{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22637238256932654,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022637238256932655,
      "eval_loss": 2.451014995574951,
      "eval_runtime": 13.8202,
      "eval_samples_per_second": 53.834,
      "eval_steps_per_second": 6.729,
      "step": 1
    },
    {
      "epoch": 0.006791171477079796,
      "grad_norm": 8.80556583404541,
      "learning_rate": 1.5e-05,
      "loss": 9.9522,
      "step": 3
    },
    {
      "epoch": 0.013582342954159592,
      "grad_norm": 7.6549296379089355,
      "learning_rate": 3e-05,
      "loss": 9.7544,
      "step": 6
    },
    {
      "epoch": 0.02037351443123939,
      "grad_norm": 5.776790142059326,
      "learning_rate": 4.5e-05,
      "loss": 9.3333,
      "step": 9
    },
    {
      "epoch": 0.02037351443123939,
      "eval_loss": 2.167935371398926,
      "eval_runtime": 13.8203,
      "eval_samples_per_second": 53.834,
      "eval_steps_per_second": 6.729,
      "step": 9
    },
    {
      "epoch": 0.027164685908319185,
      "grad_norm": 6.475290298461914,
      "learning_rate": 4.993910125649561e-05,
      "loss": 8.4645,
      "step": 12
    },
    {
      "epoch": 0.03395585738539898,
      "grad_norm": 5.600065231323242,
      "learning_rate": 4.962019382530521e-05,
      "loss": 7.9066,
      "step": 15
    },
    {
      "epoch": 0.04074702886247878,
      "grad_norm": 4.763131141662598,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 7.4846,
      "step": 18
    },
    {
      "epoch": 0.04074702886247878,
      "eval_loss": 1.6147438287734985,
      "eval_runtime": 13.8274,
      "eval_samples_per_second": 53.806,
      "eval_steps_per_second": 6.726,
      "step": 18
    },
    {
      "epoch": 0.04753820033955857,
      "grad_norm": 5.634120464324951,
      "learning_rate": 4.817959636416969e-05,
      "loss": 6.5272,
      "step": 21
    },
    {
      "epoch": 0.05432937181663837,
      "grad_norm": 6.285006523132324,
      "learning_rate": 4.707368982147318e-05,
      "loss": 5.7971,
      "step": 24
    },
    {
      "epoch": 0.06112054329371817,
      "grad_norm": 6.8695068359375,
      "learning_rate": 4.572593931387604e-05,
      "loss": 4.9845,
      "step": 27
    },
    {
      "epoch": 0.06112054329371817,
      "eval_loss": 1.031599521636963,
      "eval_runtime": 13.8524,
      "eval_samples_per_second": 53.709,
      "eval_steps_per_second": 6.714,
      "step": 27
    },
    {
      "epoch": 0.06791171477079797,
      "grad_norm": 6.803356647491455,
      "learning_rate": 4.415111107797445e-05,
      "loss": 4.4211,
      "step": 30
    },
    {
      "epoch": 0.07470288624787776,
      "grad_norm": 6.876413822174072,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 3.9065,
      "step": 33
    },
    {
      "epoch": 0.08149405772495756,
      "grad_norm": 6.460537910461426,
      "learning_rate": 4.039153688314145e-05,
      "loss": 2.6423,
      "step": 36
    },
    {
      "epoch": 0.08149405772495756,
      "eval_loss": 0.5614111423492432,
      "eval_runtime": 13.8854,
      "eval_samples_per_second": 53.582,
      "eval_steps_per_second": 6.698,
      "step": 36
    },
    {
      "epoch": 0.08828522920203735,
      "grad_norm": 6.166537284851074,
      "learning_rate": 3.824798160583012e-05,
      "loss": 2.4743,
      "step": 39
    },
    {
      "epoch": 0.09507640067911714,
      "grad_norm": 5.022619247436523,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 1.8098,
      "step": 42
    },
    {
      "epoch": 0.10186757215619695,
      "grad_norm": 3.948338270187378,
      "learning_rate": 3.355050358314172e-05,
      "loss": 1.4085,
      "step": 45
    },
    {
      "epoch": 0.10186757215619695,
      "eval_loss": 0.36165785789489746,
      "eval_runtime": 13.8242,
      "eval_samples_per_second": 53.819,
      "eval_steps_per_second": 6.727,
      "step": 45
    },
    {
      "epoch": 0.10865874363327674,
      "grad_norm": 3.390995740890503,
      "learning_rate": 3.104804738999169e-05,
      "loss": 2.1414,
      "step": 48
    },
    {
      "epoch": 0.11544991511035653,
      "grad_norm": 2.3481874465942383,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 1.2563,
      "step": 51
    },
    {
      "epoch": 0.12224108658743633,
      "grad_norm": 2.5623438358306885,
      "learning_rate": 2.587248741756253e-05,
      "loss": 0.928,
      "step": 54
    },
    {
      "epoch": 0.12224108658743633,
      "eval_loss": 0.3103027641773224,
      "eval_runtime": 13.8523,
      "eval_samples_per_second": 53.71,
      "eval_steps_per_second": 6.714,
      "step": 54
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 2.2818145751953125,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 1.4792,
      "step": 57
    },
    {
      "epoch": 0.13582342954159593,
      "grad_norm": 1.8915352821350098,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 1.7852,
      "step": 60
    },
    {
      "epoch": 0.14261460101867574,
      "grad_norm": 1.7816964387893677,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 0.7481,
      "step": 63
    },
    {
      "epoch": 0.14261460101867574,
      "eval_loss": 0.2852364480495453,
      "eval_runtime": 13.8859,
      "eval_samples_per_second": 53.58,
      "eval_steps_per_second": 6.697,
      "step": 63
    },
    {
      "epoch": 0.1494057724957555,
      "grad_norm": 1.4512760639190674,
      "learning_rate": 1.56348351646022e-05,
      "loss": 0.6048,
      "step": 66
    },
    {
      "epoch": 0.15619694397283532,
      "grad_norm": 1.6632657051086426,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 1.2286,
      "step": 69
    },
    {
      "epoch": 0.16298811544991512,
      "grad_norm": 1.75409996509552,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 1.1425,
      "step": 72
    },
    {
      "epoch": 0.16298811544991512,
      "eval_loss": 0.27254876494407654,
      "eval_runtime": 13.8868,
      "eval_samples_per_second": 53.576,
      "eval_steps_per_second": 6.697,
      "step": 72
    },
    {
      "epoch": 0.1697792869269949,
      "grad_norm": 1.7618364095687866,
      "learning_rate": 8.930309757836517e-06,
      "loss": 0.7225,
      "step": 75
    },
    {
      "epoch": 0.1765704584040747,
      "grad_norm": 1.6287004947662354,
      "learning_rate": 7.016504991533726e-06,
      "loss": 1.5803,
      "step": 78
    },
    {
      "epoch": 0.1833616298811545,
      "grad_norm": 1.694528341293335,
      "learning_rate": 5.299731159831953e-06,
      "loss": 1.501,
      "step": 81
    },
    {
      "epoch": 0.1833616298811545,
      "eval_loss": 0.2671685516834259,
      "eval_runtime": 13.8788,
      "eval_samples_per_second": 53.607,
      "eval_steps_per_second": 6.701,
      "step": 81
    },
    {
      "epoch": 0.19015280135823429,
      "grad_norm": 1.4942442178726196,
      "learning_rate": 3.798797596089351e-06,
      "loss": 0.8338,
      "step": 84
    },
    {
      "epoch": 0.1969439728353141,
      "grad_norm": 2.2192111015319824,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 1.0876,
      "step": 87
    },
    {
      "epoch": 0.2037351443123939,
      "grad_norm": 1.662070631980896,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 0.7232,
      "step": 90
    },
    {
      "epoch": 0.2037351443123939,
      "eval_loss": 0.26488208770751953,
      "eval_runtime": 13.8766,
      "eval_samples_per_second": 53.615,
      "eval_steps_per_second": 6.702,
      "step": 90
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 2.4987051486968994,
      "learning_rate": 7.426068431000882e-07,
      "loss": 1.1828,
      "step": 93
    },
    {
      "epoch": 0.21731748726655348,
      "grad_norm": 1.3806511163711548,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 1.2881,
      "step": 96
    },
    {
      "epoch": 0.22410865874363328,
      "grad_norm": 1.8483511209487915,
      "learning_rate": 1.522932452260595e-08,
      "loss": 0.8013,
      "step": 99
    },
    {
      "epoch": 0.22410865874363328,
      "eval_loss": 0.2645917236804962,
      "eval_runtime": 13.8946,
      "eval_samples_per_second": 53.546,
      "eval_steps_per_second": 6.693,
      "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": 2.45813175386112e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}