{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6999439147504206,
  "eval_steps": 13,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0179472798653954,
      "grad_norm": 0.16438888013362885,
      "learning_rate": 5e-05,
      "loss": 10.3767,
      "step": 1
    },
    {
      "epoch": 0.0179472798653954,
      "eval_loss": 10.376072883605957,
      "eval_runtime": 1.3774,
      "eval_samples_per_second": 272.971,
      "eval_steps_per_second": 68.243,
      "step": 1
    },
    {
      "epoch": 0.0358945597307908,
      "grad_norm": 0.16105057299137115,
      "learning_rate": 0.0001,
      "loss": 10.3782,
      "step": 2
    },
    {
      "epoch": 0.0538418395961862,
      "grad_norm": 0.1579691618680954,
      "learning_rate": 9.989294616193017e-05,
      "loss": 10.3767,
      "step": 3
    },
    {
      "epoch": 0.0717891194615816,
      "grad_norm": 0.15491828322410583,
      "learning_rate": 9.957224306869053e-05,
      "loss": 10.3761,
      "step": 4
    },
    {
      "epoch": 0.08973639932697701,
      "grad_norm": 0.16071100533008575,
      "learning_rate": 9.903926402016153e-05,
      "loss": 10.3753,
      "step": 5
    },
    {
      "epoch": 0.1076836791923724,
      "grad_norm": 0.16725985705852509,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.3754,
      "step": 6
    },
    {
      "epoch": 0.1256309590577678,
      "grad_norm": 0.15916956961154938,
      "learning_rate": 9.73465064747553e-05,
      "loss": 10.3758,
      "step": 7
    },
    {
      "epoch": 0.1435782389231632,
      "grad_norm": 0.16820161044597626,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.371,
      "step": 8
    },
    {
      "epoch": 0.16152551878855861,
      "grad_norm": 0.1566300243139267,
      "learning_rate": 9.484363707663442e-05,
      "loss": 10.3755,
      "step": 9
    },
    {
      "epoch": 0.17947279865395402,
      "grad_norm": 0.15642325580120087,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3756,
      "step": 10
    },
    {
      "epoch": 0.19742007851934942,
      "grad_norm": 0.16745975613594055,
      "learning_rate": 9.157348061512727e-05,
      "loss": 10.3736,
      "step": 11
    },
    {
      "epoch": 0.2153673583847448,
      "grad_norm": 0.146693155169487,
      "learning_rate": 8.966766701456177e-05,
      "loss": 10.3755,
      "step": 12
    },
    {
      "epoch": 0.2333146382501402,
      "grad_norm": 0.17552213370800018,
      "learning_rate": 8.759199037394887e-05,
      "loss": 10.3722,
      "step": 13
    },
    {
      "epoch": 0.2333146382501402,
      "eval_loss": 10.372008323669434,
      "eval_runtime": 1.3854,
      "eval_samples_per_second": 271.399,
      "eval_steps_per_second": 67.85,
      "step": 13
    },
    {
      "epoch": 0.2512619181155356,
      "grad_norm": 0.17148849368095398,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3725,
      "step": 14
    },
    {
      "epoch": 0.269209197980931,
      "grad_norm": 0.16229911148548126,
      "learning_rate": 8.296729075500344e-05,
      "loss": 10.3714,
      "step": 15
    },
    {
      "epoch": 0.2871564778463264,
      "grad_norm": 0.1958691030740738,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.3628,
      "step": 16
    },
    {
      "epoch": 0.3051037577117218,
      "grad_norm": 0.18110835552215576,
      "learning_rate": 7.777851165098012e-05,
      "loss": 10.3686,
      "step": 17
    },
    {
      "epoch": 0.32305103757711723,
      "grad_norm": 0.17129266262054443,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.371,
      "step": 18
    },
    {
      "epoch": 0.34099831744251263,
      "grad_norm": 0.19044944643974304,
      "learning_rate": 7.211443451095007e-05,
      "loss": 10.3699,
      "step": 19
    },
    {
      "epoch": 0.35894559730790804,
      "grad_norm": 0.17135095596313477,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3701,
      "step": 20
    },
    {
      "epoch": 0.37689287717330344,
      "grad_norm": 0.19162417948246002,
      "learning_rate": 6.607197326515808e-05,
      "loss": 10.3692,
      "step": 21
    },
    {
      "epoch": 0.39484015703869885,
      "grad_norm": 0.17327409982681274,
      "learning_rate": 6.294095225512603e-05,
      "loss": 10.3698,
      "step": 22
    },
    {
      "epoch": 0.4127874369040942,
      "grad_norm": 0.18172384798526764,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 10.368,
      "step": 23
    },
    {
      "epoch": 0.4307347167694896,
      "grad_norm": 0.19202207028865814,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 10.3687,
      "step": 24
    },
    {
      "epoch": 0.448681996634885,
      "grad_norm": 0.18849316239356995,
      "learning_rate": 5.327015646150716e-05,
      "loss": 10.368,
      "step": 25
    },
    {
      "epoch": 0.4666292765002804,
      "grad_norm": 0.18703168630599976,
      "learning_rate": 5e-05,
      "loss": 10.3683,
      "step": 26
    },
    {
      "epoch": 0.4666292765002804,
      "eval_loss": 10.368260383605957,
      "eval_runtime": 1.3921,
      "eval_samples_per_second": 270.092,
      "eval_steps_per_second": 67.523,
      "step": 26
    },
    {
      "epoch": 0.4845765563656758,
      "grad_norm": 0.1923580765724182,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 10.3676,
      "step": 27
    },
    {
      "epoch": 0.5025238362310712,
      "grad_norm": 0.17889352142810822,
      "learning_rate": 4.347369038899744e-05,
      "loss": 10.3673,
      "step": 28
    },
    {
      "epoch": 0.5204711160964667,
      "grad_norm": 0.19549714028835297,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 10.3691,
      "step": 29
    },
    {
      "epoch": 0.538418395961862,
      "grad_norm": 0.1798393279314041,
      "learning_rate": 3.705904774487396e-05,
      "loss": 10.3661,
      "step": 30
    },
    {
      "epoch": 0.5563656758272574,
      "grad_norm": 0.1796010434627533,
      "learning_rate": 3.392802673484193e-05,
      "loss": 10.3674,
      "step": 31
    },
    {
      "epoch": 0.5743129556926528,
      "grad_norm": 0.1846609115600586,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.369,
      "step": 32
    },
    {
      "epoch": 0.5922602355580482,
      "grad_norm": 0.1805039495229721,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 10.3641,
      "step": 33
    },
    {
      "epoch": 0.6102075154234436,
      "grad_norm": 0.18855346739292145,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3659,
      "step": 34
    },
    {
      "epoch": 0.628154795288839,
      "grad_norm": 0.1823464184999466,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 10.3658,
      "step": 35
    },
    {
      "epoch": 0.6461020751542345,
      "grad_norm": 0.17769189178943634,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 10.3716,
      "step": 36
    },
    {
      "epoch": 0.6640493550196298,
      "grad_norm": 0.20751889050006866,
      "learning_rate": 1.703270924499656e-05,
      "loss": 10.3651,
      "step": 37
    },
    {
      "epoch": 0.6819966348850253,
      "grad_norm": 0.20685072243213654,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3657,
      "step": 38
    },
    {
      "epoch": 0.6999439147504206,
      "grad_norm": 0.18949469923973083,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 10.3623,
      "step": 39
    },
    {
      "epoch": 0.6999439147504206,
      "eval_loss": 10.366268157958984,
      "eval_runtime": 1.3904,
      "eval_samples_per_second": 270.433,
      "eval_steps_per_second": 67.608,
      "step": 39
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 68882322161664.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}