{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4579628286837385,
  "eval_steps": 999999,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00030530855245582567,
      "eval_loss": 1.4630959033966064,
      "eval_runtime": 17.8511,
      "eval_samples_per_second": 14.005,
      "eval_steps_per_second": 7.002,
      "step": 1
    },
    {
      "epoch": 0.015265427622791284,
      "grad_norm": 0.17761844396591187,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.7964,
      "step": 50
    },
    {
      "epoch": 0.030530855245582567,
      "grad_norm": 0.059007592499256134,
      "learning_rate": 9.992407582166581e-05,
      "loss": 0.1063,
      "step": 100
    },
    {
      "epoch": 0.04579628286837385,
      "grad_norm": 0.03449365496635437,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0977,
      "step": 150
    },
    {
      "epoch": 0.061061710491165135,
      "grad_norm": 0.020240124315023422,
      "learning_rate": 9.811340001546251e-05,
      "loss": 0.0966,
      "step": 200
    },
    {
      "epoch": 0.07632713811395642,
      "grad_norm": 0.0397501066327095,
      "learning_rate": 9.632470336074009e-05,
      "loss": 0.0967,
      "step": 250
    },
    {
      "epoch": 0.0915925657367477,
      "grad_norm": 0.0175618976354599,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0963,
      "step": 300
    },
    {
      "epoch": 0.10685799335953898,
      "grad_norm": 0.01892520859837532,
      "learning_rate": 9.108889076126226e-05,
      "loss": 0.0957,
      "step": 350
    },
    {
      "epoch": 0.12212342098233027,
      "grad_norm": 0.05521632730960846,
      "learning_rate": 8.770533048884482e-05,
      "loss": 0.0962,
      "step": 400
    },
    {
      "epoch": 0.13738884860512154,
      "grad_norm": 0.009517563506960869,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0963,
      "step": 450
    },
    {
      "epoch": 0.15265427622791283,
      "grad_norm": 0.011137745343148708,
      "learning_rate": 7.961176263324901e-05,
      "loss": 0.0959,
      "step": 500
    },
    {
      "epoch": 0.16791970385070412,
      "grad_norm": 0.009700442664325237,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0959,
      "step": 550
    },
    {
      "epoch": 0.1831851314734954,
      "grad_norm": 0.010401156730949879,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.096,
      "step": 600
    },
    {
      "epoch": 0.19845055909628667,
      "grad_norm": 0.008901902474462986,
      "learning_rate": 6.492574055008473e-05,
      "loss": 0.096,
      "step": 650
    },
    {
      "epoch": 0.21371598671907796,
      "grad_norm": 0.01319084782153368,
      "learning_rate": 5.958553159618693e-05,
      "loss": 0.0957,
      "step": 700
    },
    {
      "epoch": 0.22898141434186925,
      "grad_norm": 0.009528940543532372,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0952,
      "step": 750
    },
    {
      "epoch": 0.24424684196466054,
      "grad_norm": 0.012201801873743534,
      "learning_rate": 4.8622282881591906e-05,
      "loss": 0.0956,
      "step": 800
    },
    {
      "epoch": 0.2595122695874518,
      "grad_norm": 0.00497408676892519,
      "learning_rate": 4.3132322109079596e-05,
      "loss": 0.0958,
      "step": 850
    },
    {
      "epoch": 0.2747776972102431,
      "grad_norm": 0.009822960942983627,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0958,
      "step": 900
    },
    {
      "epoch": 0.2900431248330344,
      "grad_norm": 0.012425845488905907,
      "learning_rate": 3.2468122240362284e-05,
      "loss": 0.0957,
      "step": 950
    },
    {
      "epoch": 0.30530855245582567,
      "grad_norm": 0.007681730668991804,
      "learning_rate": 2.7423332084455544e-05,
      "loss": 0.0957,
      "step": 1000
    },
    {
      "epoch": 0.3205739800786169,
      "grad_norm": 0.00973996426910162,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0954,
      "step": 1050
    },
    {
      "epoch": 0.33583940770140824,
      "grad_norm": 0.010639767162501812,
      "learning_rate": 1.821381258950161e-05,
      "loss": 0.0951,
      "step": 1100
    },
    {
      "epoch": 0.3511048353241995,
      "grad_norm": 0.009966506622731686,
      "learning_rate": 1.4160874341577446e-05,
      "loss": 0.0964,
      "step": 1150
    },
    {
      "epoch": 0.3663702629469908,
      "grad_norm": 0.00854047853499651,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0957,
      "step": 1200
    },
    {
      "epoch": 0.3816356905697821,
      "grad_norm": 0.007982463575899601,
      "learning_rate": 7.404029558083653e-06,
      "loss": 0.096,
      "step": 1250
    },
    {
      "epoch": 0.39690111819257334,
      "grad_norm": 0.008494519628584385,
      "learning_rate": 4.782141965121128e-06,
      "loss": 0.0951,
      "step": 1300
    },
    {
      "epoch": 0.41216654581536466,
      "grad_norm": 0.007546895649284124,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0954,
      "step": 1350
    },
    {
      "epoch": 0.4274319734381559,
      "grad_norm": 0.010720642283558846,
      "learning_rate": 1.210180868628219e-06,
      "loss": 0.0954,
      "step": 1400
    },
    {
      "epoch": 0.44269740106094724,
      "grad_norm": 0.005871440749615431,
      "learning_rate": 3.034661341025258e-07,
      "loss": 0.0952,
      "step": 1450
    },
    {
      "epoch": 0.4579628286837385,
      "grad_norm": 0.008283548057079315,
      "learning_rate": 0.0,
      "loss": 0.0954,
      "step": 1500
    }
  ],
  "logging_steps": 50,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 750,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.756008094138368e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}