_norm": 1.296766757965088,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.447,
      "step": 35
    },
    {
      "epoch": 0.002942528735632184,
      "grad_norm": 1.230973243713379,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.641,
      "step": 40
    },
    {
      "epoch": 0.003310344827586207,
      "grad_norm": 1.3208956718444824,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.6261,
      "step": 45
    },
    {
      "epoch": 0.0036781609195402297,
      "grad_norm": 1.1837828159332275,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.6179,
      "step": 50
    },
    {
      "epoch": 0.0036781609195402297,
      "eval_loss": 1.5870054960250854,
      "eval_runtime": 594.4969,
      "eval_samples_per_second": 9.628,
      "eval_steps_per_second": 4.814,
      "step": 50
    },
    {
      "epoch": 0.004045977011494253,
      "grad_norm": 1.1053797006607056,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.6441,
      "step": 55
    },
    {
      "epoch": 0.004413793103448276,
      "grad_norm": 1.1771963834762573,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.5023,
      "step": 60
    },
    {
      "epoch": 0.0047816091954022985,
      "grad_norm": 0.9694396257400513,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.684,
      "step": 65
    },
    {
      "epoch": 0.005149425287356322,
      "grad_norm": 1.202872395515442,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.6616,
      "step": 70
    },
    {
      "epoch": 0.005517241379310344,
      "grad_norm": 1.0650283098220825,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.5284,
      "step": 75
    },
    {
      "epoch": 0.005885057471264368,
      "grad_norm": 1.0592875480651855,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.6002,
      "step": 80
    },
    {
      "epoch": 0.006252873563218391,
      "grad_norm": 1.0368422269821167,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.5468,
      "step": 85
    },
    {
      "epoch": 0.006620689655172414,
      "grad_norm": 1.0760207176208496,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.5335,
      "step": 90
    },
    {
      "epoch": 0.006988505747126437,
      "grad_norm": 1.0518993139266968,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.5375,
      "step": 95
    },
    {
      "epoch": 0.0073563218390804595,
      "grad_norm": 0.99644535779953,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.57,
      "step": 100
    },
    {
      "epoch": 0.0073563218390804595,
      "eval_loss": 1.5718929767608643,
      "eval_runtime": 594.3131,
      "eval_samples_per_second": 9.631,
      "eval_steps_per_second": 4.816,
      "step": 100
    },
    {
      "epoch": 0.007724137931034483,
      "grad_norm": 0.9961000084877014,
      "learning_rate": 5e-05,
      "loss": 1.5176,
      "step": 105
    },
    {
      "epoch": 0.008091954022988505,
      "grad_norm": 0.9916229844093323,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.5182,
      "step": 110
    },
    {
      "epoch": 0.00845977011494253,
      "grad_norm": 1.0973960161209106,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.7128,
      "step": 115
    },
    {
      "epoch": 0.008827586206896552,
      "grad_norm": 0.992687463760376,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.6312,
      "step": 120
    },
    {
      "epoch": 0.009195402298850575,
      "grad_norm": 1.0211665630340576,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.6858,
      "step": 125
    },
    {
      "epoch": 0.009563218390804597,
      "grad_norm": 1.02646005153656,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.4403,
      "step": 130
    },
    {
      "epoch": 0.009931034482758621,
      "grad_norm": 1.0905909538269043,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.4371,
      "step": 135
    },
    {
      "epoch": 0.010298850574712644,
      "grad_norm": 1.1285451650619507,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.5096,
      "step": 140
    },
    {
      "epoch": 0.010666666666666666,
      "grad_norm": 1.1632394790649414,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.4889,
      "step": 145
    },
    {
      "epoch": 0.011034482758620689,
      "grad_norm": 1.2418015003204346,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.7854,
      "step": 150
    },
    {
      "epoch": 0.011034482758620689,
      "eval_loss": 1.5659912824630737,
      "eval_runtime": 594.3479,
      "eval_samples_per_second": 9.631,
      "eval_steps_per_second": 4.815,
      "step": 150
    },
    {
      "epoch": 0.011402298850574713,
      "grad_norm": 1.043492317199707,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.6572,
      "step": 155
    },
    {
      "epoch": 0.011770114942528736,
      "grad_norm": 0.958644688129425,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.6572,
      "step": 160
    },
    {
      "epoch": 0.012137931034482758,
      "grad_norm": 0.9402018785476685,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.5295,
      "step": 165
    },
    {
      "epoch": 0.012505747126436782,
      "grad_norm": 1.0198190212249756,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.532,
      "step": 170
    },
    {
      "epoch": 0.012873563218390805,
      "grad_norm": 0.9930036067962646,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.5778,
      "step": 175
    },
    {
      "epoch": 0.013241379310344827,
      "grad_norm": 0.9383140802383423,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.4909,
      "step": 180
    },
    {
      "epoch": 0.01360919540229885,
      "grad_norm": 1.0298653841018677,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.5713,
      "step": 185
    },
    {
      "epoch": 0.013977011494252874,
      "grad_norm": 0.9578173160552979,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.4889,
      "step": 190
    },
    {
      "epoch": 0.014344827586206896,
      "grad_norm": 1.009029507637024,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.5112,
      "step": 195
    },
    {
      "epoch": 0.014712643678160919,
      "grad_norm": 1.2505810260772705,
      "learning_rate": 0.0,
      "loss": 1.7079,
      "step": 200
    },
    {
      "epoch": 0.014712643678160919,
      "eval_loss": 1.564515233039856,
      "eval_runtime": 594.4025,
      "eval_samples_per_second": 9.63,
      "eval_steps_per_second": 4.815,
      "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": 8.4487308312576e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}