{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9902370990237097,
  "eval_steps": 500,
  "global_step": 804,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.037192003719200374,
      "grad_norm": 6.881888050242323,
      "learning_rate": 5e-06,
      "loss": 1.0402,
      "step": 10
    },
    {
      "epoch": 0.07438400743840075,
      "grad_norm": 3.5091968880412154,
      "learning_rate": 5e-06,
      "loss": 0.9234,
      "step": 20
    },
    {
      "epoch": 0.11157601115760112,
      "grad_norm": 1.6873942990209014,
      "learning_rate": 5e-06,
      "loss": 0.8833,
      "step": 30
    },
    {
      "epoch": 0.1487680148768015,
      "grad_norm": 2.407800596967581,
      "learning_rate": 5e-06,
      "loss": 0.8524,
      "step": 40
    },
    {
      "epoch": 0.18596001859600186,
      "grad_norm": 2.4319398224790505,
      "learning_rate": 5e-06,
      "loss": 0.828,
      "step": 50
    },
    {
      "epoch": 0.22315202231520223,
      "grad_norm": 1.6767100693953145,
      "learning_rate": 5e-06,
      "loss": 0.8117,
      "step": 60
    },
    {
      "epoch": 0.2603440260344026,
      "grad_norm": 1.1194486400318895,
      "learning_rate": 5e-06,
      "loss": 0.8019,
      "step": 70
    },
    {
      "epoch": 0.297536029753603,
      "grad_norm": 0.7791268668811029,
      "learning_rate": 5e-06,
      "loss": 0.7909,
      "step": 80
    },
    {
      "epoch": 0.33472803347280333,
      "grad_norm": 1.0231329358996892,
      "learning_rate": 5e-06,
      "loss": 0.7745,
      "step": 90
    },
    {
      "epoch": 0.3719200371920037,
      "grad_norm": 1.0119634746718196,
      "learning_rate": 5e-06,
      "loss": 0.7768,
      "step": 100
    },
    {
      "epoch": 0.40911204091120407,
      "grad_norm": 0.7286643555576803,
      "learning_rate": 5e-06,
      "loss": 0.7715,
      "step": 110
    },
    {
      "epoch": 0.44630404463040446,
      "grad_norm": 0.8830873875823773,
      "learning_rate": 5e-06,
      "loss": 0.7694,
      "step": 120
    },
    {
      "epoch": 0.48349604834960486,
      "grad_norm": 1.0262942694467152,
      "learning_rate": 5e-06,
      "loss": 0.7639,
      "step": 130
    },
    {
      "epoch": 0.5206880520688052,
      "grad_norm": 0.8416190902804997,
      "learning_rate": 5e-06,
      "loss": 0.7627,
      "step": 140
    },
    {
      "epoch": 0.5578800557880056,
      "grad_norm": 0.8213144249800172,
      "learning_rate": 5e-06,
      "loss": 0.7584,
      "step": 150
    },
    {
      "epoch": 0.595072059507206,
      "grad_norm": 0.7761932672369115,
      "learning_rate": 5e-06,
      "loss": 0.7527,
      "step": 160
    },
    {
      "epoch": 0.6322640632264063,
      "grad_norm": 0.594310752303111,
      "learning_rate": 5e-06,
      "loss": 0.7551,
      "step": 170
    },
    {
      "epoch": 0.6694560669456067,
      "grad_norm": 0.723753760030973,
      "learning_rate": 5e-06,
      "loss": 0.7505,
      "step": 180
    },
    {
      "epoch": 0.7066480706648071,
      "grad_norm": 0.8255927381229027,
      "learning_rate": 5e-06,
      "loss": 0.7537,
      "step": 190
    },
    {
      "epoch": 0.7438400743840075,
      "grad_norm": 0.6756994735330465,
      "learning_rate": 5e-06,
      "loss": 0.7471,
      "step": 200
    },
    {
      "epoch": 0.7810320781032078,
      "grad_norm": 0.7417685138593264,
      "learning_rate": 5e-06,
      "loss": 0.7519,
      "step": 210
    },
    {
      "epoch": 0.8182240818224081,
      "grad_norm": 0.7199232164518533,
      "learning_rate": 5e-06,
      "loss": 0.7445,
      "step": 220
    },
    {
      "epoch": 0.8554160855416085,
      "grad_norm": 0.5805134046445549,
      "learning_rate": 5e-06,
      "loss": 0.7469,
      "step": 230
    },
    {
      "epoch": 0.8926080892608089,
      "grad_norm": 0.8083557503057547,
      "learning_rate": 5e-06,
      "loss": 0.7426,
      "step": 240
    },
    {
      "epoch": 0.9298000929800093,
      "grad_norm": 0.5958428143365987,
      "learning_rate": 5e-06,
      "loss": 0.7429,
      "step": 250
    },
    {
      "epoch": 0.9669920966992097,
      "grad_norm": 0.7200821647238617,
      "learning_rate": 5e-06,
      "loss": 0.7455,
      "step": 260
    },
    {
      "epoch": 0.9967456996745699,
      "eval_loss": 0.7387776970863342,
      "eval_runtime": 285.1365,
      "eval_samples_per_second": 25.402,
      "eval_steps_per_second": 0.4,
      "step": 268
    },
    {
      "epoch": 1.00418410041841,
      "grad_norm": 0.9192811448757029,
      "learning_rate": 5e-06,
      "loss": 0.7395,
      "step": 270
    },
    {
      "epoch": 1.0413761041376104,
      "grad_norm": 0.7114550344465745,
      "learning_rate": 5e-06,
      "loss": 0.6952,
      "step": 280
    },
    {
      "epoch": 1.0785681078568108,
      "grad_norm": 0.7773431995256311,
      "learning_rate": 5e-06,
      "loss": 0.6894,
      "step": 290
    },
    {
      "epoch": 1.1157601115760112,
      "grad_norm": 0.8395302785079569,
      "learning_rate": 5e-06,
      "loss": 0.6895,
      "step": 300
    },
    {
      "epoch": 1.1529521152952116,
      "grad_norm": 0.5978839456204598,
      "learning_rate": 5e-06,
      "loss": 0.6839,
      "step": 310
    },
    {
      "epoch": 1.190144119014412,
      "grad_norm": 0.6886905957705741,
      "learning_rate": 5e-06,
      "loss": 0.6869,
      "step": 320
    },
    {
      "epoch": 1.2273361227336124,
      "grad_norm": 0.6062023199694873,
      "learning_rate": 5e-06,
      "loss": 0.6861,
      "step": 330
    },
    {
      "epoch": 1.2645281264528125,
      "grad_norm": 0.6559502974519889,
      "learning_rate": 5e-06,
      "loss": 0.6848,
      "step": 340
    },
    {
      "epoch": 1.301720130172013,
      "grad_norm": 0.6672718286848371,
      "learning_rate": 5e-06,
      "loss": 0.6894,
      "step": 350
    },
    {
      "epoch": 1.3389121338912133,
      "grad_norm": 0.6968811181243937,
      "learning_rate": 5e-06,
      "loss": 0.6856,
      "step": 360
    },
    {
      "epoch": 1.3761041376104137,
      "grad_norm": 0.713126345107699,
      "learning_rate": 5e-06,
      "loss": 0.6921,
      "step": 370
    },
    {
      "epoch": 1.4132961413296141,
      "grad_norm": 0.555101582608444,
      "learning_rate": 5e-06,
      "loss": 0.685,
      "step": 380
    },
    {
      "epoch": 1.4504881450488145,
      "grad_norm": 0.8155799633973349,
      "learning_rate": 5e-06,
      "loss": 0.688,
      "step": 390
    },
    {
      "epoch": 1.487680148768015,
      "grad_norm": 0.7809410682542598,
      "learning_rate": 5e-06,
      "loss": 0.6848,
      "step": 400
    },
    {
      "epoch": 1.524872152487215,
      "grad_norm": 0.859503762107944,
      "learning_rate": 5e-06,
      "loss": 0.6842,
      "step": 410
    },
    {
      "epoch": 1.5620641562064157,
      "grad_norm": 0.7216593694701429,
      "learning_rate": 5e-06,
      "loss": 0.6846,
      "step": 420
    },
    {
      "epoch": 1.5992561599256159,
      "grad_norm": 0.7100718746210283,
      "learning_rate": 5e-06,
      "loss": 0.6892,
      "step": 430
    },
    {
      "epoch": 1.6364481636448165,
      "grad_norm": 0.6713429745171309,
      "learning_rate": 5e-06,
      "loss": 0.693,
      "step": 440
    },
    {
      "epoch": 1.6736401673640167,
      "grad_norm": 0.8718788500797711,
      "learning_rate": 5e-06,
      "loss": 0.6814,
      "step": 450
    },
    {
      "epoch": 1.710832171083217,
      "grad_norm": 0.8350277998981831,
      "learning_rate": 5e-06,
      "loss": 0.6845,
      "step": 460
    },
    {
      "epoch": 1.7480241748024175,
      "grad_norm": 0.6507252875638763,
      "learning_rate": 5e-06,
      "loss": 0.6888,
      "step": 470
    },
    {
      "epoch": 1.7852161785216178,
      "grad_norm": 0.6271601112082867,
      "learning_rate": 5e-06,
      "loss": 0.6863,
      "step": 480
    },
    {
      "epoch": 1.8224081822408182,
      "grad_norm": 0.616595241070034,
      "learning_rate": 5e-06,
      "loss": 0.6849,
      "step": 490
    },
    {
      "epoch": 1.8596001859600186,
      "grad_norm": 0.6956379811592589,
      "learning_rate": 5e-06,
      "loss": 0.6821,
      "step": 500
    },
    {
      "epoch": 1.896792189679219,
      "grad_norm": 0.6804741810216053,
      "learning_rate": 5e-06,
      "loss": 0.6808,
      "step": 510
    },
    {
      "epoch": 1.9339841933984192,
      "grad_norm": 0.6471606933029862,
      "learning_rate": 5e-06,
      "loss": 0.6884,
      "step": 520
    },
    {
      "epoch": 1.9711761971176198,
      "grad_norm": 0.6546763243128592,
      "learning_rate": 5e-06,
      "loss": 0.6844,
      "step": 530
    },
    {
      "epoch": 1.9972105997210599,
      "eval_loss": 0.7266745567321777,
      "eval_runtime": 286.325,
      "eval_samples_per_second": 25.296,
      "eval_steps_per_second": 0.398,
      "step": 537
    },
    {
      "epoch": 2.00836820083682,
      "grad_norm": 1.0262138186877314,
      "learning_rate": 5e-06,
      "loss": 0.6783,
      "step": 540
    },
    {
      "epoch": 2.0455602045560206,
      "grad_norm": 0.8739740031885926,
      "learning_rate": 5e-06,
      "loss": 0.6332,
      "step": 550
    },
    {
      "epoch": 2.082752208275221,
      "grad_norm": 0.7117432291580535,
      "learning_rate": 5e-06,
      "loss": 0.6296,
      "step": 560
    },
    {
      "epoch": 2.1199442119944214,
      "grad_norm": 0.5899527267147682,
      "learning_rate": 5e-06,
      "loss": 0.6285,
      "step": 570
    },
    {
      "epoch": 2.1571362157136216,
      "grad_norm": 0.6690509984383408,
      "learning_rate": 5e-06,
      "loss": 0.6297,
      "step": 580
    },
    {
      "epoch": 2.1943282194328217,
      "grad_norm": 0.9042165551862072,
      "learning_rate": 5e-06,
      "loss": 0.6327,
      "step": 590
    },
    {
      "epoch": 2.2315202231520224,
      "grad_norm": 0.7099236499244134,
      "learning_rate": 5e-06,
      "loss": 0.6313,
      "step": 600
    },
    {
      "epoch": 2.2687122268712225,
      "grad_norm": 0.7526574548917114,
      "learning_rate": 5e-06,
      "loss": 0.6343,
      "step": 610
    },
    {
      "epoch": 2.305904230590423,
      "grad_norm": 0.5914475009740064,
      "learning_rate": 5e-06,
      "loss": 0.6304,
      "step": 620
    },
    {
      "epoch": 2.3430962343096233,
      "grad_norm": 0.6210916718103259,
      "learning_rate": 5e-06,
      "loss": 0.6266,
      "step": 630
    },
    {
      "epoch": 2.380288238028824,
      "grad_norm": 0.9617962871174769,
      "learning_rate": 5e-06,
      "loss": 0.6334,
      "step": 640
    },
    {
      "epoch": 2.417480241748024,
      "grad_norm": 0.68177525923663,
      "learning_rate": 5e-06,
      "loss": 0.6374,
      "step": 650
    },
    {
      "epoch": 2.4546722454672247,
      "grad_norm": 0.7346141491432675,
      "learning_rate": 5e-06,
      "loss": 0.6354,
      "step": 660
    },
    {
      "epoch": 2.491864249186425,
      "grad_norm": 0.765713000031021,
      "learning_rate": 5e-06,
      "loss": 0.632,
      "step": 670
    },
    {
      "epoch": 2.529056252905625,
      "grad_norm": 0.9254737796398699,
      "learning_rate": 5e-06,
      "loss": 0.6355,
      "step": 680
    },
    {
      "epoch": 2.5662482566248257,
      "grad_norm": 0.5791067801191988,
      "learning_rate": 5e-06,
      "loss": 0.635,
      "step": 690
    },
    {
      "epoch": 2.603440260344026,
      "grad_norm": 0.6114487645448582,
      "learning_rate": 5e-06,
      "loss": 0.6338,
      "step": 700
    },
    {
      "epoch": 2.6406322640632265,
      "grad_norm": 0.6334477556910006,
      "learning_rate": 5e-06,
      "loss": 0.6298,
      "step": 710
    },
    {
      "epoch": 2.6778242677824267,
      "grad_norm": 0.6414121652994028,
      "learning_rate": 5e-06,
      "loss": 0.6388,
      "step": 720
    },
    {
      "epoch": 2.7150162715016273,
      "grad_norm": 0.6324796752766957,
      "learning_rate": 5e-06,
      "loss": 0.6365,
      "step": 730
    },
    {
      "epoch": 2.7522082752208274,
      "grad_norm": 0.7190932899296674,
      "learning_rate": 5e-06,
      "loss": 0.6418,
      "step": 740
    },
    {
      "epoch": 2.789400278940028,
      "grad_norm": 0.5758231899781839,
      "learning_rate": 5e-06,
      "loss": 0.636,
      "step": 750
    },
    {
      "epoch": 2.8265922826592282,
      "grad_norm": 0.6399727518476824,
      "learning_rate": 5e-06,
      "loss": 0.6359,
      "step": 760
    },
    {
      "epoch": 2.8637842863784284,
      "grad_norm": 0.6927434726600722,
      "learning_rate": 5e-06,
      "loss": 0.6371,
      "step": 770
    },
    {
      "epoch": 2.900976290097629,
      "grad_norm": 0.626988233626989,
      "learning_rate": 5e-06,
      "loss": 0.6404,
      "step": 780
    },
    {
      "epoch": 2.9381682938168296,
      "grad_norm": 0.5823110300301132,
      "learning_rate": 5e-06,
      "loss": 0.6339,
      "step": 790
    },
    {
      "epoch": 2.97536029753603,
      "grad_norm": 0.6355859003574489,
      "learning_rate": 5e-06,
      "loss": 0.6382,
      "step": 800
    },
    {
      "epoch": 2.9902370990237097,
      "eval_loss": 0.7294604778289795,
      "eval_runtime": 287.7675,
      "eval_samples_per_second": 25.17,
      "eval_steps_per_second": 0.396,
      "step": 804
    },
    {
      "epoch": 2.9902370990237097,
      "step": 804,
      "total_flos": 1346520565678080.0,
      "train_loss": 0.7033177981922283,
      "train_runtime": 47430.6382,
      "train_samples_per_second": 8.704,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 804,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1346520565678080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}