{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1813236627379873,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003626473254759746,
      "eval_loss": 10.378419876098633,
      "eval_runtime": 3.4259,
      "eval_samples_per_second": 286.053,
      "eval_steps_per_second": 35.903,
      "step": 1
    },
    {
      "epoch": 0.010879419764279238,
      "grad_norm": 0.028440434485673904,
      "learning_rate": 3e-05,
      "loss": 10.3783,
      "step": 3
    },
    {
      "epoch": 0.01813236627379873,
      "eval_loss": 10.378182411193848,
      "eval_runtime": 3.4267,
      "eval_samples_per_second": 285.988,
      "eval_steps_per_second": 35.894,
      "step": 5
    },
    {
      "epoch": 0.021758839528558477,
      "grad_norm": 0.029924781993031502,
      "learning_rate": 6e-05,
      "loss": 10.3786,
      "step": 6
    },
    {
      "epoch": 0.032638259292837715,
      "grad_norm": 0.032576046884059906,
      "learning_rate": 9e-05,
      "loss": 10.3787,
      "step": 9
    },
    {
      "epoch": 0.03626473254759746,
      "eval_loss": 10.377327919006348,
      "eval_runtime": 3.4705,
      "eval_samples_per_second": 282.383,
      "eval_steps_per_second": 35.442,
      "step": 10
    },
    {
      "epoch": 0.043517679057116954,
      "grad_norm": 0.033237360417842865,
      "learning_rate": 0.00012,
      "loss": 10.3777,
      "step": 12
    },
    {
      "epoch": 0.05439709882139619,
      "grad_norm": 0.037652939558029175,
      "learning_rate": 0.00015000000000000001,
      "loss": 10.3763,
      "step": 15
    },
    {
      "epoch": 0.05439709882139619,
      "eval_loss": 10.37564754486084,
      "eval_runtime": 3.4616,
      "eval_samples_per_second": 283.109,
      "eval_steps_per_second": 35.533,
      "step": 15
    },
    {
      "epoch": 0.06527651858567543,
      "grad_norm": 0.04887213185429573,
      "learning_rate": 0.00018,
      "loss": 10.3747,
      "step": 18
    },
    {
      "epoch": 0.07252946509519492,
      "eval_loss": 10.372203826904297,
      "eval_runtime": 3.4694,
      "eval_samples_per_second": 282.472,
      "eval_steps_per_second": 35.453,
      "step": 20
    },
    {
      "epoch": 0.07615593834995467,
      "grad_norm": 0.07486271858215332,
      "learning_rate": 0.00019945218953682734,
      "loss": 10.3732,
      "step": 21
    },
    {
      "epoch": 0.08703535811423391,
      "grad_norm": 0.10773558914661407,
      "learning_rate": 0.0001913545457642601,
      "loss": 10.3699,
      "step": 24
    },
    {
      "epoch": 0.09066183136899365,
      "eval_loss": 10.365472793579102,
      "eval_runtime": 3.4645,
      "eval_samples_per_second": 282.866,
      "eval_steps_per_second": 35.503,
      "step": 25
    },
    {
      "epoch": 0.09791477787851315,
      "grad_norm": 0.10963417589664459,
      "learning_rate": 0.00017431448254773944,
      "loss": 10.3655,
      "step": 27
    },
    {
      "epoch": 0.10879419764279238,
      "grad_norm": 0.09174247831106186,
      "learning_rate": 0.00015000000000000001,
      "loss": 10.3617,
      "step": 30
    },
    {
      "epoch": 0.10879419764279238,
      "eval_loss": 10.359057426452637,
      "eval_runtime": 3.4524,
      "eval_samples_per_second": 283.857,
      "eval_steps_per_second": 35.627,
      "step": 30
    },
    {
      "epoch": 0.11967361740707162,
      "grad_norm": 0.06661375612020493,
      "learning_rate": 0.00012079116908177593,
      "loss": 10.3586,
      "step": 33
    },
    {
      "epoch": 0.12692656391659113,
      "eval_loss": 10.356401443481445,
      "eval_runtime": 3.4528,
      "eval_samples_per_second": 283.831,
      "eval_steps_per_second": 35.624,
      "step": 35
    },
    {
      "epoch": 0.13055303717135086,
      "grad_norm": 0.06876756995916367,
      "learning_rate": 8.954715367323468e-05,
      "loss": 10.357,
      "step": 36
    },
    {
      "epoch": 0.1414324569356301,
      "grad_norm": 0.051274798810482025,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 10.356,
      "step": 39
    },
    {
      "epoch": 0.14505893019038985,
      "eval_loss": 10.355536460876465,
      "eval_runtime": 3.4523,
      "eval_samples_per_second": 283.867,
      "eval_steps_per_second": 35.628,
      "step": 40
    },
    {
      "epoch": 0.15231187669990934,
      "grad_norm": 0.03581469506025314,
      "learning_rate": 3.308693936411421e-05,
      "loss": 10.3554,
      "step": 42
    },
    {
      "epoch": 0.1631912964641886,
      "grad_norm": 0.038194689899683,
      "learning_rate": 1.339745962155613e-05,
      "loss": 10.3555,
      "step": 45
    },
    {
      "epoch": 0.1631912964641886,
      "eval_loss": 10.355265617370605,
      "eval_runtime": 3.4538,
      "eval_samples_per_second": 283.743,
      "eval_steps_per_second": 35.613,
      "step": 45
    },
    {
      "epoch": 0.17407071622846781,
      "grad_norm": 0.037530913949012756,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 10.3563,
      "step": 48
    },
    {
      "epoch": 0.1813236627379873,
      "eval_loss": 10.355225563049316,
      "eval_runtime": 3.4386,
      "eval_samples_per_second": 285.001,
      "eval_steps_per_second": 35.77,
      "step": 50
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 11155066060800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}