{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.026720106880427523,
      "grad_norm": 4.876547256652112,
      "learning_rate": 1.1842105263157894e-06,
      "loss": 1.3304182052612306,
      "step": 10
    },
    {
      "epoch": 0.053440213760855046,
      "grad_norm": 1.9031723494526915,
      "learning_rate": 2.5e-06,
      "loss": 1.099290657043457,
      "step": 20
    },
    {
      "epoch": 0.08016032064128256,
      "grad_norm": 1.0784909354681218,
      "learning_rate": 3.815789473684211e-06,
      "loss": 0.8894227981567383,
      "step": 30
    },
    {
      "epoch": 0.10688042752171009,
      "grad_norm": 0.8341559538518258,
      "learning_rate": 4.999975664007296e-06,
      "loss": 0.7917738437652588,
      "step": 40
    },
    {
      "epoch": 0.13360053440213762,
      "grad_norm": 0.7729886199109874,
      "learning_rate": 4.997055918128024e-06,
      "loss": 0.7352667808532715,
      "step": 50
    },
    {
      "epoch": 0.16032064128256512,
      "grad_norm": 0.8173786320966572,
      "learning_rate": 4.989275486268417e-06,
      "loss": 0.7090502738952636,
      "step": 60
    },
    {
      "epoch": 0.18704074816299265,
      "grad_norm": 0.764511426280662,
      "learning_rate": 4.976649513558299e-06,
      "loss": 0.6891400337219238,
      "step": 70
    },
    {
      "epoch": 0.21376085504342018,
      "grad_norm": 0.8115933747973788,
      "learning_rate": 4.959202577296117e-06,
      "loss": 0.6775829315185546,
      "step": 80
    },
    {
      "epoch": 0.24048096192384769,
      "grad_norm": 0.7549016417926586,
      "learning_rate": 4.936968639107591e-06,
      "loss": 0.6661912441253662,
      "step": 90
    },
    {
      "epoch": 0.26720106880427524,
      "grad_norm": 0.7133908659684393,
      "learning_rate": 4.909990978837137e-06,
      "loss": 0.6624391555786133,
      "step": 100
    },
    {
      "epoch": 0.2939211756847027,
      "grad_norm": 0.7306689712473161,
      "learning_rate": 4.878322110300771e-06,
      "loss": 0.6572754383087158,
      "step": 110
    },
    {
      "epoch": 0.32064128256513025,
      "grad_norm": 0.7054501488899482,
      "learning_rate": 4.84202367906445e-06,
      "loss": 0.6535427093505859,
      "step": 120
    },
    {
      "epoch": 0.3473613894455578,
      "grad_norm": 0.7855885641182727,
      "learning_rate": 4.801166342446877e-06,
      "loss": 0.6461863994598389,
      "step": 130
    },
    {
      "epoch": 0.3740814963259853,
      "grad_norm": 0.7513352379873058,
      "learning_rate": 4.755829631980303e-06,
      "loss": 0.6391179084777832,
      "step": 140
    },
    {
      "epoch": 0.40080160320641284,
      "grad_norm": 0.7134813701717657,
      "learning_rate": 4.706101798597102e-06,
      "loss": 0.635140323638916,
      "step": 150
    },
    {
      "epoch": 0.42752171008684037,
      "grad_norm": 0.8653426407473752,
      "learning_rate": 4.652079640843434e-06,
      "loss": 0.6354692935943603,
      "step": 160
    },
    {
      "epoch": 0.45424181696726784,
      "grad_norm": 0.7349345693265136,
      "learning_rate": 4.59386831645442e-06,
      "loss": 0.6334281444549561,
      "step": 170
    },
    {
      "epoch": 0.48096192384769537,
      "grad_norm": 0.7233246443319206,
      "learning_rate": 4.531581137657591e-06,
      "loss": 0.6330723285675048,
      "step": 180
    },
    {
      "epoch": 0.5076820307281229,
      "grad_norm": 0.7692143014994247,
      "learning_rate": 4.46533935060308e-06,
      "loss": 0.6283644199371338,
      "step": 190
    },
    {
      "epoch": 0.5344021376085505,
      "grad_norm": 0.70142376719244,
      "learning_rate": 4.395271899349889e-06,
      "loss": 0.6246160984039306,
      "step": 200
    },
    {
      "epoch": 0.561122244488978,
      "grad_norm": 0.7093252765626898,
      "learning_rate": 4.321515174867686e-06,
      "loss": 0.6249143123626709,
      "step": 210
    },
    {
      "epoch": 0.5878423513694054,
      "grad_norm": 0.7214423017657354,
      "learning_rate": 4.244212749542675e-06,
      "loss": 0.6213020324707031,
      "step": 220
    },
    {
      "epoch": 0.614562458249833,
      "grad_norm": 0.7008719838494845,
      "learning_rate": 4.163515097704361e-06,
      "loss": 0.6200271606445312,
      "step": 230
    },
    {
      "epoch": 0.6412825651302605,
      "grad_norm": 0.6951688859813913,
      "learning_rate": 4.079579302717234e-06,
      "loss": 0.6169363021850586,
      "step": 240
    },
    {
      "epoch": 0.6680026720106881,
      "grad_norm": 0.6656237908469292,
      "learning_rate": 3.992568751207513e-06,
      "loss": 0.6152877330780029,
      "step": 250
    },
    {
      "epoch": 0.6947227788911156,
      "grad_norm": 0.7125107608020639,
      "learning_rate": 3.902652815020175e-06,
      "loss": 0.6130396842956543,
      "step": 260
    },
    {
      "epoch": 0.7214428857715431,
      "grad_norm": 0.6524073362173606,
      "learning_rate": 3.8100065215253563e-06,
      "loss": 0.6114709854125977,
      "step": 270
    },
    {
      "epoch": 0.7481629926519706,
      "grad_norm": 0.67209164194836,
      "learning_rate": 3.7148102129158973e-06,
      "loss": 0.6111156940460205,
      "step": 280
    },
    {
      "epoch": 0.7748830995323981,
      "grad_norm": 0.6875260178694421,
      "learning_rate": 3.6172491951592305e-06,
      "loss": 0.6086190700531006,
      "step": 290
    },
    {
      "epoch": 0.8016032064128257,
      "grad_norm": 0.6692605528542263,
      "learning_rate": 3.517513377286944e-06,
      "loss": 0.6086817741394043,
      "step": 300
    },
    {
      "epoch": 0.8283233132932531,
      "grad_norm": 0.6939501678903673,
      "learning_rate": 3.415796901724183e-06,
      "loss": 0.6049985408782959,
      "step": 310
    },
    {
      "epoch": 0.8550434201736807,
      "grad_norm": 0.7868170979936547,
      "learning_rate": 3.3122977663784643e-06,
      "loss": 0.6040192604064941,
      "step": 320
    },
    {
      "epoch": 0.8817635270541082,
      "grad_norm": 0.6608843077593789,
      "learning_rate": 3.2072174392235305e-06,
      "loss": 0.603293514251709,
      "step": 330
    },
    {
      "epoch": 0.9084836339345357,
      "grad_norm": 0.6753893682388156,
      "learning_rate": 3.1007604661285012e-06,
      "loss": 0.6026342868804931,
      "step": 340
    },
    {
      "epoch": 0.9352037408149633,
      "grad_norm": 0.6469919728660742,
      "learning_rate": 2.9931340726956844e-06,
      "loss": 0.6008067607879639,
      "step": 350
    },
    {
      "epoch": 0.9619238476953907,
      "grad_norm": 0.656851453111269,
      "learning_rate": 2.884547760882115e-06,
      "loss": 0.6047402858734131,
      "step": 360
    },
    {
      "epoch": 0.9886439545758183,
      "grad_norm": 0.6707654860145241,
      "learning_rate": 2.7752129011900143e-06,
      "loss": 0.5991304397583008,
      "step": 370
    },
    {
      "epoch": 1.0133600534402138,
      "grad_norm": 0.6467982234323543,
      "learning_rate": 2.6653423212200014e-06,
      "loss": 0.5899325370788574,
      "step": 380
    },
    {
      "epoch": 1.0400801603206413,
      "grad_norm": 0.6501455824451937,
      "learning_rate": 2.5551498913879662e-06,
      "loss": 0.5760808944702148,
      "step": 390
    },
    {
      "epoch": 1.0668002672010688,
      "grad_norm": 0.7977750981539845,
      "learning_rate": 2.444850108612034e-06,
      "loss": 0.5761138916015625,
      "step": 400
    },
    {
      "epoch": 1.0935203740814963,
      "grad_norm": 0.6749622235419189,
      "learning_rate": 2.3346576787799995e-06,
      "loss": 0.5734719276428223,
      "step": 410
    },
    {
      "epoch": 1.1202404809619237,
      "grad_norm": 0.7780859235448976,
      "learning_rate": 2.2247870988099865e-06,
      "loss": 0.5741193771362305,
      "step": 420
    },
    {
      "epoch": 1.1469605878423514,
      "grad_norm": 0.6959584711428828,
      "learning_rate": 2.115452239117886e-06,
      "loss": 0.573665714263916,
      "step": 430
    },
    {
      "epoch": 1.173680694722779,
      "grad_norm": 0.682434363128297,
      "learning_rate": 2.0068659273043165e-06,
      "loss": 0.5740629196166992,
      "step": 440
    },
    {
      "epoch": 1.2004008016032064,
      "grad_norm": 0.7733064535680229,
      "learning_rate": 1.8992395338714994e-06,
      "loss": 0.5758857250213623,
      "step": 450
    },
    {
      "epoch": 1.2271209084836339,
      "grad_norm": 0.7009839744496107,
      "learning_rate": 1.7927825607764699e-06,
      "loss": 0.5736015319824219,
      "step": 460
    },
    {
      "epoch": 1.2538410153640616,
      "grad_norm": 0.6714792232993504,
      "learning_rate": 1.6877022336215366e-06,
      "loss": 0.5754014015197754,
      "step": 470
    },
    {
      "epoch": 1.280561122244489,
      "grad_norm": 0.6304087345769598,
      "learning_rate": 1.5842030982758175e-06,
      "loss": 0.5695438385009766,
      "step": 480
    },
    {
      "epoch": 1.3072812291249165,
      "grad_norm": 0.7089749386846598,
      "learning_rate": 1.4824866227130575e-06,
      "loss": 0.5709002494812012,
      "step": 490
    },
    {
      "epoch": 1.334001336005344,
      "grad_norm": 0.6436788095472535,
      "learning_rate": 1.3827508048407697e-06,
      "loss": 0.5714809894561768,
      "step": 500
    },
    {
      "epoch": 1.334001336005344,
      "eval_loss": 0.595779299736023,
      "eval_runtime": 394.9,
      "eval_samples_per_second": 12.629,
      "eval_steps_per_second": 0.395,
      "step": 500
    },
    {
      "epoch": 1.3607214428857715,
      "grad_norm": 0.6235108655433143,
      "learning_rate": 1.2851897870841026e-06,
      "loss": 0.5693605422973633,
      "step": 510
    },
    {
      "epoch": 1.3874415497661992,
      "grad_norm": 0.6470837248213502,
      "learning_rate": 1.1899934784746445e-06,
      "loss": 0.5719375610351562,
      "step": 520
    },
    {
      "epoch": 1.4141616566466266,
      "grad_norm": 0.6146371865957677,
      "learning_rate": 1.0973471849798258e-06,
      "loss": 0.5687567234039307,
      "step": 530
    },
    {
      "epoch": 1.440881763527054,
      "grad_norm": 0.6442010786187964,
      "learning_rate": 1.0074312487924878e-06,
      "loss": 0.5679741859436035,
      "step": 540
    },
    {
      "epoch": 1.4676018704074816,
      "grad_norm": 0.6158122239595999,
      "learning_rate": 9.20420697282767e-07,
      "loss": 0.5679835319519043,
      "step": 550
    },
    {
      "epoch": 1.494321977287909,
      "grad_norm": 0.6527675279748488,
      "learning_rate": 8.364849022956395e-07,
      "loss": 0.5671506881713867,
      "step": 560
    },
    {
      "epoch": 1.5210420841683367,
      "grad_norm": 0.6481915375949961,
      "learning_rate": 7.557872504573261e-07,
      "loss": 0.5679010868072509,
      "step": 570
    },
    {
      "epoch": 1.5477621910487642,
      "grad_norm": 0.6408784041079482,
      "learning_rate": 6.784848251323137e-07,
      "loss": 0.5690211772918701,
      "step": 580
    },
    {
      "epoch": 1.5744822979291917,
      "grad_norm": 0.6321413147012679,
      "learning_rate": 6.047281006501118e-07,
      "loss": 0.56676025390625,
      "step": 590
    },
    {
      "epoch": 1.6012024048096194,
      "grad_norm": 0.6411325062046465,
      "learning_rate": 5.346606493969215e-07,
      "loss": 0.5677847862243652,
      "step": 600
    },
    {
      "epoch": 1.6279225116900466,
      "grad_norm": 0.6583161979203739,
      "learning_rate": 4.684188623424088e-07,
      "loss": 0.5674724578857422,
      "step": 610
    },
    {
      "epoch": 1.6546426185704743,
      "grad_norm": 0.6159135298529104,
      "learning_rate": 4.0613168354558087e-07,
      "loss": 0.5679883480072021,
      "step": 620
    },
    {
      "epoch": 1.6813627254509018,
      "grad_norm": 0.6419889128138545,
      "learning_rate": 3.4792035915656693e-07,
      "loss": 0.5640823364257812,
      "step": 630
    },
    {
      "epoch": 1.7080828323313293,
      "grad_norm": 0.5962542605077515,
      "learning_rate": 2.938982014028988e-07,
      "loss": 0.567740535736084,
      "step": 640
    },
    {
      "epoch": 1.734802939211757,
      "grad_norm": 0.604825354897304,
      "learning_rate": 2.441703680196972e-07,
      "loss": 0.5660459518432617,
      "step": 650
    },
    {
      "epoch": 1.7615230460921842,
      "grad_norm": 0.6003172856802951,
      "learning_rate": 1.9883365755312357e-07,
      "loss": 0.5657346725463868,
      "step": 660
    },
    {
      "epoch": 1.788243152972612,
      "grad_norm": 0.6635164215072833,
      "learning_rate": 1.5797632093555033e-07,
      "loss": 0.5652554512023926,
      "step": 670
    },
    {
      "epoch": 1.8149632598530394,
      "grad_norm": 0.59747490421471,
      "learning_rate": 1.2167788969923044e-07,
      "loss": 0.5675931453704834,
      "step": 680
    },
    {
      "epoch": 1.8416833667334669,
      "grad_norm": 0.5938643163689874,
      "learning_rate": 9.000902116286348e-08,
      "loss": 0.5656930923461914,
      "step": 690
    },
    {
      "epoch": 1.8684034736138946,
      "grad_norm": 0.6415075453296079,
      "learning_rate": 6.303136089241018e-08,
      "loss": 0.5642107009887696,
      "step": 700
    },
    {
      "epoch": 1.8951235804943218,
      "grad_norm": 0.6335771859351955,
      "learning_rate": 4.079742270388321e-08,
      "loss": 0.5658456802368164,
      "step": 710
    },
    {
      "epoch": 1.9218436873747495,
      "grad_norm": 0.5781194612989129,
      "learning_rate": 2.3350486441701404e-08,
      "loss": 0.5656781196594238,
      "step": 720
    },
    {
      "epoch": 1.948563794255177,
      "grad_norm": 0.6125226759054538,
      "learning_rate": 1.072451373158312e-08,
      "loss": 0.5650173187255859,
      "step": 730
    },
    {
      "epoch": 1.9752839011356045,
      "grad_norm": 0.610959987835565,
      "learning_rate": 2.944081871975868e-09,
      "loss": 0.5699827194213867,
      "step": 740
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.166305510628666,
      "learning_rate": 2.433599270490472e-11,
      "loss": 0.5648038864135743,
      "step": 750
    }
  ],
  "logging_steps": 10,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.234017639091405e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}