{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.875912408759124,
  "eval_steps": 1000,
  "global_step": 51,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.058394160583941604,
      "grad_norm": 4.656690719780717,
      "learning_rate": 0.0,
      "loss": 0.4427,
      "step": 1
    },
    {
      "epoch": 0.11678832116788321,
      "grad_norm": 4.86023891396574,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 0.4479,
      "step": 2
    },
    {
      "epoch": 0.17518248175182483,
      "grad_norm": 4.720432036194861,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.438,
      "step": 3
    },
    {
      "epoch": 0.23357664233576642,
      "grad_norm": 2.7065388639758448,
      "learning_rate": 5e-06,
      "loss": 0.4169,
      "step": 4
    },
    {
      "epoch": 0.291970802919708,
      "grad_norm": 2.1869690387653904,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.4031,
      "step": 5
    },
    {
      "epoch": 0.35036496350364965,
      "grad_norm": 1.6374910771466962,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.3685,
      "step": 6
    },
    {
      "epoch": 0.40875912408759124,
      "grad_norm": 1.5026227694746652,
      "learning_rate": 1e-05,
      "loss": 0.3638,
      "step": 7
    },
    {
      "epoch": 0.46715328467153283,
      "grad_norm": 1.7874379044083826,
      "learning_rate": 9.987820251299121e-06,
      "loss": 0.3384,
      "step": 8
    },
    {
      "epoch": 0.5255474452554745,
      "grad_norm": 1.399545646496995,
      "learning_rate": 9.951340343707852e-06,
      "loss": 0.3199,
      "step": 9
    },
    {
      "epoch": 0.583941605839416,
      "grad_norm": 0.9591867357924391,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.3052,
      "step": 10
    },
    {
      "epoch": 0.6423357664233577,
      "grad_norm": 1.1005637398680819,
      "learning_rate": 9.806308479691595e-06,
      "loss": 0.3048,
      "step": 11
    },
    {
      "epoch": 0.7007299270072993,
      "grad_norm": 1.0830814869796386,
      "learning_rate": 9.698463103929542e-06,
      "loss": 0.3054,
      "step": 12
    },
    {
      "epoch": 0.7591240875912408,
      "grad_norm": 0.6865164477755549,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.2981,
      "step": 13
    },
    {
      "epoch": 0.8175182481751825,
      "grad_norm": 0.5516228834269103,
      "learning_rate": 9.414737964294636e-06,
      "loss": 0.2911,
      "step": 14
    },
    {
      "epoch": 0.8759124087591241,
      "grad_norm": 0.5820793130011475,
      "learning_rate": 9.24024048078213e-06,
      "loss": 0.2853,
      "step": 15
    },
    {
      "epoch": 0.9343065693430657,
      "grad_norm": 0.4932271006804814,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.2869,
      "step": 16
    },
    {
      "epoch": 0.9927007299270073,
      "grad_norm": 0.4055326985718036,
      "learning_rate": 8.83022221559489e-06,
      "loss": 0.2839,
      "step": 17
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4055326985718036,
      "learning_rate": 8.596699001693257e-06,
      "loss": 0.2804,
      "step": 18
    },
    {
      "epoch": 1.0583941605839415,
      "grad_norm": 0.7337766666428717,
      "learning_rate": 8.345653031794292e-06,
      "loss": 0.2726,
      "step": 19
    },
    {
      "epoch": 1.1167883211678833,
      "grad_norm": 0.3691176180981217,
      "learning_rate": 8.078307376628292e-06,
      "loss": 0.276,
      "step": 20
    },
    {
      "epoch": 1.1751824817518248,
      "grad_norm": 0.344408713464,
      "learning_rate": 7.795964517353734e-06,
      "loss": 0.2691,
      "step": 21
    },
    {
      "epoch": 1.2335766423357664,
      "grad_norm": 0.33587123887427156,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.2708,
      "step": 22
    },
    {
      "epoch": 1.2919708029197081,
      "grad_norm": 0.36312692209169634,
      "learning_rate": 7.191855733945388e-06,
      "loss": 0.2722,
      "step": 23
    },
    {
      "epoch": 1.3503649635036497,
      "grad_norm": 0.3467493765316541,
      "learning_rate": 6.873032967079562e-06,
      "loss": 0.2684,
      "step": 24
    },
    {
      "epoch": 1.4087591240875912,
      "grad_norm": 0.29985014243285585,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.2644,
      "step": 25
    },
    {
      "epoch": 1.4671532846715327,
      "grad_norm": 0.3009900653944404,
      "learning_rate": 6.209609477998339e-06,
      "loss": 0.2688,
      "step": 26
    },
    {
      "epoch": 1.5255474452554745,
      "grad_norm": 0.3055997904476839,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.269,
      "step": 27
    },
    {
      "epoch": 1.583941605839416,
      "grad_norm": 0.30028028239827603,
      "learning_rate": 5.522642316338268e-06,
      "loss": 0.2656,
      "step": 28
    },
    {
      "epoch": 1.6423357664233578,
      "grad_norm": 0.2763150426486829,
      "learning_rate": 5.174497483512506e-06,
      "loss": 0.2603,
      "step": 29
    },
    {
      "epoch": 1.7007299270072993,
      "grad_norm": 0.2701531414864163,
      "learning_rate": 4.825502516487497e-06,
      "loss": 0.2624,
      "step": 30
    },
    {
      "epoch": 1.7591240875912408,
      "grad_norm": 0.27810619458497565,
      "learning_rate": 4.477357683661734e-06,
      "loss": 0.2587,
      "step": 31
    },
    {
      "epoch": 1.8175182481751824,
      "grad_norm": 0.27117315958229854,
      "learning_rate": 4.131759111665349e-06,
      "loss": 0.2607,
      "step": 32
    },
    {
      "epoch": 1.8759124087591241,
      "grad_norm": 0.29281124774062617,
      "learning_rate": 3.790390522001662e-06,
      "loss": 0.2665,
      "step": 33
    },
    {
      "epoch": 1.9343065693430657,
      "grad_norm": 0.2592120956342657,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.2535,
      "step": 34
    },
    {
      "epoch": 1.9927007299270074,
      "grad_norm": 0.2553199343344583,
      "learning_rate": 3.12696703292044e-06,
      "loss": 0.2607,
      "step": 35
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2553199343344583,
      "learning_rate": 2.8081442660546126e-06,
      "loss": 0.294,
      "step": 36
    },
    {
      "epoch": 2.0583941605839415,
      "grad_norm": 0.5638081142653227,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.2559,
      "step": 37
    },
    {
      "epoch": 2.116788321167883,
      "grad_norm": 0.2580615941336081,
      "learning_rate": 2.204035482646267e-06,
      "loss": 0.2565,
      "step": 38
    },
    {
      "epoch": 2.1751824817518246,
      "grad_norm": 0.25128786187971297,
      "learning_rate": 1.9216926233717087e-06,
      "loss": 0.2607,
      "step": 39
    },
    {
      "epoch": 2.2335766423357666,
      "grad_norm": 0.25306085564609393,
      "learning_rate": 1.6543469682057105e-06,
      "loss": 0.2563,
      "step": 40
    },
    {
      "epoch": 2.291970802919708,
      "grad_norm": 0.24846670752435976,
      "learning_rate": 1.4033009983067454e-06,
      "loss": 0.2532,
      "step": 41
    },
    {
      "epoch": 2.3503649635036497,
      "grad_norm": 0.2580515653108336,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.2576,
      "step": 42
    },
    {
      "epoch": 2.408759124087591,
      "grad_norm": 0.2530494375387585,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.2584,
      "step": 43
    },
    {
      "epoch": 2.4671532846715327,
      "grad_norm": 0.25393938765908214,
      "learning_rate": 7.597595192178702e-07,
      "loss": 0.2517,
      "step": 44
    },
    {
      "epoch": 2.5255474452554747,
      "grad_norm": 0.25923776188517333,
      "learning_rate": 5.852620357053651e-07,
      "loss": 0.255,
      "step": 45
    },
    {
      "epoch": 2.5839416058394162,
      "grad_norm": 0.24849467891024976,
      "learning_rate": 4.322727117869951e-07,
      "loss": 0.2584,
      "step": 46
    },
    {
      "epoch": 2.6423357664233578,
      "grad_norm": 0.24200618380386005,
      "learning_rate": 3.015368960704584e-07,
      "loss": 0.258,
      "step": 47
    },
    {
      "epoch": 2.7007299270072993,
      "grad_norm": 0.2351400359518212,
      "learning_rate": 1.9369152030840553e-07,
      "loss": 0.2593,
      "step": 48
    },
    {
      "epoch": 2.759124087591241,
      "grad_norm": 0.24907108276269765,
      "learning_rate": 1.0926199633097156e-07,
      "loss": 0.2515,
      "step": 49
    },
    {
      "epoch": 2.8175182481751824,
      "grad_norm": 0.2485312703705758,
      "learning_rate": 4.865965629214819e-08,
      "loss": 0.2464,
      "step": 50
    },
    {
      "epoch": 2.875912408759124,
      "grad_norm": 0.25234193575090264,
      "learning_rate": 1.2179748700879013e-08,
      "loss": 0.2502,
      "step": 51
    }
  ],
  "logging_steps": 1,
  "max_steps": 51,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 121368125374464.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}