{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.997827661115134,
  "eval_steps": 500,
  "global_step": 1035,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02896451846488052,
      "grad_norm": 1.9546706041531023,
      "learning_rate": 5e-06,
      "loss": 1.0679,
      "step": 10
    },
    {
      "epoch": 0.05792903692976104,
      "grad_norm": 5.4683536223610085,
      "learning_rate": 5e-06,
      "loss": 0.9613,
      "step": 20
    },
    {
      "epoch": 0.08689355539464157,
      "grad_norm": 1.6939976541654087,
      "learning_rate": 5e-06,
      "loss": 0.9223,
      "step": 30
    },
    {
      "epoch": 0.11585807385952208,
      "grad_norm": 1.0339182103747349,
      "learning_rate": 5e-06,
      "loss": 0.8975,
      "step": 40
    },
    {
      "epoch": 0.14482259232440262,
      "grad_norm": 0.9491704034528055,
      "learning_rate": 5e-06,
      "loss": 0.88,
      "step": 50
    },
    {
      "epoch": 0.17378711078928313,
      "grad_norm": 1.2085381768876486,
      "learning_rate": 5e-06,
      "loss": 0.8621,
      "step": 60
    },
    {
      "epoch": 0.20275162925416365,
      "grad_norm": 1.4117640839833099,
      "learning_rate": 5e-06,
      "loss": 0.8519,
      "step": 70
    },
    {
      "epoch": 0.23171614771904417,
      "grad_norm": 1.1514550106019426,
      "learning_rate": 5e-06,
      "loss": 0.8438,
      "step": 80
    },
    {
      "epoch": 0.2606806661839247,
      "grad_norm": 0.9243756138786047,
      "learning_rate": 5e-06,
      "loss": 0.8335,
      "step": 90
    },
    {
      "epoch": 0.28964518464880523,
      "grad_norm": 0.846545720738904,
      "learning_rate": 5e-06,
      "loss": 0.8269,
      "step": 100
    },
    {
      "epoch": 0.31860970311368575,
      "grad_norm": 0.5825470716035409,
      "learning_rate": 5e-06,
      "loss": 0.8194,
      "step": 110
    },
    {
      "epoch": 0.34757422157856627,
      "grad_norm": 0.7173313925098385,
      "learning_rate": 5e-06,
      "loss": 0.8195,
      "step": 120
    },
    {
      "epoch": 0.3765387400434468,
      "grad_norm": 0.7287411570445328,
      "learning_rate": 5e-06,
      "loss": 0.8156,
      "step": 130
    },
    {
      "epoch": 0.4055032585083273,
      "grad_norm": 0.7081477098458706,
      "learning_rate": 5e-06,
      "loss": 0.8116,
      "step": 140
    },
    {
      "epoch": 0.4344677769732078,
      "grad_norm": 0.8598043962323773,
      "learning_rate": 5e-06,
      "loss": 0.8135,
      "step": 150
    },
    {
      "epoch": 0.46343229543808834,
      "grad_norm": 0.5450111798416236,
      "learning_rate": 5e-06,
      "loss": 0.8074,
      "step": 160
    },
    {
      "epoch": 0.49239681390296886,
      "grad_norm": 0.939010922813204,
      "learning_rate": 5e-06,
      "loss": 0.8062,
      "step": 170
    },
    {
      "epoch": 0.5213613323678494,
      "grad_norm": 0.847543033032073,
      "learning_rate": 5e-06,
      "loss": 0.8029,
      "step": 180
    },
    {
      "epoch": 0.5503258508327299,
      "grad_norm": 0.8787853615954785,
      "learning_rate": 5e-06,
      "loss": 0.8006,
      "step": 190
    },
    {
      "epoch": 0.5792903692976105,
      "grad_norm": 1.0063082389466802,
      "learning_rate": 5e-06,
      "loss": 0.8009,
      "step": 200
    },
    {
      "epoch": 0.6082548877624909,
      "grad_norm": 0.6359141777605319,
      "learning_rate": 5e-06,
      "loss": 0.7989,
      "step": 210
    },
    {
      "epoch": 0.6372194062273715,
      "grad_norm": 0.6914513445032724,
      "learning_rate": 5e-06,
      "loss": 0.7942,
      "step": 220
    },
    {
      "epoch": 0.666183924692252,
      "grad_norm": 0.6878895702782952,
      "learning_rate": 5e-06,
      "loss": 0.7916,
      "step": 230
    },
    {
      "epoch": 0.6951484431571325,
      "grad_norm": 0.5660450961011149,
      "learning_rate": 5e-06,
      "loss": 0.7874,
      "step": 240
    },
    {
      "epoch": 0.724112961622013,
      "grad_norm": 0.5744944170750963,
      "learning_rate": 5e-06,
      "loss": 0.7853,
      "step": 250
    },
    {
      "epoch": 0.7530774800868936,
      "grad_norm": 0.8500170302127678,
      "learning_rate": 5e-06,
      "loss": 0.7868,
      "step": 260
    },
    {
      "epoch": 0.782041998551774,
      "grad_norm": 0.9550149697236748,
      "learning_rate": 5e-06,
      "loss": 0.7901,
      "step": 270
    },
    {
      "epoch": 0.8110065170166546,
      "grad_norm": 0.5546890467469614,
      "learning_rate": 5e-06,
      "loss": 0.7864,
      "step": 280
    },
    {
      "epoch": 0.8399710354815351,
      "grad_norm": 0.6331265595090024,
      "learning_rate": 5e-06,
      "loss": 0.788,
      "step": 290
    },
    {
      "epoch": 0.8689355539464156,
      "grad_norm": 0.6196206182624663,
      "learning_rate": 5e-06,
      "loss": 0.782,
      "step": 300
    },
    {
      "epoch": 0.8979000724112962,
      "grad_norm": 0.7124233685042775,
      "learning_rate": 5e-06,
      "loss": 0.7814,
      "step": 310
    },
    {
      "epoch": 0.9268645908761767,
      "grad_norm": 0.6281001430065685,
      "learning_rate": 5e-06,
      "loss": 0.7821,
      "step": 320
    },
    {
      "epoch": 0.9558291093410572,
      "grad_norm": 0.6288445991938771,
      "learning_rate": 5e-06,
      "loss": 0.7835,
      "step": 330
    },
    {
      "epoch": 0.9847936278059377,
      "grad_norm": 0.5963707636678538,
      "learning_rate": 5e-06,
      "loss": 0.785,
      "step": 340
    },
    {
      "epoch": 0.999275887038378,
      "eval_loss": 0.7745929956436157,
      "eval_runtime": 243.4419,
      "eval_samples_per_second": 38.21,
      "eval_steps_per_second": 0.6,
      "step": 345
    },
    {
      "epoch": 1.0137581462708183,
      "grad_norm": 0.887536909694853,
      "learning_rate": 5e-06,
      "loss": 0.8189,
      "step": 350
    },
    {
      "epoch": 1.0427226647356989,
      "grad_norm": 0.9746717296866173,
      "learning_rate": 5e-06,
      "loss": 0.7355,
      "step": 360
    },
    {
      "epoch": 1.0716871832005792,
      "grad_norm": 0.6469650977983997,
      "learning_rate": 5e-06,
      "loss": 0.734,
      "step": 370
    },
    {
      "epoch": 1.1006517016654598,
      "grad_norm": 0.7891671650419445,
      "learning_rate": 5e-06,
      "loss": 0.7328,
      "step": 380
    },
    {
      "epoch": 1.1296162201303404,
      "grad_norm": 0.6208155398032233,
      "learning_rate": 5e-06,
      "loss": 0.732,
      "step": 390
    },
    {
      "epoch": 1.158580738595221,
      "grad_norm": 0.6207300417186483,
      "learning_rate": 5e-06,
      "loss": 0.7297,
      "step": 400
    },
    {
      "epoch": 1.1875452570601013,
      "grad_norm": 0.6785729802747962,
      "learning_rate": 5e-06,
      "loss": 0.7341,
      "step": 410
    },
    {
      "epoch": 1.2165097755249819,
      "grad_norm": 0.8266342046421713,
      "learning_rate": 5e-06,
      "loss": 0.7323,
      "step": 420
    },
    {
      "epoch": 1.2454742939898624,
      "grad_norm": 0.9660234843621154,
      "learning_rate": 5e-06,
      "loss": 0.7306,
      "step": 430
    },
    {
      "epoch": 1.274438812454743,
      "grad_norm": 0.6935390944005595,
      "learning_rate": 5e-06,
      "loss": 0.7319,
      "step": 440
    },
    {
      "epoch": 1.3034033309196236,
      "grad_norm": 0.5941658732015132,
      "learning_rate": 5e-06,
      "loss": 0.7363,
      "step": 450
    },
    {
      "epoch": 1.332367849384504,
      "grad_norm": 0.590155807756852,
      "learning_rate": 5e-06,
      "loss": 0.7324,
      "step": 460
    },
    {
      "epoch": 1.3613323678493845,
      "grad_norm": 0.6352796068632335,
      "learning_rate": 5e-06,
      "loss": 0.7305,
      "step": 470
    },
    {
      "epoch": 1.390296886314265,
      "grad_norm": 0.6933255949901775,
      "learning_rate": 5e-06,
      "loss": 0.7335,
      "step": 480
    },
    {
      "epoch": 1.4192614047791454,
      "grad_norm": 0.5969978905166637,
      "learning_rate": 5e-06,
      "loss": 0.7331,
      "step": 490
    },
    {
      "epoch": 1.448225923244026,
      "grad_norm": 0.5822244996224603,
      "learning_rate": 5e-06,
      "loss": 0.7316,
      "step": 500
    },
    {
      "epoch": 1.4771904417089066,
      "grad_norm": 0.6473397313720373,
      "learning_rate": 5e-06,
      "loss": 0.7325,
      "step": 510
    },
    {
      "epoch": 1.5061549601737871,
      "grad_norm": 0.7379810742604224,
      "learning_rate": 5e-06,
      "loss": 0.7322,
      "step": 520
    },
    {
      "epoch": 1.5351194786386677,
      "grad_norm": 0.877777055252363,
      "learning_rate": 5e-06,
      "loss": 0.7267,
      "step": 530
    },
    {
      "epoch": 1.5640839971035483,
      "grad_norm": 0.702500798809481,
      "learning_rate": 5e-06,
      "loss": 0.7278,
      "step": 540
    },
    {
      "epoch": 1.5930485155684286,
      "grad_norm": 0.7082980837667808,
      "learning_rate": 5e-06,
      "loss": 0.7282,
      "step": 550
    },
    {
      "epoch": 1.6220130340333092,
      "grad_norm": 0.6193169422318507,
      "learning_rate": 5e-06,
      "loss": 0.7322,
      "step": 560
    },
    {
      "epoch": 1.6509775524981896,
      "grad_norm": 0.6349696489382688,
      "learning_rate": 5e-06,
      "loss": 0.7272,
      "step": 570
    },
    {
      "epoch": 1.6799420709630701,
      "grad_norm": 0.5808865809115293,
      "learning_rate": 5e-06,
      "loss": 0.7256,
      "step": 580
    },
    {
      "epoch": 1.7089065894279507,
      "grad_norm": 0.5965976052156886,
      "learning_rate": 5e-06,
      "loss": 0.7222,
      "step": 590
    },
    {
      "epoch": 1.7378711078928313,
      "grad_norm": 0.5710627722704887,
      "learning_rate": 5e-06,
      "loss": 0.7297,
      "step": 600
    },
    {
      "epoch": 1.7668356263577119,
      "grad_norm": 0.608816224452555,
      "learning_rate": 5e-06,
      "loss": 0.7262,
      "step": 610
    },
    {
      "epoch": 1.7958001448225924,
      "grad_norm": 0.6371768739478637,
      "learning_rate": 5e-06,
      "loss": 0.7303,
      "step": 620
    },
    {
      "epoch": 1.824764663287473,
      "grad_norm": 0.5358050463696646,
      "learning_rate": 5e-06,
      "loss": 0.7287,
      "step": 630
    },
    {
      "epoch": 1.8537291817523533,
      "grad_norm": 0.7036505719286567,
      "learning_rate": 5e-06,
      "loss": 0.7247,
      "step": 640
    },
    {
      "epoch": 1.882693700217234,
      "grad_norm": 0.6805629942635829,
      "learning_rate": 5e-06,
      "loss": 0.7294,
      "step": 650
    },
    {
      "epoch": 1.9116582186821143,
      "grad_norm": 0.6498078585112878,
      "learning_rate": 5e-06,
      "loss": 0.7289,
      "step": 660
    },
    {
      "epoch": 1.9406227371469948,
      "grad_norm": 0.5784132159085213,
      "learning_rate": 5e-06,
      "loss": 0.7296,
      "step": 670
    },
    {
      "epoch": 1.9695872556118754,
      "grad_norm": 0.5796673295424948,
      "learning_rate": 5e-06,
      "loss": 0.7277,
      "step": 680
    },
    {
      "epoch": 1.998551774076756,
      "grad_norm": 0.5936807614505102,
      "learning_rate": 5e-06,
      "loss": 0.72,
      "step": 690
    },
    {
      "epoch": 1.998551774076756,
      "eval_loss": 0.7591201663017273,
      "eval_runtime": 239.3101,
      "eval_samples_per_second": 38.87,
      "eval_steps_per_second": 0.61,
      "step": 690
    },
    {
      "epoch": 2.0275162925416366,
      "grad_norm": 0.715729072917497,
      "learning_rate": 5e-06,
      "loss": 0.7321,
      "step": 700
    },
    {
      "epoch": 2.056480811006517,
      "grad_norm": 0.6144874116006872,
      "learning_rate": 5e-06,
      "loss": 0.6723,
      "step": 710
    },
    {
      "epoch": 2.0854453294713977,
      "grad_norm": 0.7303697849008477,
      "learning_rate": 5e-06,
      "loss": 0.6804,
      "step": 720
    },
    {
      "epoch": 2.114409847936278,
      "grad_norm": 0.68311827138117,
      "learning_rate": 5e-06,
      "loss": 0.6797,
      "step": 730
    },
    {
      "epoch": 2.1433743664011584,
      "grad_norm": 0.5545659750688543,
      "learning_rate": 5e-06,
      "loss": 0.6733,
      "step": 740
    },
    {
      "epoch": 2.172338884866039,
      "grad_norm": 0.5612265877265745,
      "learning_rate": 5e-06,
      "loss": 0.6807,
      "step": 750
    },
    {
      "epoch": 2.2013034033309196,
      "grad_norm": 0.6652869497470263,
      "learning_rate": 5e-06,
      "loss": 0.6836,
      "step": 760
    },
    {
      "epoch": 2.2302679217958,
      "grad_norm": 0.5387482606960555,
      "learning_rate": 5e-06,
      "loss": 0.6782,
      "step": 770
    },
    {
      "epoch": 2.2592324402606807,
      "grad_norm": 0.9270487907700882,
      "learning_rate": 5e-06,
      "loss": 0.6792,
      "step": 780
    },
    {
      "epoch": 2.2881969587255613,
      "grad_norm": 0.5940033865543676,
      "learning_rate": 5e-06,
      "loss": 0.6839,
      "step": 790
    },
    {
      "epoch": 2.317161477190442,
      "grad_norm": 0.6205717881980902,
      "learning_rate": 5e-06,
      "loss": 0.6793,
      "step": 800
    },
    {
      "epoch": 2.3461259956553224,
      "grad_norm": 0.7863817807933237,
      "learning_rate": 5e-06,
      "loss": 0.6771,
      "step": 810
    },
    {
      "epoch": 2.3750905141202026,
      "grad_norm": 0.6565632670788291,
      "learning_rate": 5e-06,
      "loss": 0.6834,
      "step": 820
    },
    {
      "epoch": 2.404055032585083,
      "grad_norm": 0.6373382549439205,
      "learning_rate": 5e-06,
      "loss": 0.6828,
      "step": 830
    },
    {
      "epoch": 2.4330195510499637,
      "grad_norm": 0.6613391820459834,
      "learning_rate": 5e-06,
      "loss": 0.6835,
      "step": 840
    },
    {
      "epoch": 2.4619840695148443,
      "grad_norm": 0.5400957321029153,
      "learning_rate": 5e-06,
      "loss": 0.6852,
      "step": 850
    },
    {
      "epoch": 2.490948587979725,
      "grad_norm": 0.6001602197216074,
      "learning_rate": 5e-06,
      "loss": 0.6813,
      "step": 860
    },
    {
      "epoch": 2.5199131064446054,
      "grad_norm": 0.6758144590327261,
      "learning_rate": 5e-06,
      "loss": 0.6846,
      "step": 870
    },
    {
      "epoch": 2.548877624909486,
      "grad_norm": 0.7279056638638517,
      "learning_rate": 5e-06,
      "loss": 0.6806,
      "step": 880
    },
    {
      "epoch": 2.577842143374366,
      "grad_norm": 0.6530599852985071,
      "learning_rate": 5e-06,
      "loss": 0.6818,
      "step": 890
    },
    {
      "epoch": 2.606806661839247,
      "grad_norm": 0.6780623323564912,
      "learning_rate": 5e-06,
      "loss": 0.6825,
      "step": 900
    },
    {
      "epoch": 2.6357711803041273,
      "grad_norm": 0.5837946750071207,
      "learning_rate": 5e-06,
      "loss": 0.6825,
      "step": 910
    },
    {
      "epoch": 2.664735698769008,
      "grad_norm": 0.5602013963713363,
      "learning_rate": 5e-06,
      "loss": 0.6834,
      "step": 920
    },
    {
      "epoch": 2.6937002172338884,
      "grad_norm": 0.7041458005241192,
      "learning_rate": 5e-06,
      "loss": 0.6808,
      "step": 930
    },
    {
      "epoch": 2.722664735698769,
      "grad_norm": 0.6490957944655403,
      "learning_rate": 5e-06,
      "loss": 0.6844,
      "step": 940
    },
    {
      "epoch": 2.7516292541636496,
      "grad_norm": 0.6599285105597698,
      "learning_rate": 5e-06,
      "loss": 0.6841,
      "step": 950
    },
    {
      "epoch": 2.78059377262853,
      "grad_norm": 0.8783093936780623,
      "learning_rate": 5e-06,
      "loss": 0.6805,
      "step": 960
    },
    {
      "epoch": 2.8095582910934107,
      "grad_norm": 0.6029880285970106,
      "learning_rate": 5e-06,
      "loss": 0.6836,
      "step": 970
    },
    {
      "epoch": 2.838522809558291,
      "grad_norm": 0.6433012731687247,
      "learning_rate": 5e-06,
      "loss": 0.6802,
      "step": 980
    },
    {
      "epoch": 2.867487328023172,
      "grad_norm": 0.6070387953228661,
      "learning_rate": 5e-06,
      "loss": 0.6779,
      "step": 990
    },
    {
      "epoch": 2.896451846488052,
      "grad_norm": 0.5805918805506912,
      "learning_rate": 5e-06,
      "loss": 0.6815,
      "step": 1000
    },
    {
      "epoch": 2.9254163649529326,
      "grad_norm": 0.6364227056673066,
      "learning_rate": 5e-06,
      "loss": 0.6828,
      "step": 1010
    },
    {
      "epoch": 2.954380883417813,
      "grad_norm": 0.7905206793090467,
      "learning_rate": 5e-06,
      "loss": 0.6884,
      "step": 1020
    },
    {
      "epoch": 2.9833454018826937,
      "grad_norm": 0.6878648180858722,
      "learning_rate": 5e-06,
      "loss": 0.685,
      "step": 1030
    },
    {
      "epoch": 2.997827661115134,
      "eval_loss": 0.7575626373291016,
      "eval_runtime": 234.038,
      "eval_samples_per_second": 39.746,
      "eval_steps_per_second": 0.624,
      "step": 1035
    },
    {
      "epoch": 2.997827661115134,
      "step": 1035,
      "total_flos": 1733454169374720.0,
      "train_loss": 0.7466064549874568,
      "train_runtime": 34327.0468,
      "train_samples_per_second": 15.444,
      "train_steps_per_second": 0.03
    }
  ],
  "logging_steps": 10,
  "max_steps": 1035,
  "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": 1733454169374720.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}