{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5286343612334802,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00881057268722467,
      "grad_norm": 19.571447343122014,
      "learning_rate": 6.666666666666666e-07,
      "loss": 2.2003,
      "step": 10
    },
    {
      "epoch": 0.01762114537444934,
      "grad_norm": 6.597664324174228,
      "learning_rate": 1.3333333333333332e-06,
      "loss": 2.0343,
      "step": 20
    },
    {
      "epoch": 0.02643171806167401,
      "grad_norm": 3.014996781518845,
      "learning_rate": 2e-06,
      "loss": 1.8168,
      "step": 30
    },
    {
      "epoch": 0.03524229074889868,
      "grad_norm": 2.496924527736719,
      "learning_rate": 1.9995958747931082e-06,
      "loss": 1.7178,
      "step": 40
    },
    {
      "epoch": 0.04405286343612335,
      "grad_norm": 2.8973420754515464,
      "learning_rate": 1.9983838258067983e-06,
      "loss": 1.6557,
      "step": 50
    },
    {
      "epoch": 0.05286343612334802,
      "grad_norm": 2.3479520994877605,
      "learning_rate": 1.9963648326801653e-06,
      "loss": 1.595,
      "step": 60
    },
    {
      "epoch": 0.06167400881057269,
      "grad_norm": 2.2003866197934974,
      "learning_rate": 1.993540527265239e-06,
      "loss": 1.5428,
      "step": 70
    },
    {
      "epoch": 0.07048458149779736,
      "grad_norm": 2.222349491130299,
      "learning_rate": 1.98991319230804e-06,
      "loss": 1.5157,
      "step": 80
    },
    {
      "epoch": 0.07929515418502203,
      "grad_norm": 2.146284797118347,
      "learning_rate": 1.9854857596035474e-06,
      "loss": 1.4995,
      "step": 90
    },
    {
      "epoch": 0.0881057268722467,
      "grad_norm": 2.305597555128469,
      "learning_rate": 1.980261807626078e-06,
      "loss": 1.4886,
      "step": 100
    },
    {
      "epoch": 0.09691629955947137,
      "grad_norm": 2.199507218792448,
      "learning_rate": 1.974245558636978e-06,
      "loss": 1.4643,
      "step": 110
    },
    {
      "epoch": 0.10572687224669604,
      "grad_norm": 2.6946448901304674,
      "learning_rate": 1.967441875271983e-06,
      "loss": 1.4522,
      "step": 120
    },
    {
      "epoch": 0.1145374449339207,
      "grad_norm": 1.9626073275857734,
      "learning_rate": 1.959856256610988e-06,
      "loss": 1.4149,
      "step": 130
    },
    {
      "epoch": 0.12334801762114538,
      "grad_norm": 2.0441408462679065,
      "learning_rate": 1.951494833733414e-06,
      "loss": 1.385,
      "step": 140
    },
    {
      "epoch": 0.13215859030837004,
      "grad_norm": 2.0166534518054493,
      "learning_rate": 1.942364364762762e-06,
      "loss": 1.3718,
      "step": 150
    },
    {
      "epoch": 0.14096916299559473,
      "grad_norm": 1.9565509974119288,
      "learning_rate": 1.932472229404356e-06,
      "loss": 1.3775,
      "step": 160
    },
    {
      "epoch": 0.14977973568281938,
      "grad_norm": 2.1012455112006743,
      "learning_rate": 1.9218264229806917e-06,
      "loss": 1.3579,
      "step": 170
    },
    {
      "epoch": 0.15859030837004406,
      "grad_norm": 1.90439374473129,
      "learning_rate": 1.9104355499692162e-06,
      "loss": 1.3333,
      "step": 180
    },
    {
      "epoch": 0.16740088105726872,
      "grad_norm": 2.2252827256286922,
      "learning_rate": 1.8983088170477553e-06,
      "loss": 1.3458,
      "step": 190
    },
    {
      "epoch": 0.1762114537444934,
      "grad_norm": 1.958512432909627,
      "learning_rate": 1.8854560256532098e-06,
      "loss": 1.332,
      "step": 200
    },
    {
      "epoch": 0.18502202643171806,
      "grad_norm": 1.9065312694563097,
      "learning_rate": 1.871887564059543e-06,
      "loss": 1.3138,
      "step": 210
    },
    {
      "epoch": 0.19383259911894274,
      "grad_norm": 2.6199771240261436,
      "learning_rate": 1.8576143989814521e-06,
      "loss": 1.3229,
      "step": 220
    },
    {
      "epoch": 0.2026431718061674,
      "grad_norm": 2.217202276336257,
      "learning_rate": 1.8426480667105175e-06,
      "loss": 1.3205,
      "step": 230
    },
    {
      "epoch": 0.21145374449339208,
      "grad_norm": 1.8491248577424624,
      "learning_rate": 1.8270006637909905e-06,
      "loss": 1.3085,
      "step": 240
    },
    {
      "epoch": 0.22026431718061673,
      "grad_norm": 1.9823551473714545,
      "learning_rate": 1.8106848372427548e-06,
      "loss": 1.2956,
      "step": 250
    },
    {
      "epoch": 0.2290748898678414,
      "grad_norm": 2.1060962042553726,
      "learning_rate": 1.7937137743393693e-06,
      "loss": 1.2804,
      "step": 260
    },
    {
      "epoch": 0.23788546255506607,
      "grad_norm": 1.8695678284143167,
      "learning_rate": 1.7761011919494486e-06,
      "loss": 1.273,
      "step": 270
    },
    {
      "epoch": 0.24669603524229075,
      "grad_norm": 2.56804202001478,
      "learning_rate": 1.7578613254499968e-06,
      "loss": 1.2984,
      "step": 280
    },
    {
      "epoch": 0.2555066079295154,
      "grad_norm": 1.9594579835819614,
      "learning_rate": 1.739008917220659e-06,
      "loss": 1.2554,
      "step": 290
    },
    {
      "epoch": 0.2643171806167401,
      "grad_norm": 1.948264525063767,
      "learning_rate": 1.719559204728188e-06,
      "loss": 1.2733,
      "step": 300
    },
    {
      "epoch": 0.27312775330396477,
      "grad_norm": 1.9555361537181306,
      "learning_rate": 1.6995279082107537e-06,
      "loss": 1.2794,
      "step": 310
    },
    {
      "epoch": 0.28193832599118945,
      "grad_norm": 2.072778303156424,
      "learning_rate": 1.6789312179720546e-06,
      "loss": 1.2594,
      "step": 320
    },
    {
      "epoch": 0.2907488986784141,
      "grad_norm": 1.8797335867525704,
      "learning_rate": 1.6577857812954991e-06,
      "loss": 1.2485,
      "step": 330
    },
    {
      "epoch": 0.29955947136563876,
      "grad_norm": 2.039515984739043,
      "learning_rate": 1.6361086889890305e-06,
      "loss": 1.2645,
      "step": 340
    },
    {
      "epoch": 0.30837004405286345,
      "grad_norm": 2.0610642486240125,
      "learning_rate": 1.613917461571475e-06,
      "loss": 1.2531,
      "step": 350
    },
    {
      "epoch": 0.31718061674008813,
      "grad_norm": 2.06709238158364,
      "learning_rate": 1.5912300351115757e-06,
      "loss": 1.2491,
      "step": 360
    },
    {
      "epoch": 0.32599118942731276,
      "grad_norm": 1.8437333020014937,
      "learning_rate": 1.5680647467311555e-06,
      "loss": 1.2334,
      "step": 370
    },
    {
      "epoch": 0.33480176211453744,
      "grad_norm": 1.8965957390199724,
      "learning_rate": 1.5444403197841344e-06,
      "loss": 1.2172,
      "step": 380
    },
    {
      "epoch": 0.3436123348017621,
      "grad_norm": 10.745414670704703,
      "learning_rate": 1.5203758487233676e-06,
      "loss": 1.2306,
      "step": 390
    },
    {
      "epoch": 0.3524229074889868,
      "grad_norm": 1.978659425380664,
      "learning_rate": 1.4958907836675465e-06,
      "loss": 1.2425,
      "step": 400
    },
    {
      "epoch": 0.36123348017621143,
      "grad_norm": 1.8232345405717043,
      "learning_rate": 1.4710049146806346e-06,
      "loss": 1.2401,
      "step": 410
    },
    {
      "epoch": 0.3700440528634361,
      "grad_norm": 1.9694165773247603,
      "learning_rate": 1.4457383557765383e-06,
      "loss": 1.2137,
      "step": 420
    },
    {
      "epoch": 0.3788546255506608,
      "grad_norm": 1.857798327139117,
      "learning_rate": 1.4201115286619464e-06,
      "loss": 1.2328,
      "step": 430
    },
    {
      "epoch": 0.3876651982378855,
      "grad_norm": 1.9640307234634835,
      "learning_rate": 1.3941451462304777e-06,
      "loss": 1.2244,
      "step": 440
    },
    {
      "epoch": 0.3964757709251101,
      "grad_norm": 1.9269638055698532,
      "learning_rate": 1.3678601958214777e-06,
      "loss": 1.2399,
      "step": 450
    },
    {
      "epoch": 0.4052863436123348,
      "grad_norm": 1.8699071909555112,
      "learning_rate": 1.3412779222569906e-06,
      "loss": 1.2175,
      "step": 460
    },
    {
      "epoch": 0.41409691629955947,
      "grad_norm": 1.8481447316610542,
      "learning_rate": 1.3144198106706239e-06,
      "loss": 1.2238,
      "step": 470
    },
    {
      "epoch": 0.42290748898678415,
      "grad_norm": 1.8316730682769253,
      "learning_rate": 1.2873075691421806e-06,
      "loss": 1.2304,
      "step": 480
    },
    {
      "epoch": 0.43171806167400884,
      "grad_norm": 1.8960767894113884,
      "learning_rate": 1.2599631111520955e-06,
      "loss": 1.2036,
      "step": 490
    },
    {
      "epoch": 0.44052863436123346,
      "grad_norm": 1.9109891577097189,
      "learning_rate": 1.2324085378698529e-06,
      "loss": 1.1917,
      "step": 500
    },
    {
      "epoch": 0.44933920704845814,
      "grad_norm": 2.010796003658019,
      "learning_rate": 1.20466612029071e-06,
      "loss": 1.2279,
      "step": 510
    },
    {
      "epoch": 0.4581497797356828,
      "grad_norm": 2.6998433293606454,
      "learning_rate": 1.1767582812351548e-06,
      "loss": 1.1925,
      "step": 520
    },
    {
      "epoch": 0.4669603524229075,
      "grad_norm": 2.275146777332648,
      "learning_rate": 1.1487075772256517e-06,
      "loss": 1.1742,
      "step": 530
    },
    {
      "epoch": 0.47577092511013214,
      "grad_norm": 1.7756028193514886,
      "learning_rate": 1.1205366802553228e-06,
      "loss": 1.1833,
      "step": 540
    },
    {
      "epoch": 0.4845814977973568,
      "grad_norm": 2.042541280215003,
      "learning_rate": 1.092268359463302e-06,
      "loss": 1.1826,
      "step": 550
    },
    {
      "epoch": 0.4933920704845815,
      "grad_norm": 1.84844630790175,
      "learning_rate": 1.0639254627315658e-06,
      "loss": 1.2045,
      "step": 560
    },
    {
      "epoch": 0.5022026431718062,
      "grad_norm": 1.9498951674092562,
      "learning_rate": 1.0355308982181253e-06,
      "loss": 1.1895,
      "step": 570
    },
    {
      "epoch": 0.5110132158590308,
      "grad_norm": 1.961163999725279,
      "learning_rate": 1.0071076158414974e-06,
      "loss": 1.1898,
      "step": 580
    },
    {
      "epoch": 0.5198237885462555,
      "grad_norm": 1.91915126758986,
      "learning_rate": 9.786785887314253e-07,
      "loss": 1.2014,
      "step": 590
    },
    {
      "epoch": 0.5286343612334802,
      "grad_norm": 1.845963386436035,
      "learning_rate": 9.502667946608332e-07,
      "loss": 1.207,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 1135,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 97844723712000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}