{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9975062344139651,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02493765586034913,
      "grad_norm": 0.04108215495944023,
      "learning_rate": 4.99229333433282e-05,
      "loss": 0.4044,
      "step": 5
    },
    {
      "epoch": 0.04987531172069826,
      "grad_norm": 0.025228893384337425,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 0.391,
      "step": 10
    },
    {
      "epoch": 0.07481296758104738,
      "grad_norm": 0.025317281484603882,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 0.3583,
      "step": 15
    },
    {
      "epoch": 0.09975062344139651,
      "grad_norm": 0.023856163024902344,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.3771,
      "step": 20
    },
    {
      "epoch": 0.12468827930174564,
      "grad_norm": 0.02556118369102478,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.3408,
      "step": 25
    },
    {
      "epoch": 0.14962593516209477,
      "grad_norm": 0.026844358071684837,
      "learning_rate": 4.72751631047092e-05,
      "loss": 0.3665,
      "step": 30
    },
    {
      "epoch": 0.1745635910224439,
      "grad_norm": 0.02702774479985237,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 0.3508,
      "step": 35
    },
    {
      "epoch": 0.19950124688279303,
      "grad_norm": 0.02752436138689518,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.3558,
      "step": 40
    },
    {
      "epoch": 0.22443890274314215,
      "grad_norm": 0.029124287888407707,
      "learning_rate": 4.401014914000078e-05,
      "loss": 0.3579,
      "step": 45
    },
    {
      "epoch": 0.24937655860349128,
      "grad_norm": 0.03660265728831291,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.3333,
      "step": 50
    },
    {
      "epoch": 0.2743142144638404,
      "grad_norm": 0.027973175048828125,
      "learning_rate": 4.123620120825459e-05,
      "loss": 0.3263,
      "step": 55
    },
    {
      "epoch": 0.29925187032418954,
      "grad_norm": 0.03005453571677208,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.3476,
      "step": 60
    },
    {
      "epoch": 0.32418952618453867,
      "grad_norm": 0.03571762889623642,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 0.3294,
      "step": 65
    },
    {
      "epoch": 0.3491271820448878,
      "grad_norm": 0.03382609412074089,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.356,
      "step": 70
    },
    {
      "epoch": 0.3740648379052369,
      "grad_norm": 0.03247227147221565,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.3304,
      "step": 75
    },
    {
      "epoch": 0.39900249376558605,
      "grad_norm": 0.03641534969210625,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.3436,
      "step": 80
    },
    {
      "epoch": 0.4239401496259352,
      "grad_norm": 0.03509656339883804,
      "learning_rate": 3.083613409639764e-05,
      "loss": 0.3388,
      "step": 85
    },
    {
      "epoch": 0.4488778054862843,
      "grad_norm": 0.03508240357041359,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 0.3367,
      "step": 90
    },
    {
      "epoch": 0.47381546134663344,
      "grad_norm": 0.04164772108197212,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 0.3561,
      "step": 95
    },
    {
      "epoch": 0.49875311720698257,
      "grad_norm": 0.03994197025895119,
      "learning_rate": 2.5e-05,
      "loss": 0.3182,
      "step": 100
    },
    {
      "epoch": 0.5236907730673317,
      "grad_norm": 0.038153909146785736,
      "learning_rate": 2.303852260680388e-05,
      "loss": 0.3331,
      "step": 105
    },
    {
      "epoch": 0.5486284289276808,
      "grad_norm": 0.03781621903181076,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.3383,
      "step": 110
    },
    {
      "epoch": 0.57356608478803,
      "grad_norm": 0.04167185723781586,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 0.3366,
      "step": 115
    },
    {
      "epoch": 0.5985037406483791,
      "grad_norm": 0.042504750192165375,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.3324,
      "step": 120
    },
    {
      "epoch": 0.6234413965087282,
      "grad_norm": 0.043039821088314056,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.303,
      "step": 125
    },
    {
      "epoch": 0.6483790523690773,
      "grad_norm": 0.04201623052358627,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 0.35,
      "step": 130
    },
    {
      "epoch": 0.6733167082294265,
      "grad_norm": 0.04364593327045441,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 0.331,
      "step": 135
    },
    {
      "epoch": 0.6982543640897756,
      "grad_norm": 0.04168755188584328,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.344,
      "step": 140
    },
    {
      "epoch": 0.7231920199501247,
      "grad_norm": 0.04454099014401436,
      "learning_rate": 8.763798791745411e-06,
      "loss": 0.3567,
      "step": 145
    },
    {
      "epoch": 0.7481296758104738,
      "grad_norm": 0.07072897255420685,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.3184,
      "step": 150
    },
    {
      "epoch": 0.773067331670823,
      "grad_norm": 0.04532039538025856,
      "learning_rate": 5.989850859999227e-06,
      "loss": 0.3279,
      "step": 155
    },
    {
      "epoch": 0.7980049875311721,
      "grad_norm": 0.04330899938941002,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.3372,
      "step": 160
    },
    {
      "epoch": 0.8229426433915212,
      "grad_norm": 0.04454395920038223,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 0.3553,
      "step": 165
    },
    {
      "epoch": 0.8478802992518704,
      "grad_norm": 0.05742543563246727,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 0.3361,
      "step": 170
    },
    {
      "epoch": 0.8728179551122195,
      "grad_norm": 0.04155350476503372,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.3335,
      "step": 175
    },
    {
      "epoch": 0.8977556109725686,
      "grad_norm": 0.04169079288840294,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.3425,
      "step": 180
    },
    {
      "epoch": 0.9226932668329177,
      "grad_norm": 0.04245175048708916,
      "learning_rate": 6.907519900580861e-07,
      "loss": 0.3247,
      "step": 185
    },
    {
      "epoch": 0.9476309226932669,
      "grad_norm": 0.03987717628479004,
      "learning_rate": 3.077914851215585e-07,
      "loss": 0.3314,
      "step": 190
    },
    {
      "epoch": 0.972568578553616,
      "grad_norm": 0.11724965274333954,
      "learning_rate": 7.706665667180091e-08,
      "loss": 0.3354,
      "step": 195
    },
    {
      "epoch": 0.9975062344139651,
      "grad_norm": 0.04020114243030548,
      "learning_rate": 0.0,
      "loss": 0.3413,
      "step": 200
    },
    {
      "epoch": 0.9975062344139651,
      "step": 200,
      "total_flos": 3.3406622246696387e+18,
      "train_loss": 0.3431886351108551,
      "train_runtime": 6744.2555,
      "train_samples_per_second": 5.708,
      "train_steps_per_second": 0.03
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3406622246696387e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}