{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05133140840551813,
  "eval_steps": 17,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025665704202759064,
      "eval_loss": 2.767350435256958,
      "eval_runtime": 491.4277,
      "eval_samples_per_second": 13.355,
      "eval_steps_per_second": 1.671,
      "step": 1
    },
    {
      "epoch": 0.0007699711260827719,
      "grad_norm": 0.3417242467403412,
      "learning_rate": 3e-05,
      "loss": 2.6769,
      "step": 3
    },
    {
      "epoch": 0.0015399422521655437,
      "grad_norm": 0.35272517800331116,
      "learning_rate": 6e-05,
      "loss": 2.7375,
      "step": 6
    },
    {
      "epoch": 0.0023099133782483157,
      "grad_norm": 0.350046306848526,
      "learning_rate": 9e-05,
      "loss": 2.6718,
      "step": 9
    },
    {
      "epoch": 0.0030798845043310875,
      "grad_norm": 0.3014596104621887,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.5993,
      "step": 12
    },
    {
      "epoch": 0.0038498556304138597,
      "grad_norm": 0.3522738218307495,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.5303,
      "step": 15
    },
    {
      "epoch": 0.00436316971446904,
      "eval_loss": 2.5289151668548584,
      "eval_runtime": 493.8022,
      "eval_samples_per_second": 13.291,
      "eval_steps_per_second": 1.663,
      "step": 17
    },
    {
      "epoch": 0.0046198267564966315,
      "grad_norm": 0.3675502836704254,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.4945,
      "step": 18
    },
    {
      "epoch": 0.005389797882579404,
      "grad_norm": 0.4536501169204712,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.5246,
      "step": 21
    },
    {
      "epoch": 0.006159769008662175,
      "grad_norm": 0.39700689911842346,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.4664,
      "step": 24
    },
    {
      "epoch": 0.006929740134744947,
      "grad_norm": 0.3603559732437134,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.4274,
      "step": 27
    },
    {
      "epoch": 0.007699711260827719,
      "grad_norm": 0.368173211812973,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.4661,
      "step": 30
    },
    {
      "epoch": 0.00846968238691049,
      "grad_norm": 0.35239627957344055,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.3349,
      "step": 33
    },
    {
      "epoch": 0.00872633942893808,
      "eval_loss": 2.3943283557891846,
      "eval_runtime": 493.7443,
      "eval_samples_per_second": 13.292,
      "eval_steps_per_second": 1.663,
      "step": 34
    },
    {
      "epoch": 0.009239653512993263,
      "grad_norm": 0.3209523558616638,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.4035,
      "step": 36
    },
    {
      "epoch": 0.010009624639076035,
      "grad_norm": 0.33573678135871887,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.3783,
      "step": 39
    },
    {
      "epoch": 0.010779595765158807,
      "grad_norm": 0.3218136131763458,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.4247,
      "step": 42
    },
    {
      "epoch": 0.011549566891241578,
      "grad_norm": 0.30115804076194763,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.3915,
      "step": 45
    },
    {
      "epoch": 0.01231953801732435,
      "grad_norm": 0.34325042366981506,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.3639,
      "step": 48
    },
    {
      "epoch": 0.013089509143407122,
      "grad_norm": 0.3467099666595459,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.3171,
      "step": 51
    },
    {
      "epoch": 0.013089509143407122,
      "eval_loss": 2.341045379638672,
      "eval_runtime": 494.2874,
      "eval_samples_per_second": 13.278,
      "eval_steps_per_second": 1.661,
      "step": 51
    },
    {
      "epoch": 0.013859480269489894,
      "grad_norm": 0.3275759220123291,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.3057,
      "step": 54
    },
    {
      "epoch": 0.014629451395572667,
      "grad_norm": 0.29645541310310364,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.3326,
      "step": 57
    },
    {
      "epoch": 0.015399422521655439,
      "grad_norm": 0.3317429721355438,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.3392,
      "step": 60
    },
    {
      "epoch": 0.01616939364773821,
      "grad_norm": 0.3201993405818939,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.3972,
      "step": 63
    },
    {
      "epoch": 0.01693936477382098,
      "grad_norm": 0.3513089716434479,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.3498,
      "step": 66
    },
    {
      "epoch": 0.01745267885787616,
      "eval_loss": 2.3205010890960693,
      "eval_runtime": 493.7323,
      "eval_samples_per_second": 13.293,
      "eval_steps_per_second": 1.663,
      "step": 68
    },
    {
      "epoch": 0.017709335899903755,
      "grad_norm": 0.3993850648403168,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.2755,
      "step": 69
    },
    {
      "epoch": 0.018479307025986526,
      "grad_norm": 0.3162781000137329,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.3094,
      "step": 72
    },
    {
      "epoch": 0.019249278152069296,
      "grad_norm": 0.33009400963783264,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.3131,
      "step": 75
    },
    {
      "epoch": 0.02001924927815207,
      "grad_norm": 0.30170515179634094,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.2769,
      "step": 78
    },
    {
      "epoch": 0.02078922040423484,
      "grad_norm": 0.36391210556030273,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.3464,
      "step": 81
    },
    {
      "epoch": 0.021559191530317615,
      "grad_norm": 0.34589123725891113,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.3523,
      "step": 84
    },
    {
      "epoch": 0.021815848572345205,
      "eval_loss": 2.3070456981658936,
      "eval_runtime": 494.1111,
      "eval_samples_per_second": 13.282,
      "eval_steps_per_second": 1.662,
      "step": 85
    },
    {
      "epoch": 0.022329162656400385,
      "grad_norm": 0.3209848403930664,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.3331,
      "step": 87
    },
    {
      "epoch": 0.023099133782483156,
      "grad_norm": 0.31879422068595886,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.2655,
      "step": 90
    },
    {
      "epoch": 0.02386910490856593,
      "grad_norm": 0.32777905464172363,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.2949,
      "step": 93
    },
    {
      "epoch": 0.0246390760346487,
      "grad_norm": 0.3651144504547119,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.2816,
      "step": 96
    },
    {
      "epoch": 0.025409047160731474,
      "grad_norm": 0.3634001910686493,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.2775,
      "step": 99
    },
    {
      "epoch": 0.026179018286814244,
      "grad_norm": 0.3226020932197571,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.2755,
      "step": 102
    },
    {
      "epoch": 0.026179018286814244,
      "eval_loss": 2.298733711242676,
      "eval_runtime": 494.1645,
      "eval_samples_per_second": 13.281,
      "eval_steps_per_second": 1.661,
      "step": 102
    },
    {
      "epoch": 0.026948989412897015,
      "grad_norm": 0.3292534053325653,
      "learning_rate": 5e-05,
      "loss": 2.2091,
      "step": 105
    },
    {
      "epoch": 0.02771896053897979,
      "grad_norm": 0.34186315536499023,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.2861,
      "step": 108
    },
    {
      "epoch": 0.02848893166506256,
      "grad_norm": 0.3780612051486969,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.2936,
      "step": 111
    },
    {
      "epoch": 0.029258902791145333,
      "grad_norm": 0.3421897888183594,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.2416,
      "step": 114
    },
    {
      "epoch": 0.030028873917228104,
      "grad_norm": 0.38082820177078247,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 2.3025,
      "step": 117
    },
    {
      "epoch": 0.030542188001283284,
      "eval_loss": 2.292694330215454,
      "eval_runtime": 494.1273,
      "eval_samples_per_second": 13.282,
      "eval_steps_per_second": 1.662,
      "step": 119
    },
    {
      "epoch": 0.030798845043310877,
      "grad_norm": 0.41164785623550415,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.2888,
      "step": 120
    },
    {
      "epoch": 0.031568816169393644,
      "grad_norm": 0.3949745297431946,
      "learning_rate": 3.533749813077677e-05,
      "loss": 2.2659,
      "step": 123
    },
    {
      "epoch": 0.03233878729547642,
      "grad_norm": 0.31058645248413086,
      "learning_rate": 3.298534127791785e-05,
      "loss": 2.3101,
      "step": 126
    },
    {
      "epoch": 0.03310875842155919,
      "grad_norm": 0.3842872977256775,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 2.1922,
      "step": 129
    },
    {
      "epoch": 0.03387872954764196,
      "grad_norm": 0.37319129705429077,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.251,
      "step": 132
    },
    {
      "epoch": 0.03464870067372473,
      "grad_norm": 0.3240547180175781,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.3064,
      "step": 135
    },
    {
      "epoch": 0.03490535771575232,
      "eval_loss": 2.2887308597564697,
      "eval_runtime": 494.1479,
      "eval_samples_per_second": 13.281,
      "eval_steps_per_second": 1.661,
      "step": 136
    },
    {
      "epoch": 0.03541867179980751,
      "grad_norm": 0.3809681534767151,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.3106,
      "step": 138
    },
    {
      "epoch": 0.03618864292589028,
      "grad_norm": 0.3716019093990326,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.3156,
      "step": 141
    },
    {
      "epoch": 0.03695861405197305,
      "grad_norm": 0.3578968048095703,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.2621,
      "step": 144
    },
    {
      "epoch": 0.03772858517805582,
      "grad_norm": 0.37218406796455383,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.3245,
      "step": 147
    },
    {
      "epoch": 0.03849855630413859,
      "grad_norm": 0.3655867278575897,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.2425,
      "step": 150
    },
    {
      "epoch": 0.03926852743022137,
      "grad_norm": 0.33499404788017273,
      "learning_rate": 1.435357758543015e-05,
      "loss": 2.2394,
      "step": 153
    },
    {
      "epoch": 0.03926852743022137,
      "eval_loss": 2.2859363555908203,
      "eval_runtime": 494.1942,
      "eval_samples_per_second": 13.28,
      "eval_steps_per_second": 1.661,
      "step": 153
    },
    {
      "epoch": 0.04003849855630414,
      "grad_norm": 0.415403813123703,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.3245,
      "step": 156
    },
    {
      "epoch": 0.04080846968238691,
      "grad_norm": 0.37216442823410034,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.2985,
      "step": 159
    },
    {
      "epoch": 0.04157844080846968,
      "grad_norm": 0.3392238914966583,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.2315,
      "step": 162
    },
    {
      "epoch": 0.04234841193455245,
      "grad_norm": 0.3757283091545105,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.2423,
      "step": 165
    },
    {
      "epoch": 0.04311838306063523,
      "grad_norm": 0.3205427825450897,
      "learning_rate": 6.837175952121306e-06,
      "loss": 2.3192,
      "step": 168
    },
    {
      "epoch": 0.04363169714469041,
      "eval_loss": 2.2842438220977783,
      "eval_runtime": 494.3736,
      "eval_samples_per_second": 13.275,
      "eval_steps_per_second": 1.661,
      "step": 170
    },
    {
      "epoch": 0.043888354186718,
      "grad_norm": 0.38284480571746826,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 2.3103,
      "step": 171
    },
    {
      "epoch": 0.04465832531280077,
      "grad_norm": 0.3595847487449646,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.272,
      "step": 174
    },
    {
      "epoch": 0.04542829643888354,
      "grad_norm": 0.3618505597114563,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 2.2537,
      "step": 177
    },
    {
      "epoch": 0.04619826756496631,
      "grad_norm": 0.3798527121543884,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.235,
      "step": 180
    },
    {
      "epoch": 0.04696823869104909,
      "grad_norm": 0.4292336702346802,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.2815,
      "step": 183
    },
    {
      "epoch": 0.04773820981713186,
      "grad_norm": 0.38992390036582947,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.3201,
      "step": 186
    },
    {
      "epoch": 0.04799486685915945,
      "eval_loss": 2.283592462539673,
      "eval_runtime": 494.1905,
      "eval_samples_per_second": 13.28,
      "eval_steps_per_second": 1.661,
      "step": 187
    },
    {
      "epoch": 0.04850818094321463,
      "grad_norm": 0.3798556923866272,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.33,
      "step": 189
    },
    {
      "epoch": 0.0492781520692974,
      "grad_norm": 0.3679429590702057,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.25,
      "step": 192
    },
    {
      "epoch": 0.05004812319538017,
      "grad_norm": 0.4056394398212433,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.3329,
      "step": 195
    },
    {
      "epoch": 0.05081809432146295,
      "grad_norm": 0.44835567474365234,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 2.3408,
      "step": 198
    }
  ],
  "logging_steps": 3,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.956649411200942e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}