{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.146177459435755,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00146177459435755,
      "grad_norm": 1.1480557918548584,
      "learning_rate": 2.4752475247524754e-05,
      "loss": 2.0355,
      "step": 10
    },
    {
      "epoch": 0.0029235491887151,
      "grad_norm": 1.2355608940124512,
      "learning_rate": 2.4502450245024505e-05,
      "loss": 0.9343,
      "step": 20
    },
    {
      "epoch": 0.00438532378307265,
      "grad_norm": 1.6818450689315796,
      "learning_rate": 2.4252425242524256e-05,
      "loss": 0.294,
      "step": 30
    },
    {
      "epoch": 0.0058470983774302,
      "grad_norm": 0.5871298909187317,
      "learning_rate": 2.4002400240024003e-05,
      "loss": 0.2372,
      "step": 40
    },
    {
      "epoch": 0.00730887297178775,
      "grad_norm": 0.7146134972572327,
      "learning_rate": 2.3752375237523754e-05,
      "loss": 0.2836,
      "step": 50
    },
    {
      "epoch": 0.0087706475661453,
      "grad_norm": 0.7070990800857544,
      "learning_rate": 2.3502350235023505e-05,
      "loss": 0.2088,
      "step": 60
    },
    {
      "epoch": 0.01023242216050285,
      "grad_norm": 0.4255610704421997,
      "learning_rate": 2.3252325232523252e-05,
      "loss": 0.1978,
      "step": 70
    },
    {
      "epoch": 0.0116941967548604,
      "grad_norm": 0.49717941880226135,
      "learning_rate": 2.3002300230023006e-05,
      "loss": 0.1968,
      "step": 80
    },
    {
      "epoch": 0.01315597134921795,
      "grad_norm": 0.40119174122810364,
      "learning_rate": 2.2752275227522754e-05,
      "loss": 0.1913,
      "step": 90
    },
    {
      "epoch": 0.0146177459435755,
      "grad_norm": 0.7866990566253662,
      "learning_rate": 2.2502250225022505e-05,
      "loss": 0.2131,
      "step": 100
    },
    {
      "epoch": 0.016079520537933052,
      "grad_norm": 0.8951889872550964,
      "learning_rate": 2.2252225222522255e-05,
      "loss": 0.1765,
      "step": 110
    },
    {
      "epoch": 0.0175412951322906,
      "grad_norm": 0.29221057891845703,
      "learning_rate": 2.2002200220022003e-05,
      "loss": 0.1407,
      "step": 120
    },
    {
      "epoch": 0.019003069726648152,
      "grad_norm": 0.49533528089523315,
      "learning_rate": 2.1752175217521754e-05,
      "loss": 0.1644,
      "step": 130
    },
    {
      "epoch": 0.0204648443210057,
      "grad_norm": 0.3729006350040436,
      "learning_rate": 2.1502150215021505e-05,
      "loss": 0.099,
      "step": 140
    },
    {
      "epoch": 0.021926618915363252,
      "grad_norm": 0.8305023312568665,
      "learning_rate": 2.1252125212521255e-05,
      "loss": 0.1278,
      "step": 150
    },
    {
      "epoch": 0.0233883935097208,
      "grad_norm": 0.4704670011997223,
      "learning_rate": 2.1002100210021003e-05,
      "loss": 0.1521,
      "step": 160
    },
    {
      "epoch": 0.024850168104078352,
      "grad_norm": 0.787459135055542,
      "learning_rate": 2.0752075207520754e-05,
      "loss": 0.1326,
      "step": 170
    },
    {
      "epoch": 0.0263119426984359,
      "grad_norm": 0.5290590524673462,
      "learning_rate": 2.0502050205020504e-05,
      "loss": 0.1146,
      "step": 180
    },
    {
      "epoch": 0.027773717292793453,
      "grad_norm": 0.46197742223739624,
      "learning_rate": 2.0252025202520252e-05,
      "loss": 0.1278,
      "step": 190
    },
    {
      "epoch": 0.029235491887151,
      "grad_norm": 0.6425529718399048,
      "learning_rate": 2.0002000200020006e-05,
      "loss": 0.1063,
      "step": 200
    },
    {
      "epoch": 0.030697266481508553,
      "grad_norm": 0.7542579770088196,
      "learning_rate": 1.9751975197519753e-05,
      "loss": 0.117,
      "step": 210
    },
    {
      "epoch": 0.032159041075866104,
      "grad_norm": 0.38565704226493835,
      "learning_rate": 1.9501950195019504e-05,
      "loss": 0.1298,
      "step": 220
    },
    {
      "epoch": 0.03362081567022365,
      "grad_norm": 0.31743547320365906,
      "learning_rate": 1.9251925192519255e-05,
      "loss": 0.1127,
      "step": 230
    },
    {
      "epoch": 0.0350825902645812,
      "grad_norm": 0.9804937839508057,
      "learning_rate": 1.9001900190019003e-05,
      "loss": 0.1271,
      "step": 240
    },
    {
      "epoch": 0.03654436485893875,
      "grad_norm": 0.5180727243423462,
      "learning_rate": 1.8751875187518753e-05,
      "loss": 0.1222,
      "step": 250
    },
    {
      "epoch": 0.038006139453296305,
      "grad_norm": 0.5256487131118774,
      "learning_rate": 1.8501850185018504e-05,
      "loss": 0.0975,
      "step": 260
    },
    {
      "epoch": 0.03946791404765385,
      "grad_norm": 0.3315429091453552,
      "learning_rate": 1.8251825182518255e-05,
      "loss": 0.0949,
      "step": 270
    },
    {
      "epoch": 0.0409296886420114,
      "grad_norm": 0.4036615788936615,
      "learning_rate": 1.8001800180018002e-05,
      "loss": 0.1127,
      "step": 280
    },
    {
      "epoch": 0.04239146323636895,
      "grad_norm": 0.35830047726631165,
      "learning_rate": 1.7751775177517753e-05,
      "loss": 0.1042,
      "step": 290
    },
    {
      "epoch": 0.043853237830726505,
      "grad_norm": 0.7400040626525879,
      "learning_rate": 1.7501750175017504e-05,
      "loss": 0.1095,
      "step": 300
    },
    {
      "epoch": 0.04531501242508405,
      "grad_norm": 0.4160325229167938,
      "learning_rate": 1.725172517251725e-05,
      "loss": 0.0921,
      "step": 310
    },
    {
      "epoch": 0.0467767870194416,
      "grad_norm": 0.6937474012374878,
      "learning_rate": 1.7001700170017006e-05,
      "loss": 0.1096,
      "step": 320
    },
    {
      "epoch": 0.04823856161379915,
      "grad_norm": 0.3352717161178589,
      "learning_rate": 1.6751675167516753e-05,
      "loss": 0.0958,
      "step": 330
    },
    {
      "epoch": 0.049700336208156705,
      "grad_norm": 0.5310590267181396,
      "learning_rate": 1.6501650165016504e-05,
      "loss": 0.0866,
      "step": 340
    },
    {
      "epoch": 0.05116211080251425,
      "grad_norm": 0.44820308685302734,
      "learning_rate": 1.6251625162516255e-05,
      "loss": 0.0768,
      "step": 350
    },
    {
      "epoch": 0.0526238853968718,
      "grad_norm": 0.3603011965751648,
      "learning_rate": 1.6001600160016002e-05,
      "loss": 0.1096,
      "step": 360
    },
    {
      "epoch": 0.05408565999122935,
      "grad_norm": 0.4311069846153259,
      "learning_rate": 1.5751575157515753e-05,
      "loss": 0.0957,
      "step": 370
    },
    {
      "epoch": 0.055547434585586905,
      "grad_norm": 0.36236947774887085,
      "learning_rate": 1.5501550155015504e-05,
      "loss": 0.1151,
      "step": 380
    },
    {
      "epoch": 0.05700920917994445,
      "grad_norm": 0.405987948179245,
      "learning_rate": 1.5251525152515253e-05,
      "loss": 0.1184,
      "step": 390
    },
    {
      "epoch": 0.058470983774302,
      "grad_norm": 0.7587026357650757,
      "learning_rate": 1.5001500150015002e-05,
      "loss": 0.0836,
      "step": 400
    },
    {
      "epoch": 0.05993275836865955,
      "grad_norm": 0.7230392694473267,
      "learning_rate": 1.4751475147514754e-05,
      "loss": 0.0796,
      "step": 410
    },
    {
      "epoch": 0.061394532963017105,
      "grad_norm": 0.3412224352359772,
      "learning_rate": 1.4501450145014504e-05,
      "loss": 0.0883,
      "step": 420
    },
    {
      "epoch": 0.06285630755737465,
      "grad_norm": 0.4818565845489502,
      "learning_rate": 1.4251425142514253e-05,
      "loss": 0.0683,
      "step": 430
    },
    {
      "epoch": 0.06431808215173221,
      "grad_norm": 0.6868996620178223,
      "learning_rate": 1.4001400140014002e-05,
      "loss": 0.0923,
      "step": 440
    },
    {
      "epoch": 0.06577985674608976,
      "grad_norm": 0.3734653890132904,
      "learning_rate": 1.3751375137513753e-05,
      "loss": 0.0841,
      "step": 450
    },
    {
      "epoch": 0.0672416313404473,
      "grad_norm": 0.4107135534286499,
      "learning_rate": 1.3501350135013502e-05,
      "loss": 0.0797,
      "step": 460
    },
    {
      "epoch": 0.06870340593480485,
      "grad_norm": 0.43387386202812195,
      "learning_rate": 1.3251325132513251e-05,
      "loss": 0.0721,
      "step": 470
    },
    {
      "epoch": 0.0701651805291624,
      "grad_norm": 0.5933758020401001,
      "learning_rate": 1.3001300130013003e-05,
      "loss": 0.1408,
      "step": 480
    },
    {
      "epoch": 0.07162695512351995,
      "grad_norm": 0.42749252915382385,
      "learning_rate": 1.2751275127512753e-05,
      "loss": 0.0926,
      "step": 490
    },
    {
      "epoch": 0.0730887297178775,
      "grad_norm": 0.5452368855476379,
      "learning_rate": 1.2501250125012502e-05,
      "loss": 0.0871,
      "step": 500
    },
    {
      "epoch": 0.07455050431223505,
      "grad_norm": 0.42915862798690796,
      "learning_rate": 1.2251225122512252e-05,
      "loss": 0.0779,
      "step": 510
    },
    {
      "epoch": 0.07601227890659261,
      "grad_norm": 0.5489547252655029,
      "learning_rate": 1.2001200120012002e-05,
      "loss": 0.0649,
      "step": 520
    },
    {
      "epoch": 0.07747405350095016,
      "grad_norm": 0.3804190158843994,
      "learning_rate": 1.1751175117511752e-05,
      "loss": 0.0692,
      "step": 530
    },
    {
      "epoch": 0.0789358280953077,
      "grad_norm": 0.4363003075122833,
      "learning_rate": 1.1501150115011503e-05,
      "loss": 0.1051,
      "step": 540
    },
    {
      "epoch": 0.08039760268966525,
      "grad_norm": 0.352827787399292,
      "learning_rate": 1.1251125112511252e-05,
      "loss": 0.0924,
      "step": 550
    },
    {
      "epoch": 0.0818593772840228,
      "grad_norm": 0.3126923143863678,
      "learning_rate": 1.1001100110011001e-05,
      "loss": 0.08,
      "step": 560
    },
    {
      "epoch": 0.08332115187838035,
      "grad_norm": 0.8426673412322998,
      "learning_rate": 1.0751075107510752e-05,
      "loss": 0.0856,
      "step": 570
    },
    {
      "epoch": 0.0847829264727379,
      "grad_norm": 0.862802267074585,
      "learning_rate": 1.0501050105010501e-05,
      "loss": 0.0839,
      "step": 580
    },
    {
      "epoch": 0.08624470106709545,
      "grad_norm": 0.3358764946460724,
      "learning_rate": 1.0251025102510252e-05,
      "loss": 0.0661,
      "step": 590
    },
    {
      "epoch": 0.08770647566145301,
      "grad_norm": 0.27090683579444885,
      "learning_rate": 1.0001000100010003e-05,
      "loss": 0.0756,
      "step": 600
    },
    {
      "epoch": 0.08916825025581056,
      "grad_norm": 0.2274910807609558,
      "learning_rate": 9.750975097509752e-06,
      "loss": 0.0803,
      "step": 610
    },
    {
      "epoch": 0.0906300248501681,
      "grad_norm": 0.38698479533195496,
      "learning_rate": 9.500950095009501e-06,
      "loss": 0.0792,
      "step": 620
    },
    {
      "epoch": 0.09209179944452565,
      "grad_norm": 0.4514479637145996,
      "learning_rate": 9.250925092509252e-06,
      "loss": 0.0732,
      "step": 630
    },
    {
      "epoch": 0.0935535740388832,
      "grad_norm": 0.5197333693504333,
      "learning_rate": 9.000900090009001e-06,
      "loss": 0.0669,
      "step": 640
    },
    {
      "epoch": 0.09501534863324075,
      "grad_norm": 0.4484429657459259,
      "learning_rate": 8.750875087508752e-06,
      "loss": 0.0842,
      "step": 650
    },
    {
      "epoch": 0.0964771232275983,
      "grad_norm": 0.2479228973388672,
      "learning_rate": 8.500850085008503e-06,
      "loss": 0.0599,
      "step": 660
    },
    {
      "epoch": 0.09793889782195585,
      "grad_norm": 0.46314725279808044,
      "learning_rate": 8.250825082508252e-06,
      "loss": 0.0707,
      "step": 670
    },
    {
      "epoch": 0.09940067241631341,
      "grad_norm": 0.33118072152137756,
      "learning_rate": 8.000800080008001e-06,
      "loss": 0.0742,
      "step": 680
    },
    {
      "epoch": 0.10086244701067096,
      "grad_norm": 0.4030800759792328,
      "learning_rate": 7.750775077507752e-06,
      "loss": 0.0759,
      "step": 690
    },
    {
      "epoch": 0.1023242216050285,
      "grad_norm": 0.31615331768989563,
      "learning_rate": 7.500750075007501e-06,
      "loss": 0.0912,
      "step": 700
    },
    {
      "epoch": 0.10378599619938605,
      "grad_norm": 0.32550713419914246,
      "learning_rate": 7.250725072507252e-06,
      "loss": 0.0864,
      "step": 710
    },
    {
      "epoch": 0.1052477707937436,
      "grad_norm": 0.47825929522514343,
      "learning_rate": 7.000700070007001e-06,
      "loss": 0.0735,
      "step": 720
    },
    {
      "epoch": 0.10670954538810115,
      "grad_norm": 0.534595787525177,
      "learning_rate": 6.750675067506751e-06,
      "loss": 0.0742,
      "step": 730
    },
    {
      "epoch": 0.1081713199824587,
      "grad_norm": 0.5879881978034973,
      "learning_rate": 6.500650065006502e-06,
      "loss": 0.0816,
      "step": 740
    },
    {
      "epoch": 0.10963309457681626,
      "grad_norm": 0.7548266053199768,
      "learning_rate": 6.250625062506251e-06,
      "loss": 0.0612,
      "step": 750
    },
    {
      "epoch": 0.11109486917117381,
      "grad_norm": 1.1165082454681396,
      "learning_rate": 6.000600060006001e-06,
      "loss": 0.0766,
      "step": 760
    },
    {
      "epoch": 0.11255664376553136,
      "grad_norm": 0.5112439393997192,
      "learning_rate": 5.750575057505752e-06,
      "loss": 0.0628,
      "step": 770
    },
    {
      "epoch": 0.1140184183598889,
      "grad_norm": 0.416564017534256,
      "learning_rate": 5.500550055005501e-06,
      "loss": 0.0751,
      "step": 780
    },
    {
      "epoch": 0.11548019295424646,
      "grad_norm": 0.9259045124053955,
      "learning_rate": 5.250525052505251e-06,
      "loss": 0.1037,
      "step": 790
    },
    {
      "epoch": 0.116941967548604,
      "grad_norm": 0.3240310847759247,
      "learning_rate": 5.0005000500050015e-06,
      "loss": 0.0826,
      "step": 800
    },
    {
      "epoch": 0.11840374214296155,
      "grad_norm": 0.32784464955329895,
      "learning_rate": 4.750475047504751e-06,
      "loss": 0.0849,
      "step": 810
    },
    {
      "epoch": 0.1198655167373191,
      "grad_norm": 0.198726087808609,
      "learning_rate": 4.500450045004501e-06,
      "loss": 0.0554,
      "step": 820
    },
    {
      "epoch": 0.12132729133167666,
      "grad_norm": 0.47690388560295105,
      "learning_rate": 4.250425042504251e-06,
      "loss": 0.07,
      "step": 830
    },
    {
      "epoch": 0.12278906592603421,
      "grad_norm": 0.6009281873703003,
      "learning_rate": 4.0004000400040005e-06,
      "loss": 0.1019,
      "step": 840
    },
    {
      "epoch": 0.12425084052039176,
      "grad_norm": 0.37418490648269653,
      "learning_rate": 3.7503750375037505e-06,
      "loss": 0.0935,
      "step": 850
    },
    {
      "epoch": 0.1257126151147493,
      "grad_norm": 0.36421412229537964,
      "learning_rate": 3.5003500350035005e-06,
      "loss": 0.0883,
      "step": 860
    },
    {
      "epoch": 0.12717438970910686,
      "grad_norm": 0.44606733322143555,
      "learning_rate": 3.250325032503251e-06,
      "loss": 0.1029,
      "step": 870
    },
    {
      "epoch": 0.12863616430346442,
      "grad_norm": 0.4448641836643219,
      "learning_rate": 3.0003000300030004e-06,
      "loss": 0.0802,
      "step": 880
    },
    {
      "epoch": 0.13009793889782195,
      "grad_norm": 0.42409053444862366,
      "learning_rate": 2.7502750275027504e-06,
      "loss": 0.0688,
      "step": 890
    },
    {
      "epoch": 0.13155971349217951,
      "grad_norm": 0.43361061811447144,
      "learning_rate": 2.5002500250025008e-06,
      "loss": 0.0575,
      "step": 900
    },
    {
      "epoch": 0.13302148808653705,
      "grad_norm": 0.3293386995792389,
      "learning_rate": 2.2502250225022503e-06,
      "loss": 0.0547,
      "step": 910
    },
    {
      "epoch": 0.1344832626808946,
      "grad_norm": 1.1192256212234497,
      "learning_rate": 2.0002000200020003e-06,
      "loss": 0.0809,
      "step": 920
    },
    {
      "epoch": 0.13594503727525215,
      "grad_norm": 0.45779263973236084,
      "learning_rate": 1.7501750175017502e-06,
      "loss": 0.0993,
      "step": 930
    },
    {
      "epoch": 0.1374068118696097,
      "grad_norm": 0.3892732560634613,
      "learning_rate": 1.5001500150015002e-06,
      "loss": 0.0467,
      "step": 940
    },
    {
      "epoch": 0.13886858646396727,
      "grad_norm": 0.621871829032898,
      "learning_rate": 1.2501250125012504e-06,
      "loss": 0.0756,
      "step": 950
    },
    {
      "epoch": 0.1403303610583248,
      "grad_norm": 0.37552908062934875,
      "learning_rate": 1.0001000100010001e-06,
      "loss": 0.0774,
      "step": 960
    },
    {
      "epoch": 0.14179213565268237,
      "grad_norm": 0.42678821086883545,
      "learning_rate": 7.500750075007501e-07,
      "loss": 0.0657,
      "step": 970
    },
    {
      "epoch": 0.1432539102470399,
      "grad_norm": 0.552952766418457,
      "learning_rate": 5.000500050005001e-07,
      "loss": 0.0517,
      "step": 980
    },
    {
      "epoch": 0.14471568484139746,
      "grad_norm": 0.2972164750099182,
      "learning_rate": 2.5002500250025003e-07,
      "loss": 0.0597,
      "step": 990
    },
    {
      "epoch": 0.146177459435755,
      "grad_norm": 0.501569926738739,
      "learning_rate": 0.0,
      "loss": 0.0774,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2645444001792000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}