{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13020833333333334,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005208333333333333,
      "grad_norm": 1.149965763092041,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.1312,
      "step": 1
    },
    {
      "epoch": 0.005208333333333333,
      "eval_loss": 3.160311460494995,
      "eval_runtime": 2.6854,
      "eval_samples_per_second": 60.326,
      "eval_steps_per_second": 7.82,
      "step": 1
    },
    {
      "epoch": 0.010416666666666666,
      "grad_norm": 1.072540521621704,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.1759,
      "step": 2
    },
    {
      "epoch": 0.015625,
      "grad_norm": 1.0272471904754639,
      "learning_rate": 6e-06,
      "loss": 3.1055,
      "step": 3
    },
    {
      "epoch": 0.020833333333333332,
      "grad_norm": 1.1299035549163818,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.2217,
      "step": 4
    },
    {
      "epoch": 0.026041666666666668,
      "grad_norm": 0.9919382929801941,
      "learning_rate": 1e-05,
      "loss": 3.028,
      "step": 5
    },
    {
      "epoch": 0.03125,
      "grad_norm": 1.0636495351791382,
      "learning_rate": 1.2e-05,
      "loss": 3.2194,
      "step": 6
    },
    {
      "epoch": 0.036458333333333336,
      "grad_norm": 1.0188517570495605,
      "learning_rate": 1.4e-05,
      "loss": 3.1403,
      "step": 7
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 1.1026723384857178,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.1992,
      "step": 8
    },
    {
      "epoch": 0.046875,
      "grad_norm": 0.966528058052063,
      "learning_rate": 1.8e-05,
      "loss": 3.0237,
      "step": 9
    },
    {
      "epoch": 0.046875,
      "eval_loss": 3.1478817462921143,
      "eval_runtime": 2.0938,
      "eval_samples_per_second": 77.372,
      "eval_steps_per_second": 10.03,
      "step": 9
    },
    {
      "epoch": 0.052083333333333336,
      "grad_norm": 0.8940801620483398,
      "learning_rate": 2e-05,
      "loss": 3.0852,
      "step": 10
    },
    {
      "epoch": 0.057291666666666664,
      "grad_norm": 1.0513722896575928,
      "learning_rate": 1.999390827019096e-05,
      "loss": 3.2125,
      "step": 11
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.9304180145263672,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 3.1098,
      "step": 12
    },
    {
      "epoch": 0.06770833333333333,
      "grad_norm": 0.7351564168930054,
      "learning_rate": 1.9945218953682736e-05,
      "loss": 3.0332,
      "step": 13
    },
    {
      "epoch": 0.07291666666666667,
      "grad_norm": 0.862900972366333,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 3.173,
      "step": 14
    },
    {
      "epoch": 0.078125,
      "grad_norm": 0.7154681086540222,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 3.0754,
      "step": 15
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.8201392889022827,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 3.1666,
      "step": 16
    },
    {
      "epoch": 0.08854166666666667,
      "grad_norm": 0.7526658177375793,
      "learning_rate": 1.9702957262759964e-05,
      "loss": 3.0601,
      "step": 17
    },
    {
      "epoch": 0.09375,
      "grad_norm": 0.7286026477813721,
      "learning_rate": 1.961261695938319e-05,
      "loss": 3.0727,
      "step": 18
    },
    {
      "epoch": 0.09375,
      "eval_loss": 3.06829571723938,
      "eval_runtime": 2.1125,
      "eval_samples_per_second": 76.688,
      "eval_steps_per_second": 9.941,
      "step": 18
    },
    {
      "epoch": 0.09895833333333333,
      "grad_norm": 0.6828358769416809,
      "learning_rate": 1.9510565162951538e-05,
      "loss": 3.0873,
      "step": 19
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 0.7122036814689636,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 3.042,
      "step": 20
    },
    {
      "epoch": 0.109375,
      "grad_norm": 0.642253577709198,
      "learning_rate": 1.9271838545667876e-05,
      "loss": 3.0086,
      "step": 21
    },
    {
      "epoch": 0.11458333333333333,
      "grad_norm": 0.7375343441963196,
      "learning_rate": 1.913545457642601e-05,
      "loss": 3.0629,
      "step": 22
    },
    {
      "epoch": 0.11979166666666667,
      "grad_norm": 0.6836945414543152,
      "learning_rate": 1.8987940462991673e-05,
      "loss": 3.0095,
      "step": 23
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.8602219820022583,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 3.0885,
      "step": 24
    },
    {
      "epoch": 0.13020833333333334,
      "grad_norm": 0.6618623733520508,
      "learning_rate": 1.866025403784439e-05,
      "loss": 2.9082,
      "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": 506757189206016.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}