{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 201,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 0.5843608975410461,
      "learning_rate": 7.058823529411765e-06,
      "loss": 1.8954,
      "step": 5
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 0.5829306244850159,
      "learning_rate": 1.5882352941176473e-05,
      "loss": 1.9066,
      "step": 10
    },
    {
      "epoch": 0.22556390977443608,
      "grad_norm": 0.4856240153312683,
      "learning_rate": 2.4705882352941174e-05,
      "loss": 1.8401,
      "step": 15
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.4811968505382538,
      "learning_rate": 2.9997072124327365e-05,
      "loss": 1.7568,
      "step": 20
    },
    {
      "epoch": 0.37593984962406013,
      "grad_norm": 0.4097922444343567,
      "learning_rate": 2.9964146648174195e-05,
      "loss": 1.7135,
      "step": 25
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 0.470956414937973,
      "learning_rate": 2.9894716440202756e-05,
      "loss": 1.663,
      "step": 30
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.46692782640457153,
      "learning_rate": 2.978895087399522e-05,
      "loss": 1.6288,
      "step": 35
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.4785483479499817,
      "learning_rate": 2.9647107962502205e-05,
      "loss": 1.5842,
      "step": 40
    },
    {
      "epoch": 0.6766917293233082,
      "grad_norm": 0.6028839349746704,
      "learning_rate": 2.946953372862538e-05,
      "loss": 1.5293,
      "step": 45
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 0.6228252649307251,
      "learning_rate": 2.9256661361101666e-05,
      "loss": 1.4678,
      "step": 50
    },
    {
      "epoch": 0.8270676691729323,
      "grad_norm": 0.6252663731575012,
      "learning_rate": 2.9009010157748082e-05,
      "loss": 1.4163,
      "step": 55
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.6308442950248718,
      "learning_rate": 2.8727184258645276e-05,
      "loss": 1.3788,
      "step": 60
    },
    {
      "epoch": 0.9774436090225563,
      "grad_norm": 0.7826851606369019,
      "learning_rate": 2.841187117235008e-05,
      "loss": 1.3428,
      "step": 65
    },
    {
      "epoch": 1.045112781954887,
      "grad_norm": 1.1327600479125977,
      "learning_rate": 2.8063840098732322e-05,
      "loss": 1.2124,
      "step": 70
    },
    {
      "epoch": 1.1203007518796992,
      "grad_norm": 1.054235577583313,
      "learning_rate": 2.768394005252739e-05,
      "loss": 1.1427,
      "step": 75
    },
    {
      "epoch": 1.1954887218045114,
      "grad_norm": 1.178091049194336,
      "learning_rate": 2.7273097792182038e-05,
      "loss": 1.1609,
      "step": 80
    },
    {
      "epoch": 1.2706766917293233,
      "grad_norm": 1.2119579315185547,
      "learning_rate": 2.6832315559045938e-05,
      "loss": 1.0633,
      "step": 85
    },
    {
      "epoch": 1.3458646616541352,
      "grad_norm": 1.0310696363449097,
      "learning_rate": 2.6362668632424302e-05,
      "loss": 1.0456,
      "step": 90
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 1.2468197345733643,
      "learning_rate": 2.586530270645584e-05,
      "loss": 1.0244,
      "step": 95
    },
    {
      "epoch": 1.4962406015037595,
      "grad_norm": 1.4294254779815674,
      "learning_rate": 2.534143109521518e-05,
      "loss": 0.989,
      "step": 100
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 1.7933841943740845,
      "learning_rate": 2.4792331772857826e-05,
      "loss": 0.9748,
      "step": 105
    },
    {
      "epoch": 1.6466165413533833,
      "grad_norm": 1.389110803604126,
      "learning_rate": 2.421934425602816e-05,
      "loss": 0.9058,
      "step": 110
    },
    {
      "epoch": 1.7218045112781954,
      "grad_norm": 1.226500153541565,
      "learning_rate": 2.3623866336135806e-05,
      "loss": 0.9148,
      "step": 115
    },
    {
      "epoch": 1.7969924812030076,
      "grad_norm": 1.363110899925232,
      "learning_rate": 2.3007350669471866e-05,
      "loss": 0.8737,
      "step": 120
    },
    {
      "epoch": 1.8721804511278195,
      "grad_norm": 1.4197795391082764,
      "learning_rate": 2.237130123348338e-05,
      "loss": 0.872,
      "step": 125
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 1.230918526649475,
      "learning_rate": 2.171726965785095e-05,
      "loss": 0.868,
      "step": 130
    },
    {
      "epoch": 2.0150375939849625,
      "grad_norm": 1.576594591140747,
      "learning_rate": 2.1046851439319587e-05,
      "loss": 0.7835,
      "step": 135
    },
    {
      "epoch": 2.090225563909774,
      "grad_norm": 1.4939583539962769,
      "learning_rate": 2.0361682049516837e-05,
      "loss": 0.6887,
      "step": 140
    },
    {
      "epoch": 2.1654135338345863,
      "grad_norm": 2.268726110458374,
      "learning_rate": 1.966343294525297e-05,
      "loss": 0.6642,
      "step": 145
    },
    {
      "epoch": 2.2406015037593985,
      "grad_norm": 1.6134439706802368,
      "learning_rate": 1.8953807491036015e-05,
      "loss": 0.6663,
      "step": 150
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 1.713577151298523,
      "learning_rate": 1.8234536803748657e-05,
      "loss": 0.6383,
      "step": 155
    },
    {
      "epoch": 2.3909774436090228,
      "grad_norm": 2.0117926597595215,
      "learning_rate": 1.7507375529623748e-05,
      "loss": 0.684,
      "step": 160
    },
    {
      "epoch": 2.4661654135338344,
      "grad_norm": 1.974694848060608,
      "learning_rate": 1.6774097563820486e-05,
      "loss": 0.6357,
      "step": 165
    },
    {
      "epoch": 2.5413533834586466,
      "grad_norm": 1.564803123474121,
      "learning_rate": 1.603649172304317e-05,
      "loss": 0.6048,
      "step": 170
    },
    {
      "epoch": 2.6165413533834587,
      "grad_norm": 2.4491689205169678,
      "learning_rate": 1.5296357381759197e-05,
      "loss": 0.586,
      "step": 175
    },
    {
      "epoch": 2.6917293233082704,
      "grad_norm": 1.540130615234375,
      "learning_rate": 1.4555500082661603e-05,
      "loss": 0.5548,
      "step": 180
    },
    {
      "epoch": 2.7669172932330826,
      "grad_norm": 1.8671647310256958,
      "learning_rate": 1.3815727132084322e-05,
      "loss": 0.581,
      "step": 185
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 2.341644525527954,
      "learning_rate": 1.3078843191115099e-05,
      "loss": 0.5204,
      "step": 190
    },
    {
      "epoch": 2.917293233082707,
      "grad_norm": 1.749429702758789,
      "learning_rate": 1.234664587316141e-05,
      "loss": 0.5241,
      "step": 195
    },
    {
      "epoch": 2.992481203007519,
      "grad_norm": 1.812374234199524,
      "learning_rate": 1.1620921358709076e-05,
      "loss": 0.5162,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 335,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.3198236595532595e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}