{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.1984838042729153,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.036756260050539856,
      "grad_norm": 1.0688965320587158,
      "learning_rate": 1.0975609756097562e-05,
      "loss": 1.1745,
      "step": 10
    },
    {
      "epoch": 0.07351252010107971,
      "grad_norm": 0.6050378084182739,
      "learning_rate": 2.3170731707317075e-05,
      "loss": 0.9615,
      "step": 20
    },
    {
      "epoch": 0.11026878015161957,
      "grad_norm": 0.5260648727416992,
      "learning_rate": 3.5365853658536584e-05,
      "loss": 0.9305,
      "step": 30
    },
    {
      "epoch": 0.14702504020215942,
      "grad_norm": 0.4684043824672699,
      "learning_rate": 4.75609756097561e-05,
      "loss": 0.8995,
      "step": 40
    },
    {
      "epoch": 0.1837813002526993,
      "grad_norm": 0.4516962468624115,
      "learning_rate": 4.998685537302135e-05,
      "loss": 0.8836,
      "step": 50
    },
    {
      "epoch": 0.22053756030323915,
      "grad_norm": 0.4993128776550293,
      "learning_rate": 4.9933479014963055e-05,
      "loss": 0.8635,
      "step": 60
    },
    {
      "epoch": 0.257293820353779,
      "grad_norm": 0.4929085373878479,
      "learning_rate": 4.9839137016353147e-05,
      "loss": 0.8769,
      "step": 70
    },
    {
      "epoch": 0.29405008040431885,
      "grad_norm": 0.4800896644592285,
      "learning_rate": 4.970398438084758e-05,
      "loss": 0.9013,
      "step": 80
    },
    {
      "epoch": 0.33080634045485874,
      "grad_norm": 0.42861899733543396,
      "learning_rate": 4.952824316387163e-05,
      "loss": 0.8876,
      "step": 90
    },
    {
      "epoch": 0.3675626005053986,
      "grad_norm": 0.45206961035728455,
      "learning_rate": 4.931220210778332e-05,
      "loss": 0.8549,
      "step": 100
    },
    {
      "epoch": 0.4043188605559384,
      "grad_norm": 0.7127406597137451,
      "learning_rate": 4.905621616747054e-05,
      "loss": 0.8494,
      "step": 110
    },
    {
      "epoch": 0.4410751206064783,
      "grad_norm": 0.40425172448158264,
      "learning_rate": 4.876070592716105e-05,
      "loss": 0.8437,
      "step": 120
    },
    {
      "epoch": 0.47783138065701813,
      "grad_norm": 0.4734930992126465,
      "learning_rate": 4.842615690940373e-05,
      "loss": 0.8411,
      "step": 130
    },
    {
      "epoch": 0.514587640707558,
      "grad_norm": 0.4126618802547455,
      "learning_rate": 4.80531187773563e-05,
      "loss": 0.8658,
      "step": 140
    },
    {
      "epoch": 0.5513439007580979,
      "grad_norm": 0.4084201157093048,
      "learning_rate": 4.7642204431690206e-05,
      "loss": 0.8467,
      "step": 150
    },
    {
      "epoch": 0.5881001608086377,
      "grad_norm": 0.38719961047172546,
      "learning_rate": 4.71940890035964e-05,
      "loss": 0.8834,
      "step": 160
    },
    {
      "epoch": 0.6248564208591776,
      "grad_norm": 0.37913328409194946,
      "learning_rate": 4.6709508745546575e-05,
      "loss": 0.8286,
      "step": 170
    },
    {
      "epoch": 0.6616126809097175,
      "grad_norm": 0.35573574900627136,
      "learning_rate": 4.618925982163232e-05,
      "loss": 0.8447,
      "step": 180
    },
    {
      "epoch": 0.6983689409602573,
      "grad_norm": 0.3563328683376312,
      "learning_rate": 4.563419699946956e-05,
      "loss": 0.855,
      "step": 190
    },
    {
      "epoch": 0.7351252010107971,
      "grad_norm": 0.3638900816440582,
      "learning_rate": 4.504523224581762e-05,
      "loss": 0.864,
      "step": 200
    },
    {
      "epoch": 0.771881461061337,
      "grad_norm": 0.38919857144355774,
      "learning_rate": 4.442333322822028e-05,
      "loss": 0.8375,
      "step": 210
    },
    {
      "epoch": 0.8086377211118768,
      "grad_norm": 0.3908405303955078,
      "learning_rate": 4.376952172513046e-05,
      "loss": 0.8642,
      "step": 220
    },
    {
      "epoch": 0.8453939811624167,
      "grad_norm": 0.37455061078071594,
      "learning_rate": 4.308487194713097e-05,
      "loss": 0.8775,
      "step": 230
    },
    {
      "epoch": 0.8821502412129566,
      "grad_norm": 0.3894438147544861,
      "learning_rate": 4.2370508772009334e-05,
      "loss": 0.8454,
      "step": 240
    },
    {
      "epoch": 0.9189065012634965,
      "grad_norm": 0.40810340642929077,
      "learning_rate": 4.162760589658649e-05,
      "loss": 0.8399,
      "step": 250
    },
    {
      "epoch": 0.9556627613140363,
      "grad_norm": 0.36629530787467957,
      "learning_rate": 4.0857383908336076e-05,
      "loss": 0.8519,
      "step": 260
    },
    {
      "epoch": 0.9924190213645762,
      "grad_norm": 0.37508270144462585,
      "learning_rate": 4.0061108279962336e-05,
      "loss": 0.8629,
      "step": 270
    },
    {
      "epoch": 1.025729382035378,
      "grad_norm": 0.5247800350189209,
      "learning_rate": 3.924008729023185e-05,
      "loss": 0.7402,
      "step": 280
    },
    {
      "epoch": 1.0624856420859177,
      "grad_norm": 0.39590781927108765,
      "learning_rate": 3.8395669874474915e-05,
      "loss": 0.7421,
      "step": 290
    },
    {
      "epoch": 1.0992419021364577,
      "grad_norm": 0.3770304322242737,
      "learning_rate": 3.752924340828837e-05,
      "loss": 0.6945,
      "step": 300
    },
    {
      "epoch": 1.1359981621869975,
      "grad_norm": 0.355007529258728,
      "learning_rate": 3.66422314280811e-05,
      "loss": 0.6956,
      "step": 310
    },
    {
      "epoch": 1.1727544222375372,
      "grad_norm": 0.35693830251693726,
      "learning_rate": 3.573609129220748e-05,
      "loss": 0.6778,
      "step": 320
    },
    {
      "epoch": 1.2095106822880772,
      "grad_norm": 0.3579568862915039,
      "learning_rate": 3.4812311786531426e-05,
      "loss": 0.6869,
      "step": 330
    },
    {
      "epoch": 1.246266942338617,
      "grad_norm": 0.332889199256897,
      "learning_rate": 3.387241067835513e-05,
      "loss": 0.6995,
      "step": 340
    },
    {
      "epoch": 1.283023202389157,
      "grad_norm": 0.3603542447090149,
      "learning_rate": 3.2917932222731325e-05,
      "loss": 0.7057,
      "step": 350
    },
    {
      "epoch": 1.3197794624396968,
      "grad_norm": 0.3424987196922302,
      "learning_rate": 3.195044462525636e-05,
      "loss": 0.6823,
      "step": 360
    },
    {
      "epoch": 1.3565357224902366,
      "grad_norm": 0.349817156791687,
      "learning_rate": 3.097153746551248e-05,
      "loss": 0.7167,
      "step": 370
    },
    {
      "epoch": 1.3932919825407764,
      "grad_norm": 0.340465247631073,
      "learning_rate": 2.998281908539272e-05,
      "loss": 0.6917,
      "step": 380
    },
    {
      "epoch": 1.4300482425913164,
      "grad_norm": 0.3161555528640747,
      "learning_rate": 2.898591394659948e-05,
      "loss": 0.7037,
      "step": 390
    },
    {
      "epoch": 1.4668045026418561,
      "grad_norm": 0.3468339741230011,
      "learning_rate": 2.798245996165813e-05,
      "loss": 0.7021,
      "step": 400
    },
    {
      "epoch": 1.5035607626923961,
      "grad_norm": 0.34667858481407166,
      "learning_rate": 2.697410580283107e-05,
      "loss": 0.7188,
      "step": 410
    },
    {
      "epoch": 1.540317022742936,
      "grad_norm": 0.3385638892650604,
      "learning_rate": 2.5962508193353542e-05,
      "loss": 0.6913,
      "step": 420
    },
    {
      "epoch": 1.5770732827934757,
      "grad_norm": 0.3313932716846466,
      "learning_rate": 2.4949329185441666e-05,
      "loss": 0.696,
      "step": 430
    },
    {
      "epoch": 1.6138295428440155,
      "grad_norm": 0.335350900888443,
      "learning_rate": 2.3936233429545054e-05,
      "loss": 0.7101,
      "step": 440
    },
    {
      "epoch": 1.6505858028945555,
      "grad_norm": 0.33174756169319153,
      "learning_rate": 2.2924885439330477e-05,
      "loss": 0.6899,
      "step": 450
    },
    {
      "epoch": 1.6873420629450955,
      "grad_norm": 0.35936641693115234,
      "learning_rate": 2.1916946856890293e-05,
      "loss": 0.6858,
      "step": 460
    },
    {
      "epoch": 1.7240983229956353,
      "grad_norm": 0.351677805185318,
      "learning_rate": 2.0914073722668788e-05,
      "loss": 0.6687,
      "step": 470
    },
    {
      "epoch": 1.760854583046175,
      "grad_norm": 0.36415979266166687,
      "learning_rate": 1.9917913754592183e-05,
      "loss": 0.6877,
      "step": 480
    },
    {
      "epoch": 1.7976108430967148,
      "grad_norm": 0.31224891543388367,
      "learning_rate": 1.8930103640872313e-05,
      "loss": 0.7051,
      "step": 490
    },
    {
      "epoch": 1.8343671031472548,
      "grad_norm": 0.3152935206890106,
      "learning_rate": 1.795226635093226e-05,
      "loss": 0.6666,
      "step": 500
    },
    {
      "epoch": 1.8711233631977946,
      "grad_norm": 0.3329021632671356,
      "learning_rate": 1.6986008468871783e-05,
      "loss": 0.6766,
      "step": 510
    },
    {
      "epoch": 1.9078796232483346,
      "grad_norm": 0.3460406959056854,
      "learning_rate": 1.6032917553853936e-05,
      "loss": 0.6735,
      "step": 520
    },
    {
      "epoch": 1.9446358832988744,
      "grad_norm": 0.3377283215522766,
      "learning_rate": 1.509455953174948e-05,
      "loss": 0.669,
      "step": 530
    },
    {
      "epoch": 1.9813921433494142,
      "grad_norm": 0.35212215781211853,
      "learning_rate": 1.4172476122324806e-05,
      "loss": 0.6608,
      "step": 540
    },
    {
      "epoch": 2.014702504020216,
      "grad_norm": 0.4792023003101349,
      "learning_rate": 1.3268182306200405e-05,
      "loss": 0.5849,
      "step": 550
    },
    {
      "epoch": 2.051458764070756,
      "grad_norm": 0.37128546833992004,
      "learning_rate": 1.2383163835741692e-05,
      "loss": 0.4627,
      "step": 560
    },
    {
      "epoch": 2.0882150241212956,
      "grad_norm": 0.4129978120326996,
      "learning_rate": 1.1518874793971754e-05,
      "loss": 0.451,
      "step": 570
    },
    {
      "epoch": 2.1249712841718353,
      "grad_norm": 0.37535038590431213,
      "learning_rate": 1.0676735205516788e-05,
      "loss": 0.4377,
      "step": 580
    },
    {
      "epoch": 2.1617275442223756,
      "grad_norm": 0.394779771566391,
      "learning_rate": 9.858128703509348e-06,
      "loss": 0.4401,
      "step": 590
    },
    {
      "epoch": 2.1984838042729153,
      "grad_norm": 0.3875374495983124,
      "learning_rate": 9.064400256282757e-06,
      "loss": 0.4448,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 816,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9960308772634624e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}