{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.99695843190267,
  "eval_steps": 500,
  "global_step": 1107,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027036160865157147,
      "grad_norm": 3.523985384534832,
      "learning_rate": 5e-06,
      "loss": 0.8602,
      "step": 10
    },
    {
      "epoch": 0.054072321730314295,
      "grad_norm": 2.330230157876199,
      "learning_rate": 5e-06,
      "loss": 0.6873,
      "step": 20
    },
    {
      "epoch": 0.08110848259547145,
      "grad_norm": 2.692866742411895,
      "learning_rate": 5e-06,
      "loss": 0.6489,
      "step": 30
    },
    {
      "epoch": 0.10814464346062859,
      "grad_norm": 1.742013451785388,
      "learning_rate": 5e-06,
      "loss": 0.6363,
      "step": 40
    },
    {
      "epoch": 0.13518080432578575,
      "grad_norm": 1.9825861616522564,
      "learning_rate": 5e-06,
      "loss": 0.6212,
      "step": 50
    },
    {
      "epoch": 0.1622169651909429,
      "grad_norm": 1.963028689906959,
      "learning_rate": 5e-06,
      "loss": 0.6158,
      "step": 60
    },
    {
      "epoch": 0.18925312605610004,
      "grad_norm": 1.5400134410581494,
      "learning_rate": 5e-06,
      "loss": 0.6126,
      "step": 70
    },
    {
      "epoch": 0.21628928692125718,
      "grad_norm": 1.7957880103549582,
      "learning_rate": 5e-06,
      "loss": 0.6046,
      "step": 80
    },
    {
      "epoch": 0.24332544778641432,
      "grad_norm": 2.0825972162611626,
      "learning_rate": 5e-06,
      "loss": 0.6015,
      "step": 90
    },
    {
      "epoch": 0.2703616086515715,
      "grad_norm": 1.5684743614874819,
      "learning_rate": 5e-06,
      "loss": 0.6044,
      "step": 100
    },
    {
      "epoch": 0.29739776951672864,
      "grad_norm": 1.5536576895608207,
      "learning_rate": 5e-06,
      "loss": 0.6009,
      "step": 110
    },
    {
      "epoch": 0.3244339303818858,
      "grad_norm": 1.9211273900718062,
      "learning_rate": 5e-06,
      "loss": 0.5959,
      "step": 120
    },
    {
      "epoch": 0.3514700912470429,
      "grad_norm": 1.857918426411918,
      "learning_rate": 5e-06,
      "loss": 0.5981,
      "step": 130
    },
    {
      "epoch": 0.37850625211220007,
      "grad_norm": 2.480111887309551,
      "learning_rate": 5e-06,
      "loss": 0.5972,
      "step": 140
    },
    {
      "epoch": 0.4055424129773572,
      "grad_norm": 1.9435865546624187,
      "learning_rate": 5e-06,
      "loss": 0.589,
      "step": 150
    },
    {
      "epoch": 0.43257857384251436,
      "grad_norm": 2.256806266648931,
      "learning_rate": 5e-06,
      "loss": 0.5905,
      "step": 160
    },
    {
      "epoch": 0.4596147347076715,
      "grad_norm": 1.9395141957859183,
      "learning_rate": 5e-06,
      "loss": 0.5907,
      "step": 170
    },
    {
      "epoch": 0.48665089557282865,
      "grad_norm": 1.70470436825217,
      "learning_rate": 5e-06,
      "loss": 0.5891,
      "step": 180
    },
    {
      "epoch": 0.5136870564379858,
      "grad_norm": 1.2803454947922437,
      "learning_rate": 5e-06,
      "loss": 0.5864,
      "step": 190
    },
    {
      "epoch": 0.540723217303143,
      "grad_norm": 1.6583430834053514,
      "learning_rate": 5e-06,
      "loss": 0.5845,
      "step": 200
    },
    {
      "epoch": 0.5677593781683001,
      "grad_norm": 1.6236160787848246,
      "learning_rate": 5e-06,
      "loss": 0.5873,
      "step": 210
    },
    {
      "epoch": 0.5947955390334573,
      "grad_norm": 1.4448675180275712,
      "learning_rate": 5e-06,
      "loss": 0.5829,
      "step": 220
    },
    {
      "epoch": 0.6218316998986144,
      "grad_norm": 1.5221126449990794,
      "learning_rate": 5e-06,
      "loss": 0.5844,
      "step": 230
    },
    {
      "epoch": 0.6488678607637716,
      "grad_norm": 1.3401517373172736,
      "learning_rate": 5e-06,
      "loss": 0.581,
      "step": 240
    },
    {
      "epoch": 0.6759040216289287,
      "grad_norm": 3.0974221570456697,
      "learning_rate": 5e-06,
      "loss": 0.5751,
      "step": 250
    },
    {
      "epoch": 0.7029401824940859,
      "grad_norm": 1.7078786998431879,
      "learning_rate": 5e-06,
      "loss": 0.5786,
      "step": 260
    },
    {
      "epoch": 0.729976343359243,
      "grad_norm": 1.3452565169314334,
      "learning_rate": 5e-06,
      "loss": 0.5802,
      "step": 270
    },
    {
      "epoch": 0.7570125042244001,
      "grad_norm": 1.2754169661691006,
      "learning_rate": 5e-06,
      "loss": 0.5753,
      "step": 280
    },
    {
      "epoch": 0.7840486650895573,
      "grad_norm": 1.561813747345879,
      "learning_rate": 5e-06,
      "loss": 0.5756,
      "step": 290
    },
    {
      "epoch": 0.8110848259547144,
      "grad_norm": 1.4562454979417123,
      "learning_rate": 5e-06,
      "loss": 0.5754,
      "step": 300
    },
    {
      "epoch": 0.8381209868198716,
      "grad_norm": 1.3655414659589415,
      "learning_rate": 5e-06,
      "loss": 0.5731,
      "step": 310
    },
    {
      "epoch": 0.8651571476850287,
      "grad_norm": 1.57353294016275,
      "learning_rate": 5e-06,
      "loss": 0.5721,
      "step": 320
    },
    {
      "epoch": 0.8921933085501859,
      "grad_norm": 1.9418137004471465,
      "learning_rate": 5e-06,
      "loss": 0.5736,
      "step": 330
    },
    {
      "epoch": 0.919229469415343,
      "grad_norm": 1.6960343893725316,
      "learning_rate": 5e-06,
      "loss": 0.5806,
      "step": 340
    },
    {
      "epoch": 0.9462656302805001,
      "grad_norm": 2.406507142621058,
      "learning_rate": 5e-06,
      "loss": 0.5714,
      "step": 350
    },
    {
      "epoch": 0.9733017911456573,
      "grad_norm": 1.9230224466359063,
      "learning_rate": 5e-06,
      "loss": 0.5704,
      "step": 360
    },
    {
      "epoch": 0.9976343359242987,
      "eval_loss": 0.07099956274032593,
      "eval_runtime": 383.3884,
      "eval_samples_per_second": 25.992,
      "eval_steps_per_second": 0.407,
      "step": 369
    },
    {
      "epoch": 1.0023656640757013,
      "grad_norm": 3.4559216993428326,
      "learning_rate": 5e-06,
      "loss": 0.5655,
      "step": 370
    },
    {
      "epoch": 1.0294018249408583,
      "grad_norm": 2.6945339527227783,
      "learning_rate": 5e-06,
      "loss": 0.4803,
      "step": 380
    },
    {
      "epoch": 1.0564379858060156,
      "grad_norm": 2.274860352040799,
      "learning_rate": 5e-06,
      "loss": 0.4751,
      "step": 390
    },
    {
      "epoch": 1.0834741466711728,
      "grad_norm": 1.9418080331159586,
      "learning_rate": 5e-06,
      "loss": 0.4775,
      "step": 400
    },
    {
      "epoch": 1.1105103075363298,
      "grad_norm": 1.3221563752390588,
      "learning_rate": 5e-06,
      "loss": 0.4751,
      "step": 410
    },
    {
      "epoch": 1.1375464684014869,
      "grad_norm": 1.6270959849174909,
      "learning_rate": 5e-06,
      "loss": 0.4773,
      "step": 420
    },
    {
      "epoch": 1.1645826292666441,
      "grad_norm": 1.723481598695817,
      "learning_rate": 5e-06,
      "loss": 0.4861,
      "step": 430
    },
    {
      "epoch": 1.1916187901318014,
      "grad_norm": 1.6689122667194243,
      "learning_rate": 5e-06,
      "loss": 0.4771,
      "step": 440
    },
    {
      "epoch": 1.2186549509969584,
      "grad_norm": 1.8852129756960698,
      "learning_rate": 5e-06,
      "loss": 0.4817,
      "step": 450
    },
    {
      "epoch": 1.2456911118621157,
      "grad_norm": 1.5781803973122046,
      "learning_rate": 5e-06,
      "loss": 0.4832,
      "step": 460
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 1.8932565449503365,
      "learning_rate": 5e-06,
      "loss": 0.4855,
      "step": 470
    },
    {
      "epoch": 1.29976343359243,
      "grad_norm": 1.5040934591134398,
      "learning_rate": 5e-06,
      "loss": 0.4816,
      "step": 480
    },
    {
      "epoch": 1.326799594457587,
      "grad_norm": 1.415624345433887,
      "learning_rate": 5e-06,
      "loss": 0.4817,
      "step": 490
    },
    {
      "epoch": 1.3538357553227442,
      "grad_norm": 1.4726186128545236,
      "learning_rate": 5e-06,
      "loss": 0.4859,
      "step": 500
    },
    {
      "epoch": 1.3808719161879013,
      "grad_norm": 1.371837855586058,
      "learning_rate": 5e-06,
      "loss": 0.4862,
      "step": 510
    },
    {
      "epoch": 1.4079080770530585,
      "grad_norm": 1.625255953470612,
      "learning_rate": 5e-06,
      "loss": 0.4899,
      "step": 520
    },
    {
      "epoch": 1.4349442379182156,
      "grad_norm": 1.4470657655644708,
      "learning_rate": 5e-06,
      "loss": 0.484,
      "step": 530
    },
    {
      "epoch": 1.4619803987833728,
      "grad_norm": 1.4168708504506906,
      "learning_rate": 5e-06,
      "loss": 0.489,
      "step": 540
    },
    {
      "epoch": 1.4890165596485299,
      "grad_norm": 1.2953354115079219,
      "learning_rate": 5e-06,
      "loss": 0.4876,
      "step": 550
    },
    {
      "epoch": 1.5160527205136871,
      "grad_norm": 1.2905587316106748,
      "learning_rate": 5e-06,
      "loss": 0.4898,
      "step": 560
    },
    {
      "epoch": 1.5430888813788441,
      "grad_norm": 1.874461693755812,
      "learning_rate": 5e-06,
      "loss": 0.4852,
      "step": 570
    },
    {
      "epoch": 1.5701250422440014,
      "grad_norm": 1.537393515627057,
      "learning_rate": 5e-06,
      "loss": 0.4874,
      "step": 580
    },
    {
      "epoch": 1.5971612031091587,
      "grad_norm": 1.7234212392856714,
      "learning_rate": 5e-06,
      "loss": 0.4911,
      "step": 590
    },
    {
      "epoch": 1.6241973639743157,
      "grad_norm": 1.4569000028167551,
      "learning_rate": 5e-06,
      "loss": 0.487,
      "step": 600
    },
    {
      "epoch": 1.6512335248394727,
      "grad_norm": 1.4876997193606485,
      "learning_rate": 5e-06,
      "loss": 0.4854,
      "step": 610
    },
    {
      "epoch": 1.67826968570463,
      "grad_norm": 1.4853131850089583,
      "learning_rate": 5e-06,
      "loss": 0.4902,
      "step": 620
    },
    {
      "epoch": 1.7053058465697872,
      "grad_norm": 1.4854501350323384,
      "learning_rate": 5e-06,
      "loss": 0.4952,
      "step": 630
    },
    {
      "epoch": 1.7323420074349443,
      "grad_norm": 1.613201730070182,
      "learning_rate": 5e-06,
      "loss": 0.493,
      "step": 640
    },
    {
      "epoch": 1.7593781683001013,
      "grad_norm": 1.3411867074544503,
      "learning_rate": 5e-06,
      "loss": 0.4904,
      "step": 650
    },
    {
      "epoch": 1.7864143291652586,
      "grad_norm": 1.3453881021060534,
      "learning_rate": 5e-06,
      "loss": 0.4879,
      "step": 660
    },
    {
      "epoch": 1.8134504900304158,
      "grad_norm": 1.4275860747925428,
      "learning_rate": 5e-06,
      "loss": 0.4904,
      "step": 670
    },
    {
      "epoch": 1.8404866508955728,
      "grad_norm": 1.3712075307477265,
      "learning_rate": 5e-06,
      "loss": 0.4935,
      "step": 680
    },
    {
      "epoch": 1.8675228117607299,
      "grad_norm": 1.2986482215538881,
      "learning_rate": 5e-06,
      "loss": 0.4917,
      "step": 690
    },
    {
      "epoch": 1.8945589726258871,
      "grad_norm": 1.2770662158812232,
      "learning_rate": 5e-06,
      "loss": 0.4943,
      "step": 700
    },
    {
      "epoch": 1.9215951334910444,
      "grad_norm": 1.2971456378708284,
      "learning_rate": 5e-06,
      "loss": 0.4994,
      "step": 710
    },
    {
      "epoch": 1.9486312943562014,
      "grad_norm": 1.2953045522832038,
      "learning_rate": 5e-06,
      "loss": 0.4927,
      "step": 720
    },
    {
      "epoch": 1.9756674552213584,
      "grad_norm": 1.2187798944947157,
      "learning_rate": 5e-06,
      "loss": 0.4886,
      "step": 730
    },
    {
      "epoch": 1.9972963839134843,
      "eval_loss": 0.07174264639616013,
      "eval_runtime": 383.5066,
      "eval_samples_per_second": 25.984,
      "eval_steps_per_second": 0.407,
      "step": 738
    },
    {
      "epoch": 2.0047313281514025,
      "grad_norm": 3.2606644157882583,
      "learning_rate": 5e-06,
      "loss": 0.477,
      "step": 740
    },
    {
      "epoch": 2.0317674890165596,
      "grad_norm": 1.997812835463083,
      "learning_rate": 5e-06,
      "loss": 0.3854,
      "step": 750
    },
    {
      "epoch": 2.0588036498817166,
      "grad_norm": 1.9996540417166961,
      "learning_rate": 5e-06,
      "loss": 0.3864,
      "step": 760
    },
    {
      "epoch": 2.085839810746874,
      "grad_norm": 1.8618681796717789,
      "learning_rate": 5e-06,
      "loss": 0.3812,
      "step": 770
    },
    {
      "epoch": 2.112875971612031,
      "grad_norm": 1.4915524529602713,
      "learning_rate": 5e-06,
      "loss": 0.3811,
      "step": 780
    },
    {
      "epoch": 2.139912132477188,
      "grad_norm": 1.5723106961760522,
      "learning_rate": 5e-06,
      "loss": 0.3808,
      "step": 790
    },
    {
      "epoch": 2.1669482933423456,
      "grad_norm": 1.714466030885258,
      "learning_rate": 5e-06,
      "loss": 0.3876,
      "step": 800
    },
    {
      "epoch": 2.1939844542075027,
      "grad_norm": 1.7511244660613634,
      "learning_rate": 5e-06,
      "loss": 0.3862,
      "step": 810
    },
    {
      "epoch": 2.2210206150726597,
      "grad_norm": 1.5027273200313567,
      "learning_rate": 5e-06,
      "loss": 0.3873,
      "step": 820
    },
    {
      "epoch": 2.2480567759378167,
      "grad_norm": 1.6128980496405356,
      "learning_rate": 5e-06,
      "loss": 0.3896,
      "step": 830
    },
    {
      "epoch": 2.2750929368029738,
      "grad_norm": 1.561276115932866,
      "learning_rate": 5e-06,
      "loss": 0.3909,
      "step": 840
    },
    {
      "epoch": 2.3021290976681312,
      "grad_norm": 1.7787495204510098,
      "learning_rate": 5e-06,
      "loss": 0.3866,
      "step": 850
    },
    {
      "epoch": 2.3291652585332883,
      "grad_norm": 1.5802735443144562,
      "learning_rate": 5e-06,
      "loss": 0.3896,
      "step": 860
    },
    {
      "epoch": 2.3562014193984453,
      "grad_norm": 1.5469387511116455,
      "learning_rate": 5e-06,
      "loss": 0.3948,
      "step": 870
    },
    {
      "epoch": 2.3832375802636028,
      "grad_norm": 1.6780934080456225,
      "learning_rate": 5e-06,
      "loss": 0.3937,
      "step": 880
    },
    {
      "epoch": 2.41027374112876,
      "grad_norm": 1.5538724349535749,
      "learning_rate": 5e-06,
      "loss": 0.3933,
      "step": 890
    },
    {
      "epoch": 2.437309901993917,
      "grad_norm": 1.6919213854745063,
      "learning_rate": 5e-06,
      "loss": 0.3927,
      "step": 900
    },
    {
      "epoch": 2.464346062859074,
      "grad_norm": 1.6467399942324181,
      "learning_rate": 5e-06,
      "loss": 0.3916,
      "step": 910
    },
    {
      "epoch": 2.4913822237242313,
      "grad_norm": 1.5494538660407549,
      "learning_rate": 5e-06,
      "loss": 0.393,
      "step": 920
    },
    {
      "epoch": 2.5184183845893884,
      "grad_norm": 1.6061582119048823,
      "learning_rate": 5e-06,
      "loss": 0.392,
      "step": 930
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.5497867717979459,
      "learning_rate": 5e-06,
      "loss": 0.3996,
      "step": 940
    },
    {
      "epoch": 2.5724907063197024,
      "grad_norm": 1.8696325727031804,
      "learning_rate": 5e-06,
      "loss": 0.3949,
      "step": 950
    },
    {
      "epoch": 2.59952686718486,
      "grad_norm": 1.6545052949984496,
      "learning_rate": 5e-06,
      "loss": 0.4002,
      "step": 960
    },
    {
      "epoch": 2.626563028050017,
      "grad_norm": 1.5124642558655546,
      "learning_rate": 5e-06,
      "loss": 0.3988,
      "step": 970
    },
    {
      "epoch": 2.653599188915174,
      "grad_norm": 1.559510310440385,
      "learning_rate": 5e-06,
      "loss": 0.4024,
      "step": 980
    },
    {
      "epoch": 2.6806353497803315,
      "grad_norm": 1.676052966396514,
      "learning_rate": 5e-06,
      "loss": 0.4007,
      "step": 990
    },
    {
      "epoch": 2.7076715106454885,
      "grad_norm": 2.1046446839691,
      "learning_rate": 5e-06,
      "loss": 0.3952,
      "step": 1000
    },
    {
      "epoch": 2.7347076715106455,
      "grad_norm": 2.0451177849286464,
      "learning_rate": 5e-06,
      "loss": 0.4021,
      "step": 1010
    },
    {
      "epoch": 2.7617438323758026,
      "grad_norm": 1.6691707308120913,
      "learning_rate": 5e-06,
      "loss": 0.4046,
      "step": 1020
    },
    {
      "epoch": 2.7887799932409596,
      "grad_norm": 1.4465197945931527,
      "learning_rate": 5e-06,
      "loss": 0.4022,
      "step": 1030
    },
    {
      "epoch": 2.815816154106117,
      "grad_norm": 1.4351190888202614,
      "learning_rate": 5e-06,
      "loss": 0.4014,
      "step": 1040
    },
    {
      "epoch": 2.842852314971274,
      "grad_norm": 1.485706611946695,
      "learning_rate": 5e-06,
      "loss": 0.4034,
      "step": 1050
    },
    {
      "epoch": 2.869888475836431,
      "grad_norm": 1.4860832182563435,
      "learning_rate": 5e-06,
      "loss": 0.3996,
      "step": 1060
    },
    {
      "epoch": 2.8969246367015886,
      "grad_norm": 1.5630718102725172,
      "learning_rate": 5e-06,
      "loss": 0.4077,
      "step": 1070
    },
    {
      "epoch": 2.9239607975667457,
      "grad_norm": 1.4737818975824717,
      "learning_rate": 5e-06,
      "loss": 0.4027,
      "step": 1080
    },
    {
      "epoch": 2.9509969584319027,
      "grad_norm": 1.5487795543993597,
      "learning_rate": 5e-06,
      "loss": 0.406,
      "step": 1090
    },
    {
      "epoch": 2.9780331192970597,
      "grad_norm": 1.3628828414709748,
      "learning_rate": 5e-06,
      "loss": 0.4047,
      "step": 1100
    },
    {
      "epoch": 2.99695843190267,
      "eval_loss": 0.07649385929107666,
      "eval_runtime": 385.8472,
      "eval_samples_per_second": 25.826,
      "eval_steps_per_second": 0.404,
      "step": 1107
    },
    {
      "epoch": 2.99695843190267,
      "step": 1107,
      "total_flos": 1854056851046400.0,
      "train_loss": 0.49424083467636865,
      "train_runtime": 64065.8676,
      "train_samples_per_second": 8.866,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 1107,
  "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": 1854056851046400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}