{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0023720290336353717,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.488116134541487e-05,
      "grad_norm": 1.1179174184799194,
      "learning_rate": 1e-05,
      "loss": 2.0136,
      "step": 1
    },
    {
      "epoch": 9.488116134541487e-05,
      "eval_loss": 2.044814109802246,
      "eval_runtime": 1082.9405,
      "eval_samples_per_second": 8.196,
      "eval_steps_per_second": 1.025,
      "step": 1
    },
    {
      "epoch": 0.00018976232269082974,
      "grad_norm": 1.2873406410217285,
      "learning_rate": 2e-05,
      "loss": 2.2054,
      "step": 2
    },
    {
      "epoch": 0.00028464348403624463,
      "grad_norm": 1.4217164516448975,
      "learning_rate": 3e-05,
      "loss": 2.2993,
      "step": 3
    },
    {
      "epoch": 0.00037952464538165947,
      "grad_norm": 1.0913364887237549,
      "learning_rate": 4e-05,
      "loss": 1.9095,
      "step": 4
    },
    {
      "epoch": 0.00047440580672707437,
      "grad_norm": 1.1571333408355713,
      "learning_rate": 5e-05,
      "loss": 1.8157,
      "step": 5
    },
    {
      "epoch": 0.0005692869680724893,
      "grad_norm": 1.1290559768676758,
      "learning_rate": 6e-05,
      "loss": 1.6643,
      "step": 6
    },
    {
      "epoch": 0.000664168129417904,
      "grad_norm": 1.201819896697998,
      "learning_rate": 7e-05,
      "loss": 1.9168,
      "step": 7
    },
    {
      "epoch": 0.0007590492907633189,
      "grad_norm": 1.501457929611206,
      "learning_rate": 8e-05,
      "loss": 2.1298,
      "step": 8
    },
    {
      "epoch": 0.0008539304521087338,
      "grad_norm": 1.226552963256836,
      "learning_rate": 9e-05,
      "loss": 1.9444,
      "step": 9
    },
    {
      "epoch": 0.0008539304521087338,
      "eval_loss": 1.828656792640686,
      "eval_runtime": 1085.5057,
      "eval_samples_per_second": 8.177,
      "eval_steps_per_second": 1.023,
      "step": 9
    },
    {
      "epoch": 0.0009488116134541487,
      "grad_norm": 1.08986496925354,
      "learning_rate": 0.0001,
      "loss": 2.0429,
      "step": 10
    },
    {
      "epoch": 0.0010436927747995636,
      "grad_norm": 1.1125391721725464,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.8817,
      "step": 11
    },
    {
      "epoch": 0.0011385739361449785,
      "grad_norm": 1.5336627960205078,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.8072,
      "step": 12
    },
    {
      "epoch": 0.0012334550974903932,
      "grad_norm": 1.4077439308166504,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.8512,
      "step": 13
    },
    {
      "epoch": 0.001328336258835808,
      "grad_norm": 1.3526650667190552,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.7567,
      "step": 14
    },
    {
      "epoch": 0.001423217420181223,
      "grad_norm": 1.23054039478302,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.782,
      "step": 15
    },
    {
      "epoch": 0.0015180985815266379,
      "grad_norm": 1.219004511833191,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.7007,
      "step": 16
    },
    {
      "epoch": 0.0016129797428720528,
      "grad_norm": 0.9380444288253784,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.7286,
      "step": 17
    },
    {
      "epoch": 0.0017078609042174677,
      "grad_norm": 1.0295952558517456,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7644,
      "step": 18
    },
    {
      "epoch": 0.0017078609042174677,
      "eval_loss": 1.6711846590042114,
      "eval_runtime": 1084.8063,
      "eval_samples_per_second": 8.182,
      "eval_steps_per_second": 1.023,
      "step": 18
    },
    {
      "epoch": 0.0018027420655628826,
      "grad_norm": 1.3452121019363403,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.9288,
      "step": 19
    },
    {
      "epoch": 0.0018976232269082975,
      "grad_norm": 0.9437580108642578,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.5166,
      "step": 20
    },
    {
      "epoch": 0.001992504388253712,
      "grad_norm": 0.9429516792297363,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.4955,
      "step": 21
    },
    {
      "epoch": 0.0020873855495991273,
      "grad_norm": 0.8644145727157593,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.4253,
      "step": 22
    },
    {
      "epoch": 0.002182266710944542,
      "grad_norm": 0.940532922744751,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.6322,
      "step": 23
    },
    {
      "epoch": 0.002277147872289957,
      "grad_norm": 0.9520596265792847,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.4608,
      "step": 24
    },
    {
      "epoch": 0.0023720290336353717,
      "grad_norm": 1.16845703125,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5855,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.85471921553408e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}