{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008091044684633144,
  "eval_steps": 9,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.172772408720348e-05,
      "eval_loss": 3.0754568576812744,
      "eval_runtime": 1473.3121,
      "eval_samples_per_second": 13.988,
      "eval_steps_per_second": 1.748,
      "step": 1
    },
    {
      "epoch": 0.00024518317226161047,
      "grad_norm": 2.296231508255005,
      "learning_rate": 1.5e-05,
      "loss": 3.1328,
      "step": 3
    },
    {
      "epoch": 0.0004903663445232209,
      "grad_norm": 2.6038119792938232,
      "learning_rate": 3e-05,
      "loss": 3.1551,
      "step": 6
    },
    {
      "epoch": 0.0007355495167848313,
      "grad_norm": 2.212124824523926,
      "learning_rate": 4.5e-05,
      "loss": 2.9992,
      "step": 9
    },
    {
      "epoch": 0.0007355495167848313,
      "eval_loss": 2.8090972900390625,
      "eval_runtime": 1479.6417,
      "eval_samples_per_second": 13.928,
      "eval_steps_per_second": 1.741,
      "step": 9
    },
    {
      "epoch": 0.0009807326890464419,
      "grad_norm": 1.9561810493469238,
      "learning_rate": 4.993910125649561e-05,
      "loss": 2.5897,
      "step": 12
    },
    {
      "epoch": 0.0012259158613080522,
      "grad_norm": 1.9245012998580933,
      "learning_rate": 4.962019382530521e-05,
      "loss": 2.4492,
      "step": 15
    },
    {
      "epoch": 0.0014710990335696627,
      "grad_norm": 1.889432668685913,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 2.2559,
      "step": 18
    },
    {
      "epoch": 0.0014710990335696627,
      "eval_loss": 2.1555984020233154,
      "eval_runtime": 1479.8367,
      "eval_samples_per_second": 13.926,
      "eval_steps_per_second": 1.741,
      "step": 18
    },
    {
      "epoch": 0.0017162822058312732,
      "grad_norm": 1.7957980632781982,
      "learning_rate": 4.817959636416969e-05,
      "loss": 2.1327,
      "step": 21
    },
    {
      "epoch": 0.0019614653780928837,
      "grad_norm": 1.9399701356887817,
      "learning_rate": 4.707368982147318e-05,
      "loss": 2.0367,
      "step": 24
    },
    {
      "epoch": 0.002206648550354494,
      "grad_norm": 1.5504800081253052,
      "learning_rate": 4.572593931387604e-05,
      "loss": 1.9053,
      "step": 27
    },
    {
      "epoch": 0.002206648550354494,
      "eval_loss": 1.9717642068862915,
      "eval_runtime": 1481.1895,
      "eval_samples_per_second": 13.913,
      "eval_steps_per_second": 1.739,
      "step": 27
    },
    {
      "epoch": 0.0024518317226161043,
      "grad_norm": 1.7425073385238647,
      "learning_rate": 4.415111107797445e-05,
      "loss": 1.8392,
      "step": 30
    },
    {
      "epoch": 0.002697014894877715,
      "grad_norm": 1.7729347944259644,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 1.7942,
      "step": 33
    },
    {
      "epoch": 0.0029421980671393254,
      "grad_norm": 1.707261085510254,
      "learning_rate": 4.039153688314145e-05,
      "loss": 1.8025,
      "step": 36
    },
    {
      "epoch": 0.0029421980671393254,
      "eval_loss": 1.9066901206970215,
      "eval_runtime": 1480.5341,
      "eval_samples_per_second": 13.919,
      "eval_steps_per_second": 1.74,
      "step": 36
    },
    {
      "epoch": 0.0031873812394009357,
      "grad_norm": 1.7224209308624268,
      "learning_rate": 3.824798160583012e-05,
      "loss": 1.8219,
      "step": 39
    },
    {
      "epoch": 0.0034325644116625464,
      "grad_norm": 1.7952418327331543,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 1.7616,
      "step": 42
    },
    {
      "epoch": 0.0036777475839241567,
      "grad_norm": 1.5710504055023193,
      "learning_rate": 3.355050358314172e-05,
      "loss": 1.7893,
      "step": 45
    },
    {
      "epoch": 0.0036777475839241567,
      "eval_loss": 1.8848282098770142,
      "eval_runtime": 1480.2374,
      "eval_samples_per_second": 13.922,
      "eval_steps_per_second": 1.74,
      "step": 45
    },
    {
      "epoch": 0.0039229307561857675,
      "grad_norm": 1.5914199352264404,
      "learning_rate": 3.104804738999169e-05,
      "loss": 1.9077,
      "step": 48
    },
    {
      "epoch": 0.004168113928447377,
      "grad_norm": 1.5195039510726929,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 1.7559,
      "step": 51
    },
    {
      "epoch": 0.004413297100708988,
      "grad_norm": 1.5680406093597412,
      "learning_rate": 2.587248741756253e-05,
      "loss": 1.8401,
      "step": 54
    },
    {
      "epoch": 0.004413297100708988,
      "eval_loss": 1.8674110174179077,
      "eval_runtime": 1480.6768,
      "eval_samples_per_second": 13.918,
      "eval_steps_per_second": 1.74,
      "step": 54
    },
    {
      "epoch": 0.004658480272970599,
      "grad_norm": 1.7326178550720215,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 1.8627,
      "step": 57
    },
    {
      "epoch": 0.004903663445232209,
      "grad_norm": 1.689798355102539,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 1.7823,
      "step": 60
    },
    {
      "epoch": 0.005148846617493819,
      "grad_norm": 1.675605297088623,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 1.8888,
      "step": 63
    },
    {
      "epoch": 0.005148846617493819,
      "eval_loss": 1.8558694124221802,
      "eval_runtime": 1480.1771,
      "eval_samples_per_second": 13.923,
      "eval_steps_per_second": 1.74,
      "step": 63
    },
    {
      "epoch": 0.00539402978975543,
      "grad_norm": 1.4975136518478394,
      "learning_rate": 1.56348351646022e-05,
      "loss": 1.8776,
      "step": 66
    },
    {
      "epoch": 0.00563921296201704,
      "grad_norm": 1.6283100843429565,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 1.8479,
      "step": 69
    },
    {
      "epoch": 0.005884396134278651,
      "grad_norm": 1.4557535648345947,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 1.8951,
      "step": 72
    },
    {
      "epoch": 0.005884396134278651,
      "eval_loss": 1.849563479423523,
      "eval_runtime": 1480.307,
      "eval_samples_per_second": 13.921,
      "eval_steps_per_second": 1.74,
      "step": 72
    },
    {
      "epoch": 0.0061295793065402615,
      "grad_norm": 1.6248055696487427,
      "learning_rate": 8.930309757836517e-06,
      "loss": 1.9235,
      "step": 75
    },
    {
      "epoch": 0.006374762478801871,
      "grad_norm": 1.6928157806396484,
      "learning_rate": 7.016504991533726e-06,
      "loss": 1.8022,
      "step": 78
    },
    {
      "epoch": 0.006619945651063482,
      "grad_norm": 1.8526602983474731,
      "learning_rate": 5.299731159831953e-06,
      "loss": 1.9286,
      "step": 81
    },
    {
      "epoch": 0.006619945651063482,
      "eval_loss": 1.846510648727417,
      "eval_runtime": 1480.0811,
      "eval_samples_per_second": 13.924,
      "eval_steps_per_second": 1.74,
      "step": 81
    },
    {
      "epoch": 0.006865128823325093,
      "grad_norm": 1.4159300327301025,
      "learning_rate": 3.798797596089351e-06,
      "loss": 1.7466,
      "step": 84
    },
    {
      "epoch": 0.007110311995586703,
      "grad_norm": 1.5407592058181763,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 1.736,
      "step": 87
    },
    {
      "epoch": 0.0073554951678483135,
      "grad_norm": 1.683846354484558,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 1.8533,
      "step": 90
    },
    {
      "epoch": 0.0073554951678483135,
      "eval_loss": 1.8448913097381592,
      "eval_runtime": 1478.1743,
      "eval_samples_per_second": 13.942,
      "eval_steps_per_second": 1.743,
      "step": 90
    },
    {
      "epoch": 0.007600678340109924,
      "grad_norm": 1.427655577659607,
      "learning_rate": 7.426068431000882e-07,
      "loss": 1.6916,
      "step": 93
    },
    {
      "epoch": 0.007845861512371535,
      "grad_norm": 1.4828401803970337,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 1.7312,
      "step": 96
    },
    {
      "epoch": 0.008091044684633144,
      "grad_norm": 1.8109315633773804,
      "learning_rate": 1.522932452260595e-08,
      "loss": 1.8273,
      "step": 99
    },
    {
      "epoch": 0.008091044684633144,
      "eval_loss": 1.8446593284606934,
      "eval_runtime": 1477.5292,
      "eval_samples_per_second": 13.948,
      "eval_steps_per_second": 1.743,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3895431483922842e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}