{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08680555555555555,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008680555555555555,
      "eval_loss": 1.937089443206787,
      "eval_runtime": 131.5855,
      "eval_samples_per_second": 14.743,
      "eval_steps_per_second": 1.847,
      "step": 1
    },
    {
      "epoch": 0.0026041666666666665,
      "grad_norm": 23.593791961669922,
      "learning_rate": 1.5e-05,
      "loss": 7.6661,
      "step": 3
    },
    {
      "epoch": 0.005208333333333333,
      "grad_norm": 19.38722801208496,
      "learning_rate": 3e-05,
      "loss": 7.2214,
      "step": 6
    },
    {
      "epoch": 0.0078125,
      "grad_norm": 8.94090747833252,
      "learning_rate": 4.5e-05,
      "loss": 5.5255,
      "step": 9
    },
    {
      "epoch": 0.0078125,
      "eval_loss": 1.2398158311843872,
      "eval_runtime": 133.0104,
      "eval_samples_per_second": 14.585,
      "eval_steps_per_second": 1.827,
      "step": 9
    },
    {
      "epoch": 0.010416666666666666,
      "grad_norm": 7.774077892303467,
      "learning_rate": 4.993910125649561e-05,
      "loss": 4.6268,
      "step": 12
    },
    {
      "epoch": 0.013020833333333334,
      "grad_norm": 4.864662170410156,
      "learning_rate": 4.962019382530521e-05,
      "loss": 3.9421,
      "step": 15
    },
    {
      "epoch": 0.015625,
      "grad_norm": 3.9902665615081787,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 3.4764,
      "step": 18
    },
    {
      "epoch": 0.015625,
      "eval_loss": 0.8059016466140747,
      "eval_runtime": 133.0467,
      "eval_samples_per_second": 14.581,
      "eval_steps_per_second": 1.826,
      "step": 18
    },
    {
      "epoch": 0.018229166666666668,
      "grad_norm": 4.092312812805176,
      "learning_rate": 4.817959636416969e-05,
      "loss": 3.1563,
      "step": 21
    },
    {
      "epoch": 0.020833333333333332,
      "grad_norm": 4.029233455657959,
      "learning_rate": 4.707368982147318e-05,
      "loss": 2.8557,
      "step": 24
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 3.739703416824341,
      "learning_rate": 4.572593931387604e-05,
      "loss": 2.7301,
      "step": 27
    },
    {
      "epoch": 0.0234375,
      "eval_loss": 0.627487063407898,
      "eval_runtime": 133.024,
      "eval_samples_per_second": 14.584,
      "eval_steps_per_second": 1.827,
      "step": 27
    },
    {
      "epoch": 0.026041666666666668,
      "grad_norm": 3.982668161392212,
      "learning_rate": 4.415111107797445e-05,
      "loss": 2.4342,
      "step": 30
    },
    {
      "epoch": 0.028645833333333332,
      "grad_norm": 3.4705731868743896,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 2.236,
      "step": 33
    },
    {
      "epoch": 0.03125,
      "grad_norm": 3.903174638748169,
      "learning_rate": 4.039153688314145e-05,
      "loss": 2.1105,
      "step": 36
    },
    {
      "epoch": 0.03125,
      "eval_loss": 0.5284584760665894,
      "eval_runtime": 133.1079,
      "eval_samples_per_second": 14.575,
      "eval_steps_per_second": 1.826,
      "step": 36
    },
    {
      "epoch": 0.033854166666666664,
      "grad_norm": 3.955035448074341,
      "learning_rate": 3.824798160583012e-05,
      "loss": 2.1069,
      "step": 39
    },
    {
      "epoch": 0.036458333333333336,
      "grad_norm": 4.207739353179932,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 1.9208,
      "step": 42
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 4.347591400146484,
      "learning_rate": 3.355050358314172e-05,
      "loss": 1.9558,
      "step": 45
    },
    {
      "epoch": 0.0390625,
      "eval_loss": 0.46904227137565613,
      "eval_runtime": 133.003,
      "eval_samples_per_second": 14.586,
      "eval_steps_per_second": 1.827,
      "step": 45
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 4.274533271789551,
      "learning_rate": 3.104804738999169e-05,
      "loss": 1.8352,
      "step": 48
    },
    {
      "epoch": 0.044270833333333336,
      "grad_norm": 3.8483474254608154,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 1.7612,
      "step": 51
    },
    {
      "epoch": 0.046875,
      "grad_norm": 4.284761428833008,
      "learning_rate": 2.587248741756253e-05,
      "loss": 1.8031,
      "step": 54
    },
    {
      "epoch": 0.046875,
      "eval_loss": 0.43528732657432556,
      "eval_runtime": 132.9965,
      "eval_samples_per_second": 14.587,
      "eval_steps_per_second": 1.827,
      "step": 54
    },
    {
      "epoch": 0.049479166666666664,
      "grad_norm": 4.528855323791504,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 1.6669,
      "step": 57
    },
    {
      "epoch": 0.052083333333333336,
      "grad_norm": 4.008581638336182,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 1.7404,
      "step": 60
    },
    {
      "epoch": 0.0546875,
      "grad_norm": 4.258989334106445,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 1.6657,
      "step": 63
    },
    {
      "epoch": 0.0546875,
      "eval_loss": 0.4117554724216461,
      "eval_runtime": 133.0085,
      "eval_samples_per_second": 14.586,
      "eval_steps_per_second": 1.827,
      "step": 63
    },
    {
      "epoch": 0.057291666666666664,
      "grad_norm": 4.279396057128906,
      "learning_rate": 1.56348351646022e-05,
      "loss": 1.6728,
      "step": 66
    },
    {
      "epoch": 0.059895833333333336,
      "grad_norm": 4.159554958343506,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 1.6461,
      "step": 69
    },
    {
      "epoch": 0.0625,
      "grad_norm": 4.362893104553223,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 1.5333,
      "step": 72
    },
    {
      "epoch": 0.0625,
      "eval_loss": 0.39763975143432617,
      "eval_runtime": 132.9302,
      "eval_samples_per_second": 14.594,
      "eval_steps_per_second": 1.828,
      "step": 72
    },
    {
      "epoch": 0.06510416666666667,
      "grad_norm": 4.511038780212402,
      "learning_rate": 8.930309757836517e-06,
      "loss": 1.5358,
      "step": 75
    },
    {
      "epoch": 0.06770833333333333,
      "grad_norm": 4.454962253570557,
      "learning_rate": 7.016504991533726e-06,
      "loss": 1.5103,
      "step": 78
    },
    {
      "epoch": 0.0703125,
      "grad_norm": 4.400078773498535,
      "learning_rate": 5.299731159831953e-06,
      "loss": 1.478,
      "step": 81
    },
    {
      "epoch": 0.0703125,
      "eval_loss": 0.3869146704673767,
      "eval_runtime": 133.0114,
      "eval_samples_per_second": 14.585,
      "eval_steps_per_second": 1.827,
      "step": 81
    },
    {
      "epoch": 0.07291666666666667,
      "grad_norm": 4.320717811584473,
      "learning_rate": 3.798797596089351e-06,
      "loss": 1.4953,
      "step": 84
    },
    {
      "epoch": 0.07552083333333333,
      "grad_norm": 4.3952789306640625,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 1.5565,
      "step": 87
    },
    {
      "epoch": 0.078125,
      "grad_norm": 3.9055593013763428,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 1.5535,
      "step": 90
    },
    {
      "epoch": 0.078125,
      "eval_loss": 0.3823155462741852,
      "eval_runtime": 132.9844,
      "eval_samples_per_second": 14.588,
      "eval_steps_per_second": 1.827,
      "step": 90
    },
    {
      "epoch": 0.08072916666666667,
      "grad_norm": 4.043277740478516,
      "learning_rate": 7.426068431000882e-07,
      "loss": 1.5073,
      "step": 93
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 4.137203693389893,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 1.5309,
      "step": 96
    },
    {
      "epoch": 0.0859375,
      "grad_norm": 4.494436740875244,
      "learning_rate": 1.522932452260595e-08,
      "loss": 1.4219,
      "step": 99
    },
    {
      "epoch": 0.0859375,
      "eval_loss": 0.3812783360481262,
      "eval_runtime": 132.9892,
      "eval_samples_per_second": 14.588,
      "eval_steps_per_second": 1.827,
      "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.406258997362688e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}