{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 723,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04149377593360996,
      "grad_norm": 0.564109206199646,
      "learning_rate": 9e-05,
      "loss": 2.028769111633301,
      "step": 10
    },
    {
      "epoch": 0.08298755186721991,
      "grad_norm": 0.3017788231372833,
      "learning_rate": 0.00019,
      "loss": 1.3911235809326172,
      "step": 20
    },
    {
      "epoch": 0.12448132780082988,
      "grad_norm": 0.19067230820655823,
      "learning_rate": 0.0001999191303479577,
      "loss": 0.9321062088012695,
      "step": 30
    },
    {
      "epoch": 0.16597510373443983,
      "grad_norm": 0.16072602570056915,
      "learning_rate": 0.00019963974885425266,
      "loss": 0.7978806972503663,
      "step": 40
    },
    {
      "epoch": 0.2074688796680498,
      "grad_norm": 0.24699056148529053,
      "learning_rate": 0.00019916141484135297,
      "loss": 0.7692349433898926,
      "step": 50
    },
    {
      "epoch": 0.24896265560165975,
      "grad_norm": 0.19357353448867798,
      "learning_rate": 0.0001984850834075801,
      "loss": 0.6707598686218261,
      "step": 60
    },
    {
      "epoch": 0.29045643153526973,
      "grad_norm": 0.2131027728319168,
      "learning_rate": 0.00019761210499634753,
      "loss": 0.6942025184631347,
      "step": 70
    },
    {
      "epoch": 0.33195020746887965,
      "grad_norm": 0.1985936164855957,
      "learning_rate": 0.00019654422269970546,
      "loss": 0.6449690818786621,
      "step": 80
    },
    {
      "epoch": 0.37344398340248963,
      "grad_norm": 0.25582998991012573,
      "learning_rate": 0.00019528356877787702,
      "loss": 0.6622867107391357,
      "step": 90
    },
    {
      "epoch": 0.4149377593360996,
      "grad_norm": 0.30684924125671387,
      "learning_rate": 0.0001938326604017349,
      "loss": 0.5823399066925049,
      "step": 100
    },
    {
      "epoch": 0.45643153526970953,
      "grad_norm": 0.2845880687236786,
      "learning_rate": 0.00019219439462672008,
      "loss": 0.6002421855926514,
      "step": 110
    },
    {
      "epoch": 0.4979253112033195,
      "grad_norm": 0.25951942801475525,
      "learning_rate": 0.00019037204260823786,
      "loss": 0.5823984622955323,
      "step": 120
    },
    {
      "epoch": 0.5394190871369294,
      "grad_norm": 0.34280383586883545,
      "learning_rate": 0.0001883692430700818,
      "loss": 0.5439570426940918,
      "step": 130
    },
    {
      "epoch": 0.5809128630705395,
      "grad_norm": 0.2681763470172882,
      "learning_rate": 0.0001861899950389269,
      "loss": 0.47908792495727537,
      "step": 140
    },
    {
      "epoch": 0.6224066390041494,
      "grad_norm": 0.32833316922187805,
      "learning_rate": 0.00018383864985939942,
      "loss": 0.4661055088043213,
      "step": 150
    },
    {
      "epoch": 0.6639004149377593,
      "grad_norm": 0.2559301257133484,
      "learning_rate": 0.00018131990250566733,
      "loss": 0.46738500595092775,
      "step": 160
    },
    {
      "epoch": 0.7053941908713693,
      "grad_norm": 0.3888081908226013,
      "learning_rate": 0.00017863878220689868,
      "loss": 0.4815069198608398,
      "step": 170
    },
    {
      "epoch": 0.7468879668049793,
      "grad_norm": 0.3049161732196808,
      "learning_rate": 0.00017580064240530743,
      "loss": 0.43445429801940916,
      "step": 180
    },
    {
      "epoch": 0.7883817427385892,
      "grad_norm": 0.2690380811691284,
      "learning_rate": 0.00017281115006683687,
      "loss": 0.45731124877929685,
      "step": 190
    },
    {
      "epoch": 0.8298755186721992,
      "grad_norm": 0.33490434288978577,
      "learning_rate": 0.00016967627436582445,
      "loss": 0.4687365531921387,
      "step": 200
    },
    {
      "epoch": 0.8713692946058091,
      "grad_norm": 0.24168512225151062,
      "learning_rate": 0.00016640227476624164,
      "loss": 0.4687990188598633,
      "step": 210
    },
    {
      "epoch": 0.9128630705394191,
      "grad_norm": 0.34385180473327637,
      "learning_rate": 0.00016299568852330703,
      "loss": 0.3935831546783447,
      "step": 220
    },
    {
      "epoch": 0.9543568464730291,
      "grad_norm": 0.23051096498966217,
      "learning_rate": 0.00015946331763042867,
      "loss": 0.4378076076507568,
      "step": 230
    },
    {
      "epoch": 0.995850622406639,
      "grad_norm": 0.2851276397705078,
      "learning_rate": 0.0001558122152375387,
      "loss": 0.38995463848114015,
      "step": 240
    },
    {
      "epoch": 1.037344398340249,
      "grad_norm": 0.27530986070632935,
      "learning_rate": 0.0001520496715679391,
      "loss": 0.3525043249130249,
      "step": 250
    },
    {
      "epoch": 1.0788381742738589,
      "grad_norm": 0.3134066164493561,
      "learning_rate": 0.00014818319936177885,
      "loss": 0.3430550336837769,
      "step": 260
    },
    {
      "epoch": 1.120331950207469,
      "grad_norm": 0.2579948902130127,
      "learning_rate": 0.00014422051887522734,
      "loss": 0.3576380968093872,
      "step": 270
    },
    {
      "epoch": 1.161825726141079,
      "grad_norm": 0.3332265019416809,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.34686951637268065,
      "step": 280
    },
    {
      "epoch": 1.2033195020746887,
      "grad_norm": 0.2892957031726837,
      "learning_rate": 0.0001360383587910944,
      "loss": 0.3565561771392822,
      "step": 290
    },
    {
      "epoch": 1.2448132780082988,
      "grad_norm": 0.36435216665267944,
      "learning_rate": 0.0001318352166630461,
      "loss": 0.3826176404953003,
      "step": 300
    },
    {
      "epoch": 1.2863070539419086,
      "grad_norm": 0.2598886489868164,
      "learning_rate": 0.00012756850857234686,
      "loss": 0.383035945892334,
      "step": 310
    },
    {
      "epoch": 1.3278008298755186,
      "grad_norm": 0.3070371150970459,
      "learning_rate": 0.0001232467539335182,
      "loss": 0.38975255489349364,
      "step": 320
    },
    {
      "epoch": 1.3692946058091287,
      "grad_norm": 0.36054837703704834,
      "learning_rate": 0.00011887858207353677,
      "loss": 0.35456552505493166,
      "step": 330
    },
    {
      "epoch": 1.4107883817427385,
      "grad_norm": 0.3497623801231384,
      "learning_rate": 0.00011447271500149848,
      "loss": 0.3724538564682007,
      "step": 340
    },
    {
      "epoch": 1.4522821576763485,
      "grad_norm": 0.3663632273674011,
      "learning_rate": 0.00011003794999322245,
      "loss": 0.30321061611175537,
      "step": 350
    },
    {
      "epoch": 1.4937759336099585,
      "grad_norm": 0.3324264585971832,
      "learning_rate": 0.00010558314202556864,
      "loss": 0.3620842695236206,
      "step": 360
    },
    {
      "epoch": 1.5352697095435683,
      "grad_norm": 0.266297310590744,
      "learning_rate": 0.00010111718609554255,
      "loss": 0.3614461898803711,
      "step": 370
    },
    {
      "epoch": 1.5767634854771784,
      "grad_norm": 0.31072020530700684,
      "learning_rate": 9.664899945949128e-05,
      "loss": 0.35188119411468505,
      "step": 380
    },
    {
      "epoch": 1.6182572614107884,
      "grad_norm": 0.346194863319397,
      "learning_rate": 9.21875038278536e-05,
      "loss": 0.3691046476364136,
      "step": 390
    },
    {
      "epoch": 1.6597510373443982,
      "grad_norm": 0.3481053113937378,
      "learning_rate": 8.774160755101685e-05,
      "loss": 0.3168217420578003,
      "step": 400
    },
    {
      "epoch": 1.7012448132780082,
      "grad_norm": 0.2926409840583801,
      "learning_rate": 8.332018783184953e-05,
      "loss": 0.3263134241104126,
      "step": 410
    },
    {
      "epoch": 1.7427385892116183,
      "grad_norm": 0.34743258357048035,
      "learning_rate": 7.89320730004274e-05,
      "loss": 0.3515430688858032,
      "step": 420
    },
    {
      "epoch": 1.784232365145228,
      "grad_norm": 0.3595181405544281,
      "learning_rate": 7.458602488634416e-05,
      "loss": 0.3001941442489624,
      "step": 430
    },
    {
      "epoch": 1.8257261410788381,
      "grad_norm": 0.33753901720046997,
      "learning_rate": 7.029072132380543e-05,
      "loss": 0.3434969186782837,
      "step": 440
    },
    {
      "epoch": 1.8672199170124482,
      "grad_norm": 0.30696454644203186,
      "learning_rate": 6.605473882443725e-05,
      "loss": 0.3275391340255737,
      "step": 450
    },
    {
      "epoch": 1.908713692946058,
      "grad_norm": 0.2938442826271057,
      "learning_rate": 6.188653545240793e-05,
      "loss": 0.32708489894866943,
      "step": 460
    },
    {
      "epoch": 1.950207468879668,
      "grad_norm": 0.33095526695251465,
      "learning_rate": 5.779443393605536e-05,
      "loss": 0.3128932237625122,
      "step": 470
    },
    {
      "epoch": 1.991701244813278,
      "grad_norm": 0.3159911632537842,
      "learning_rate": 5.378660504974271e-05,
      "loss": 0.34669668674468995,
      "step": 480
    },
    {
      "epoch": 2.033195020746888,
      "grad_norm": 0.24556255340576172,
      "learning_rate": 4.987105129912252e-05,
      "loss": 0.31173632144927976,
      "step": 490
    },
    {
      "epoch": 2.074688796680498,
      "grad_norm": 0.46301814913749695,
      "learning_rate": 4.6055590942386806e-05,
      "loss": 0.27455806732177734,
      "step": 500
    },
    {
      "epoch": 2.116182572614108,
      "grad_norm": 0.32270464301109314,
      "learning_rate": 4.2347842379407046e-05,
      "loss": 0.2737681150436401,
      "step": 510
    },
    {
      "epoch": 2.1576763485477177,
      "grad_norm": 0.2876337170600891,
      "learning_rate": 3.8755208939934816e-05,
      "loss": 0.24638769626617432,
      "step": 520
    },
    {
      "epoch": 2.199170124481328,
      "grad_norm": 0.3305664360523224,
      "learning_rate": 3.528486410123758e-05,
      "loss": 0.24475789070129395,
      "step": 530
    },
    {
      "epoch": 2.240663900414938,
      "grad_norm": 0.36426597833633423,
      "learning_rate": 3.1943737164684094e-05,
      "loss": 0.2594085931777954,
      "step": 540
    },
    {
      "epoch": 2.2821576763485476,
      "grad_norm": 0.41087988018989563,
      "learning_rate": 2.8738499419881516e-05,
      "loss": 0.26367506980895994,
      "step": 550
    },
    {
      "epoch": 2.323651452282158,
      "grad_norm": 0.38982436060905457,
      "learning_rate": 2.567555082398818e-05,
      "loss": 0.2622672080993652,
      "step": 560
    },
    {
      "epoch": 2.3651452282157677,
      "grad_norm": 0.2861771583557129,
      "learning_rate": 2.2761007222801866e-05,
      "loss": 0.2659438610076904,
      "step": 570
    },
    {
      "epoch": 2.4066390041493775,
      "grad_norm": 0.36791718006134033,
      "learning_rate": 2.000068813913777e-05,
      "loss": 0.2801490545272827,
      "step": 580
    },
    {
      "epoch": 2.4481327800829877,
      "grad_norm": 0.3523130714893341,
      "learning_rate": 1.740010515288033e-05,
      "loss": 0.25940186977386476,
      "step": 590
    },
    {
      "epoch": 2.4896265560165975,
      "grad_norm": 0.37734347581863403,
      "learning_rate": 1.496445089591031e-05,
      "loss": 0.24883666038513183,
      "step": 600
    },
    {
      "epoch": 2.5311203319502074,
      "grad_norm": 0.44160351157188416,
      "learning_rate": 1.2698588683881186e-05,
      "loss": 0.27171275615692136,
      "step": 610
    },
    {
      "epoch": 2.572614107883817,
      "grad_norm": 0.34471505880355835,
      "learning_rate": 1.0607042805547329e-05,
      "loss": 0.23731329441070556,
      "step": 620
    },
    {
      "epoch": 2.6141078838174274,
      "grad_norm": 0.3286232352256775,
      "learning_rate": 8.693989489033495e-06,
      "loss": 0.31161048412323,
      "step": 630
    },
    {
      "epoch": 2.6556016597510372,
      "grad_norm": 0.45905137062072754,
      "learning_rate": 6.963248563083202e-06,
      "loss": 0.2313161611557007,
      "step": 640
    },
    {
      "epoch": 2.6970954356846475,
      "grad_norm": 0.3563501536846161,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.2797666549682617,
      "step": 650
    },
    {
      "epoch": 2.7385892116182573,
      "grad_norm": 0.48521143198013306,
      "learning_rate": 4.062156165066211e-06,
      "loss": 0.2831265926361084,
      "step": 660
    },
    {
      "epoch": 2.780082987551867,
      "grad_norm": 0.31040000915527344,
      "learning_rate": 2.8975973575499527e-06,
      "loss": 0.24125280380249023,
      "step": 670
    },
    {
      "epoch": 2.821576763485477,
      "grad_norm": 0.38852402567863464,
      "learning_rate": 1.9269247033782744e-06,
      "loss": 0.2259364128112793,
      "step": 680
    },
    {
      "epoch": 2.863070539419087,
      "grad_norm": 0.39744216203689575,
      "learning_rate": 1.1520763624931597e-06,
      "loss": 0.2719549655914307,
      "step": 690
    },
    {
      "epoch": 2.904564315352697,
      "grad_norm": 0.383863627910614,
      "learning_rate": 5.745994888285311e-07,
      "loss": 0.2623055219650269,
      "step": 700
    },
    {
      "epoch": 2.9460580912863072,
      "grad_norm": 0.4238494634628296,
      "learning_rate": 1.9564714107945803e-07,
      "loss": 0.3000368118286133,
      "step": 710
    },
    {
      "epoch": 2.987551867219917,
      "grad_norm": 0.35640251636505127,
      "learning_rate": 1.5975980368709843e-08,
      "loss": 0.2339564085006714,
      "step": 720
    }
  ],
  "logging_steps": 10,
  "max_steps": 723,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.3778245830970368e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}