{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.995488721804511,
  "eval_steps": 500,
  "global_step": 996,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 5.823914796640075,
      "learning_rate": 5e-06,
      "loss": 0.801,
      "step": 10
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 2.3399969132192253,
      "learning_rate": 5e-06,
      "loss": 0.7172,
      "step": 20
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 0.8783578572732146,
      "learning_rate": 5e-06,
      "loss": 0.6923,
      "step": 30
    },
    {
      "epoch": 0.12030075187969924,
      "grad_norm": 1.7232554735132826,
      "learning_rate": 5e-06,
      "loss": 0.6834,
      "step": 40
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 1.6494035164725938,
      "learning_rate": 5e-06,
      "loss": 0.6655,
      "step": 50
    },
    {
      "epoch": 0.18045112781954886,
      "grad_norm": 0.9942658093552336,
      "learning_rate": 5e-06,
      "loss": 0.6568,
      "step": 60
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.8609069727317351,
      "learning_rate": 5e-06,
      "loss": 0.6548,
      "step": 70
    },
    {
      "epoch": 0.24060150375939848,
      "grad_norm": 0.8740060444495542,
      "learning_rate": 5e-06,
      "loss": 0.6454,
      "step": 80
    },
    {
      "epoch": 0.2706766917293233,
      "grad_norm": 1.0114201009544495,
      "learning_rate": 5e-06,
      "loss": 0.6331,
      "step": 90
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.782353210012559,
      "learning_rate": 5e-06,
      "loss": 0.6267,
      "step": 100
    },
    {
      "epoch": 0.3308270676691729,
      "grad_norm": 0.6061308240718153,
      "learning_rate": 5e-06,
      "loss": 0.6305,
      "step": 110
    },
    {
      "epoch": 0.3609022556390977,
      "grad_norm": 0.663886451339362,
      "learning_rate": 5e-06,
      "loss": 0.6246,
      "step": 120
    },
    {
      "epoch": 0.39097744360902253,
      "grad_norm": 0.8509285444900951,
      "learning_rate": 5e-06,
      "loss": 0.6305,
      "step": 130
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.650634026198435,
      "learning_rate": 5e-06,
      "loss": 0.6291,
      "step": 140
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 0.7050446482120244,
      "learning_rate": 5e-06,
      "loss": 0.6279,
      "step": 150
    },
    {
      "epoch": 0.48120300751879697,
      "grad_norm": 0.5260864128397903,
      "learning_rate": 5e-06,
      "loss": 0.6167,
      "step": 160
    },
    {
      "epoch": 0.5112781954887218,
      "grad_norm": 0.5159636362174167,
      "learning_rate": 5e-06,
      "loss": 0.6189,
      "step": 170
    },
    {
      "epoch": 0.5413533834586466,
      "grad_norm": 0.576027072578746,
      "learning_rate": 5e-06,
      "loss": 0.6096,
      "step": 180
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.6020714354457843,
      "learning_rate": 5e-06,
      "loss": 0.6207,
      "step": 190
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.8904744763001984,
      "learning_rate": 5e-06,
      "loss": 0.6143,
      "step": 200
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.5645606661034147,
      "learning_rate": 5e-06,
      "loss": 0.619,
      "step": 210
    },
    {
      "epoch": 0.6616541353383458,
      "grad_norm": 0.7456282489942,
      "learning_rate": 5e-06,
      "loss": 0.6229,
      "step": 220
    },
    {
      "epoch": 0.6917293233082706,
      "grad_norm": 0.47671003637879944,
      "learning_rate": 5e-06,
      "loss": 0.6141,
      "step": 230
    },
    {
      "epoch": 0.7218045112781954,
      "grad_norm": 0.5712162016443497,
      "learning_rate": 5e-06,
      "loss": 0.6148,
      "step": 240
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 0.5787527818544967,
      "learning_rate": 5e-06,
      "loss": 0.6112,
      "step": 250
    },
    {
      "epoch": 0.7819548872180451,
      "grad_norm": 0.7727895820276254,
      "learning_rate": 5e-06,
      "loss": 0.6124,
      "step": 260
    },
    {
      "epoch": 0.8120300751879699,
      "grad_norm": 0.6627350412484229,
      "learning_rate": 5e-06,
      "loss": 0.6101,
      "step": 270
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.49307733921025576,
      "learning_rate": 5e-06,
      "loss": 0.6101,
      "step": 280
    },
    {
      "epoch": 0.8721804511278195,
      "grad_norm": 0.5299740752648865,
      "learning_rate": 5e-06,
      "loss": 0.6074,
      "step": 290
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.9821666854504033,
      "learning_rate": 5e-06,
      "loss": 0.6035,
      "step": 300
    },
    {
      "epoch": 0.9323308270676691,
      "grad_norm": 0.5537120584191855,
      "learning_rate": 5e-06,
      "loss": 0.6037,
      "step": 310
    },
    {
      "epoch": 0.9624060150375939,
      "grad_norm": 0.5346047989400851,
      "learning_rate": 5e-06,
      "loss": 0.6128,
      "step": 320
    },
    {
      "epoch": 0.9924812030075187,
      "grad_norm": 0.5177704737274331,
      "learning_rate": 5e-06,
      "loss": 0.6043,
      "step": 330
    },
    {
      "epoch": 0.9984962406015038,
      "eval_loss": 0.6096732020378113,
      "eval_runtime": 116.9563,
      "eval_samples_per_second": 76.593,
      "eval_steps_per_second": 0.599,
      "step": 332
    },
    {
      "epoch": 1.0225563909774436,
      "grad_norm": 0.4996873605367385,
      "learning_rate": 5e-06,
      "loss": 0.58,
      "step": 340
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.59979801353788,
      "learning_rate": 5e-06,
      "loss": 0.5596,
      "step": 350
    },
    {
      "epoch": 1.0827067669172932,
      "grad_norm": 0.645810347625552,
      "learning_rate": 5e-06,
      "loss": 0.5591,
      "step": 360
    },
    {
      "epoch": 1.112781954887218,
      "grad_norm": 0.6113621459091085,
      "learning_rate": 5e-06,
      "loss": 0.5553,
      "step": 370
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.6400931476209645,
      "learning_rate": 5e-06,
      "loss": 0.5564,
      "step": 380
    },
    {
      "epoch": 1.1729323308270676,
      "grad_norm": 0.6192317007821239,
      "learning_rate": 5e-06,
      "loss": 0.5605,
      "step": 390
    },
    {
      "epoch": 1.2030075187969924,
      "grad_norm": 0.5237078678145406,
      "learning_rate": 5e-06,
      "loss": 0.5519,
      "step": 400
    },
    {
      "epoch": 1.2330827067669172,
      "grad_norm": 0.5140051147329998,
      "learning_rate": 5e-06,
      "loss": 0.5574,
      "step": 410
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 0.6369697944320184,
      "learning_rate": 5e-06,
      "loss": 0.5541,
      "step": 420
    },
    {
      "epoch": 1.2932330827067668,
      "grad_norm": 0.5985062376730702,
      "learning_rate": 5e-06,
      "loss": 0.5582,
      "step": 430
    },
    {
      "epoch": 1.3233082706766917,
      "grad_norm": 0.48850272868134653,
      "learning_rate": 5e-06,
      "loss": 0.5532,
      "step": 440
    },
    {
      "epoch": 1.3533834586466165,
      "grad_norm": 0.5920840023317582,
      "learning_rate": 5e-06,
      "loss": 0.5571,
      "step": 450
    },
    {
      "epoch": 1.3834586466165413,
      "grad_norm": 0.5287134171137652,
      "learning_rate": 5e-06,
      "loss": 0.5487,
      "step": 460
    },
    {
      "epoch": 1.413533834586466,
      "grad_norm": 0.48569117162380887,
      "learning_rate": 5e-06,
      "loss": 0.5586,
      "step": 470
    },
    {
      "epoch": 1.443609022556391,
      "grad_norm": 0.5524909003831754,
      "learning_rate": 5e-06,
      "loss": 0.5528,
      "step": 480
    },
    {
      "epoch": 1.4736842105263157,
      "grad_norm": 0.45528161895298735,
      "learning_rate": 5e-06,
      "loss": 0.5624,
      "step": 490
    },
    {
      "epoch": 1.5037593984962405,
      "grad_norm": 0.5654083015816137,
      "learning_rate": 5e-06,
      "loss": 0.5565,
      "step": 500
    },
    {
      "epoch": 1.5338345864661656,
      "grad_norm": 0.5087876058685868,
      "learning_rate": 5e-06,
      "loss": 0.5587,
      "step": 510
    },
    {
      "epoch": 1.5639097744360901,
      "grad_norm": 0.4290062049121276,
      "learning_rate": 5e-06,
      "loss": 0.5493,
      "step": 520
    },
    {
      "epoch": 1.5939849624060152,
      "grad_norm": 0.6235091434876753,
      "learning_rate": 5e-06,
      "loss": 0.5603,
      "step": 530
    },
    {
      "epoch": 1.6240601503759398,
      "grad_norm": 0.5314512113272476,
      "learning_rate": 5e-06,
      "loss": 0.5564,
      "step": 540
    },
    {
      "epoch": 1.6541353383458648,
      "grad_norm": 0.5049026603516721,
      "learning_rate": 5e-06,
      "loss": 0.5605,
      "step": 550
    },
    {
      "epoch": 1.6842105263157894,
      "grad_norm": 0.5650921119799542,
      "learning_rate": 5e-06,
      "loss": 0.5601,
      "step": 560
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.5193160484708012,
      "learning_rate": 5e-06,
      "loss": 0.5554,
      "step": 570
    },
    {
      "epoch": 1.744360902255639,
      "grad_norm": 0.5213313242863221,
      "learning_rate": 5e-06,
      "loss": 0.5645,
      "step": 580
    },
    {
      "epoch": 1.774436090225564,
      "grad_norm": 0.6327600595776153,
      "learning_rate": 5e-06,
      "loss": 0.5536,
      "step": 590
    },
    {
      "epoch": 1.8045112781954886,
      "grad_norm": 0.5461472827380875,
      "learning_rate": 5e-06,
      "loss": 0.5625,
      "step": 600
    },
    {
      "epoch": 1.8345864661654137,
      "grad_norm": 0.6541180795154581,
      "learning_rate": 5e-06,
      "loss": 0.554,
      "step": 610
    },
    {
      "epoch": 1.8646616541353382,
      "grad_norm": 0.5572692340571848,
      "learning_rate": 5e-06,
      "loss": 0.5529,
      "step": 620
    },
    {
      "epoch": 1.8947368421052633,
      "grad_norm": 0.5724927689201437,
      "learning_rate": 5e-06,
      "loss": 0.547,
      "step": 630
    },
    {
      "epoch": 1.9248120300751879,
      "grad_norm": 0.48899030621990486,
      "learning_rate": 5e-06,
      "loss": 0.5508,
      "step": 640
    },
    {
      "epoch": 1.954887218045113,
      "grad_norm": 0.4783796037203571,
      "learning_rate": 5e-06,
      "loss": 0.5626,
      "step": 650
    },
    {
      "epoch": 1.9849624060150375,
      "grad_norm": 0.4380429796439722,
      "learning_rate": 5e-06,
      "loss": 0.5579,
      "step": 660
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6012639403343201,
      "eval_runtime": 116.0368,
      "eval_samples_per_second": 77.2,
      "eval_steps_per_second": 0.603,
      "step": 665
    },
    {
      "epoch": 2.0150375939849625,
      "grad_norm": 0.8195061236201225,
      "learning_rate": 5e-06,
      "loss": 0.5349,
      "step": 670
    },
    {
      "epoch": 2.045112781954887,
      "grad_norm": 0.5727072462132908,
      "learning_rate": 5e-06,
      "loss": 0.5023,
      "step": 680
    },
    {
      "epoch": 2.075187969924812,
      "grad_norm": 0.5716937306059446,
      "learning_rate": 5e-06,
      "loss": 0.5025,
      "step": 690
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.5936120169922254,
      "learning_rate": 5e-06,
      "loss": 0.502,
      "step": 700
    },
    {
      "epoch": 2.1353383458646618,
      "grad_norm": 0.5323072505815232,
      "learning_rate": 5e-06,
      "loss": 0.5005,
      "step": 710
    },
    {
      "epoch": 2.1654135338345863,
      "grad_norm": 0.5082968360924967,
      "learning_rate": 5e-06,
      "loss": 0.5037,
      "step": 720
    },
    {
      "epoch": 2.1954887218045114,
      "grad_norm": 0.5227485772254855,
      "learning_rate": 5e-06,
      "loss": 0.4989,
      "step": 730
    },
    {
      "epoch": 2.225563909774436,
      "grad_norm": 0.6533374147188858,
      "learning_rate": 5e-06,
      "loss": 0.5051,
      "step": 740
    },
    {
      "epoch": 2.255639097744361,
      "grad_norm": 0.5912234992209703,
      "learning_rate": 5e-06,
      "loss": 0.5048,
      "step": 750
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.5434227115064355,
      "learning_rate": 5e-06,
      "loss": 0.508,
      "step": 760
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 0.5720087264790767,
      "learning_rate": 5e-06,
      "loss": 0.5099,
      "step": 770
    },
    {
      "epoch": 2.345864661654135,
      "grad_norm": 0.6089476678610672,
      "learning_rate": 5e-06,
      "loss": 0.5024,
      "step": 780
    },
    {
      "epoch": 2.3759398496240602,
      "grad_norm": 0.5508640915356684,
      "learning_rate": 5e-06,
      "loss": 0.5115,
      "step": 790
    },
    {
      "epoch": 2.406015037593985,
      "grad_norm": 0.5118656252283122,
      "learning_rate": 5e-06,
      "loss": 0.5051,
      "step": 800
    },
    {
      "epoch": 2.43609022556391,
      "grad_norm": 0.5065404177593222,
      "learning_rate": 5e-06,
      "loss": 0.5094,
      "step": 810
    },
    {
      "epoch": 2.4661654135338344,
      "grad_norm": 0.5181429354716248,
      "learning_rate": 5e-06,
      "loss": 0.5106,
      "step": 820
    },
    {
      "epoch": 2.4962406015037595,
      "grad_norm": 0.5322514457543749,
      "learning_rate": 5e-06,
      "loss": 0.5109,
      "step": 830
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 0.6196654734671412,
      "learning_rate": 5e-06,
      "loss": 0.5061,
      "step": 840
    },
    {
      "epoch": 2.556390977443609,
      "grad_norm": 0.5256550356188423,
      "learning_rate": 5e-06,
      "loss": 0.5096,
      "step": 850
    },
    {
      "epoch": 2.5864661654135337,
      "grad_norm": 0.4721653082846406,
      "learning_rate": 5e-06,
      "loss": 0.5091,
      "step": 860
    },
    {
      "epoch": 2.6165413533834587,
      "grad_norm": 0.5461766886120224,
      "learning_rate": 5e-06,
      "loss": 0.5125,
      "step": 870
    },
    {
      "epoch": 2.6466165413533833,
      "grad_norm": 0.8881592761313983,
      "learning_rate": 5e-06,
      "loss": 0.5133,
      "step": 880
    },
    {
      "epoch": 2.6766917293233083,
      "grad_norm": 0.5215263169318092,
      "learning_rate": 5e-06,
      "loss": 0.5137,
      "step": 890
    },
    {
      "epoch": 2.706766917293233,
      "grad_norm": 0.5970816519010325,
      "learning_rate": 5e-06,
      "loss": 0.5085,
      "step": 900
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 0.5663757119297533,
      "learning_rate": 5e-06,
      "loss": 0.5136,
      "step": 910
    },
    {
      "epoch": 2.7669172932330826,
      "grad_norm": 0.48531820284070437,
      "learning_rate": 5e-06,
      "loss": 0.5105,
      "step": 920
    },
    {
      "epoch": 2.7969924812030076,
      "grad_norm": 0.5235848494113168,
      "learning_rate": 5e-06,
      "loss": 0.5106,
      "step": 930
    },
    {
      "epoch": 2.827067669172932,
      "grad_norm": 0.6230274670862681,
      "learning_rate": 5e-06,
      "loss": 0.5109,
      "step": 940
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.5464639670084257,
      "learning_rate": 5e-06,
      "loss": 0.502,
      "step": 950
    },
    {
      "epoch": 2.887218045112782,
      "grad_norm": 0.5388668922788399,
      "learning_rate": 5e-06,
      "loss": 0.5059,
      "step": 960
    },
    {
      "epoch": 2.917293233082707,
      "grad_norm": 0.5634658215547509,
      "learning_rate": 5e-06,
      "loss": 0.5147,
      "step": 970
    },
    {
      "epoch": 2.9473684210526314,
      "grad_norm": 0.5876554762818471,
      "learning_rate": 5e-06,
      "loss": 0.507,
      "step": 980
    },
    {
      "epoch": 2.9774436090225564,
      "grad_norm": 0.5816222818084577,
      "learning_rate": 5e-06,
      "loss": 0.5116,
      "step": 990
    },
    {
      "epoch": 2.995488721804511,
      "eval_loss": 0.605595588684082,
      "eval_runtime": 114.1196,
      "eval_samples_per_second": 78.497,
      "eval_steps_per_second": 0.613,
      "step": 996
    },
    {
      "epoch": 2.995488721804511,
      "step": 996,
      "total_flos": 1667918337146880.0,
      "train_loss": 0.5664463261045126,
      "train_runtime": 17372.9601,
      "train_samples_per_second": 29.39,
      "train_steps_per_second": 0.057
    }
  ],
  "logging_steps": 10,
  "max_steps": 996,
  "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": 1667918337146880.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}