{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 587,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017035775127768313,
      "grad_norm": 1.6640625,
      "learning_rate": 5e-06,
      "loss": 0.3494,
      "step": 10
    },
    {
      "epoch": 0.034071550255536626,
      "grad_norm": 1.203125,
      "learning_rate": 1e-05,
      "loss": 0.3494,
      "step": 20
    },
    {
      "epoch": 0.05110732538330494,
      "grad_norm": 1.2421875,
      "learning_rate": 1.5e-05,
      "loss": 0.3523,
      "step": 30
    },
    {
      "epoch": 0.06814310051107325,
      "grad_norm": 1.53125,
      "learning_rate": 2e-05,
      "loss": 0.3428,
      "step": 40
    },
    {
      "epoch": 0.08517887563884156,
      "grad_norm": 1.3046875,
      "learning_rate": 2.5e-05,
      "loss": 0.359,
      "step": 50
    },
    {
      "epoch": 0.08517887563884156,
      "eval_loss": 0.3472045063972473,
      "eval_runtime": 44.9607,
      "eval_samples_per_second": 3.27,
      "eval_steps_per_second": 3.27,
      "step": 50
    },
    {
      "epoch": 0.10221465076660988,
      "grad_norm": 1.21875,
      "learning_rate": 3e-05,
      "loss": 0.3494,
      "step": 60
    },
    {
      "epoch": 0.11925042589437819,
      "grad_norm": 1.2734375,
      "learning_rate": 3.5e-05,
      "loss": 0.3527,
      "step": 70
    },
    {
      "epoch": 0.1362862010221465,
      "grad_norm": 0.64453125,
      "learning_rate": 4e-05,
      "loss": 0.349,
      "step": 80
    },
    {
      "epoch": 0.15332197614991483,
      "grad_norm": 1.0703125,
      "learning_rate": 4.5e-05,
      "loss": 0.3432,
      "step": 90
    },
    {
      "epoch": 0.17035775127768313,
      "grad_norm": 1.40625,
      "learning_rate": 5e-05,
      "loss": 0.3252,
      "step": 100
    },
    {
      "epoch": 0.17035775127768313,
      "eval_loss": 0.35169535875320435,
      "eval_runtime": 45.0372,
      "eval_samples_per_second": 3.264,
      "eval_steps_per_second": 3.264,
      "step": 100
    },
    {
      "epoch": 0.18739352640545145,
      "grad_norm": 1.2890625,
      "learning_rate": 4.897330595482547e-05,
      "loss": 0.3191,
      "step": 110
    },
    {
      "epoch": 0.20442930153321975,
      "grad_norm": 2.28125,
      "learning_rate": 4.7946611909650925e-05,
      "loss": 0.289,
      "step": 120
    },
    {
      "epoch": 0.22146507666098808,
      "grad_norm": 3.765625,
      "learning_rate": 4.691991786447639e-05,
      "loss": 0.2395,
      "step": 130
    },
    {
      "epoch": 0.23850085178875638,
      "grad_norm": 9.5625,
      "learning_rate": 4.5893223819301853e-05,
      "loss": 0.3263,
      "step": 140
    },
    {
      "epoch": 0.2555366269165247,
      "grad_norm": 4.84375,
      "learning_rate": 4.486652977412731e-05,
      "loss": 0.1648,
      "step": 150
    },
    {
      "epoch": 0.2555366269165247,
      "eval_loss": 0.611720085144043,
      "eval_runtime": 44.8864,
      "eval_samples_per_second": 3.275,
      "eval_steps_per_second": 3.275,
      "step": 150
    },
    {
      "epoch": 0.272572402044293,
      "grad_norm": 21.125,
      "learning_rate": 4.383983572895277e-05,
      "loss": 0.163,
      "step": 160
    },
    {
      "epoch": 0.28960817717206133,
      "grad_norm": 7.25,
      "learning_rate": 4.281314168377823e-05,
      "loss": 0.4368,
      "step": 170
    },
    {
      "epoch": 0.30664395229982966,
      "grad_norm": 29.625,
      "learning_rate": 4.17864476386037e-05,
      "loss": 0.2398,
      "step": 180
    },
    {
      "epoch": 0.32367972742759793,
      "grad_norm": 15.3125,
      "learning_rate": 4.075975359342916e-05,
      "loss": 0.1639,
      "step": 190
    },
    {
      "epoch": 0.34071550255536626,
      "grad_norm": 0.119140625,
      "learning_rate": 3.973305954825462e-05,
      "loss": 0.2869,
      "step": 200
    },
    {
      "epoch": 0.34071550255536626,
      "eval_loss": 0.6622754335403442,
      "eval_runtime": 44.5126,
      "eval_samples_per_second": 3.302,
      "eval_steps_per_second": 3.302,
      "step": 200
    },
    {
      "epoch": 0.3577512776831346,
      "grad_norm": 0.021484375,
      "learning_rate": 3.8706365503080084e-05,
      "loss": 0.1419,
      "step": 210
    },
    {
      "epoch": 0.3747870528109029,
      "grad_norm": 9.6875,
      "learning_rate": 3.767967145790555e-05,
      "loss": 0.1224,
      "step": 220
    },
    {
      "epoch": 0.39182282793867124,
      "grad_norm": 0.0693359375,
      "learning_rate": 3.6652977412731007e-05,
      "loss": 0.3138,
      "step": 230
    },
    {
      "epoch": 0.4088586030664395,
      "grad_norm": 6.8125,
      "learning_rate": 3.562628336755647e-05,
      "loss": 0.1766,
      "step": 240
    },
    {
      "epoch": 0.42589437819420783,
      "grad_norm": 0.07421875,
      "learning_rate": 3.459958932238193e-05,
      "loss": 0.1243,
      "step": 250
    },
    {
      "epoch": 0.42589437819420783,
      "eval_loss": 0.6063656210899353,
      "eval_runtime": 43.927,
      "eval_samples_per_second": 3.346,
      "eval_steps_per_second": 3.346,
      "step": 250
    },
    {
      "epoch": 0.44293015332197616,
      "grad_norm": 7.59375,
      "learning_rate": 3.357289527720739e-05,
      "loss": 0.1272,
      "step": 260
    },
    {
      "epoch": 0.4599659284497445,
      "grad_norm": 28.375,
      "learning_rate": 3.254620123203286e-05,
      "loss": 0.4251,
      "step": 270
    },
    {
      "epoch": 0.47700170357751276,
      "grad_norm": 0.462890625,
      "learning_rate": 3.1519507186858315e-05,
      "loss": 0.4472,
      "step": 280
    },
    {
      "epoch": 0.4940374787052811,
      "grad_norm": 40.25,
      "learning_rate": 3.049281314168378e-05,
      "loss": 0.4209,
      "step": 290
    },
    {
      "epoch": 0.5110732538330494,
      "grad_norm": 0.031494140625,
      "learning_rate": 2.9466119096509244e-05,
      "loss": 0.1857,
      "step": 300
    },
    {
      "epoch": 0.5110732538330494,
      "eval_loss": 0.7174944281578064,
      "eval_runtime": 43.835,
      "eval_samples_per_second": 3.353,
      "eval_steps_per_second": 3.353,
      "step": 300
    },
    {
      "epoch": 0.5281090289608177,
      "grad_norm": 3.015625,
      "learning_rate": 2.8439425051334705e-05,
      "loss": 0.2324,
      "step": 310
    },
    {
      "epoch": 0.545144804088586,
      "grad_norm": 0.0184326171875,
      "learning_rate": 2.7412731006160163e-05,
      "loss": 0.1289,
      "step": 320
    },
    {
      "epoch": 0.5621805792163543,
      "grad_norm": 0.1201171875,
      "learning_rate": 2.6386036960985628e-05,
      "loss": 0.1295,
      "step": 330
    },
    {
      "epoch": 0.5792163543441227,
      "grad_norm": 0.005859375,
      "learning_rate": 2.5359342915811092e-05,
      "loss": 0.393,
      "step": 340
    },
    {
      "epoch": 0.596252129471891,
      "grad_norm": 23.375,
      "learning_rate": 2.433264887063655e-05,
      "loss": 0.3171,
      "step": 350
    },
    {
      "epoch": 0.596252129471891,
      "eval_loss": 0.7911351919174194,
      "eval_runtime": 43.7143,
      "eval_samples_per_second": 3.363,
      "eval_steps_per_second": 3.363,
      "step": 350
    },
    {
      "epoch": 0.6132879045996593,
      "grad_norm": 0.0242919921875,
      "learning_rate": 2.3305954825462014e-05,
      "loss": 0.535,
      "step": 360
    },
    {
      "epoch": 0.6303236797274276,
      "grad_norm": 0.50390625,
      "learning_rate": 2.2279260780287475e-05,
      "loss": 0.2197,
      "step": 370
    },
    {
      "epoch": 0.6473594548551959,
      "grad_norm": 2.53125,
      "learning_rate": 2.125256673511294e-05,
      "loss": 0.3187,
      "step": 380
    },
    {
      "epoch": 0.6643952299829642,
      "grad_norm": 7.8125,
      "learning_rate": 2.02258726899384e-05,
      "loss": 0.1459,
      "step": 390
    },
    {
      "epoch": 0.6814310051107325,
      "grad_norm": 39.25,
      "learning_rate": 1.919917864476386e-05,
      "loss": 0.5212,
      "step": 400
    },
    {
      "epoch": 0.6814310051107325,
      "eval_loss": 0.7614322304725647,
      "eval_runtime": 43.7037,
      "eval_samples_per_second": 3.364,
      "eval_steps_per_second": 3.364,
      "step": 400
    },
    {
      "epoch": 0.6984667802385008,
      "grad_norm": 3.640625,
      "learning_rate": 1.8172484599589323e-05,
      "loss": 0.1773,
      "step": 410
    },
    {
      "epoch": 0.7155025553662692,
      "grad_norm": 0.005645751953125,
      "learning_rate": 1.7145790554414784e-05,
      "loss": 0.2599,
      "step": 420
    },
    {
      "epoch": 0.7325383304940375,
      "grad_norm": 30.5,
      "learning_rate": 1.611909650924025e-05,
      "loss": 0.3468,
      "step": 430
    },
    {
      "epoch": 0.7495741056218058,
      "grad_norm": 5.5,
      "learning_rate": 1.5092402464065708e-05,
      "loss": 0.2754,
      "step": 440
    },
    {
      "epoch": 0.7666098807495741,
      "grad_norm": 32.0,
      "learning_rate": 1.406570841889117e-05,
      "loss": 0.3287,
      "step": 450
    },
    {
      "epoch": 0.7666098807495741,
      "eval_loss": 0.8178677558898926,
      "eval_runtime": 43.7442,
      "eval_samples_per_second": 3.36,
      "eval_steps_per_second": 3.36,
      "step": 450
    },
    {
      "epoch": 0.7836456558773425,
      "grad_norm": 3.0,
      "learning_rate": 1.3039014373716632e-05,
      "loss": 0.1921,
      "step": 460
    },
    {
      "epoch": 0.8006814310051107,
      "grad_norm": 28.125,
      "learning_rate": 1.2012320328542096e-05,
      "loss": 0.4395,
      "step": 470
    },
    {
      "epoch": 0.817717206132879,
      "grad_norm": 4.25,
      "learning_rate": 1.0985626283367557e-05,
      "loss": 0.2133,
      "step": 480
    },
    {
      "epoch": 0.8347529812606473,
      "grad_norm": 7.25,
      "learning_rate": 9.95893223819302e-06,
      "loss": 0.4362,
      "step": 490
    },
    {
      "epoch": 0.8517887563884157,
      "grad_norm": 5.78125,
      "learning_rate": 8.932238193018481e-06,
      "loss": 0.418,
      "step": 500
    },
    {
      "epoch": 0.8517887563884157,
      "eval_loss": 0.8019587993621826,
      "eval_runtime": 43.8445,
      "eval_samples_per_second": 3.353,
      "eval_steps_per_second": 3.353,
      "step": 500
    },
    {
      "epoch": 0.868824531516184,
      "grad_norm": 5.84375,
      "learning_rate": 7.905544147843944e-06,
      "loss": 0.236,
      "step": 510
    },
    {
      "epoch": 0.8858603066439523,
      "grad_norm": 9.0625,
      "learning_rate": 6.878850102669406e-06,
      "loss": 0.5388,
      "step": 520
    },
    {
      "epoch": 0.9028960817717206,
      "grad_norm": 0.00543212890625,
      "learning_rate": 5.852156057494867e-06,
      "loss": 0.0928,
      "step": 530
    },
    {
      "epoch": 0.919931856899489,
      "grad_norm": 10.9375,
      "learning_rate": 4.825462012320329e-06,
      "loss": 0.1343,
      "step": 540
    },
    {
      "epoch": 0.9369676320272572,
      "grad_norm": 6.59375,
      "learning_rate": 3.7987679671457908e-06,
      "loss": 0.099,
      "step": 550
    },
    {
      "epoch": 0.9369676320272572,
      "eval_loss": 0.8314433097839355,
      "eval_runtime": 43.8265,
      "eval_samples_per_second": 3.354,
      "eval_steps_per_second": 3.354,
      "step": 550
    },
    {
      "epoch": 0.9540034071550255,
      "grad_norm": 32.75,
      "learning_rate": 2.7720739219712527e-06,
      "loss": 0.1544,
      "step": 560
    },
    {
      "epoch": 0.9710391822827938,
      "grad_norm": 22.75,
      "learning_rate": 1.7453798767967144e-06,
      "loss": 0.2434,
      "step": 570
    },
    {
      "epoch": 0.9880749574105622,
      "grad_norm": 0.33203125,
      "learning_rate": 7.186858316221766e-07,
      "loss": 0.1046,
      "step": 580
    }
  ],
  "logging_steps": 10,
  "max_steps": 587,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8836792572744000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}