{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9868766404199475,
  "eval_steps": 500,
  "global_step": 47,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02099737532808399,
      "grad_norm": 1.512850046157837,
      "learning_rate": 4.9944171965578836e-05,
      "loss": 1.099,
      "num_input_tokens_seen": 2097152,
      "step": 1
    },
    {
      "epoch": 0.04199475065616798,
      "grad_norm": 1.480190396308899,
      "learning_rate": 4.97769372038695e-05,
      "loss": 1.0954,
      "num_input_tokens_seen": 4194304,
      "step": 2
    },
    {
      "epoch": 0.06299212598425197,
      "grad_norm": 1.2695276737213135,
      "learning_rate": 4.9499042625914674e-05,
      "loss": 1.0273,
      "num_input_tokens_seen": 6291456,
      "step": 3
    },
    {
      "epoch": 0.08398950131233596,
      "grad_norm": 1.0559132099151611,
      "learning_rate": 4.911172937635942e-05,
      "loss": 0.9301,
      "num_input_tokens_seen": 8388608,
      "step": 4
    },
    {
      "epoch": 0.10498687664041995,
      "grad_norm": 0.8047496676445007,
      "learning_rate": 4.861672729019797e-05,
      "loss": 0.8696,
      "num_input_tokens_seen": 10485760,
      "step": 5
    },
    {
      "epoch": 0.12598425196850394,
      "grad_norm": 0.6325356364250183,
      "learning_rate": 4.801624716691072e-05,
      "loss": 0.8379,
      "num_input_tokens_seen": 12582912,
      "step": 6
    },
    {
      "epoch": 0.14698162729658792,
      "grad_norm": 0.504206120967865,
      "learning_rate": 4.731297089649703e-05,
      "loss": 0.8087,
      "num_input_tokens_seen": 14680064,
      "step": 7
    },
    {
      "epoch": 0.1679790026246719,
      "grad_norm": 0.4543064534664154,
      "learning_rate": 4.651003948150349e-05,
      "loss": 0.8071,
      "num_input_tokens_seen": 16777216,
      "step": 8
    },
    {
      "epoch": 0.1889763779527559,
      "grad_norm": 0.35835036635398865,
      "learning_rate": 4.561103900854401e-05,
      "loss": 0.7521,
      "num_input_tokens_seen": 18874368,
      "step": 9
    },
    {
      "epoch": 0.2099737532808399,
      "grad_norm": 0.33651018142700195,
      "learning_rate": 4.4619984631966524e-05,
      "loss": 0.7666,
      "num_input_tokens_seen": 20971520,
      "step": 10
    },
    {
      "epoch": 0.23097112860892388,
      "grad_norm": 0.2762841284275055,
      "learning_rate": 4.354130264119894e-05,
      "loss": 0.7226,
      "num_input_tokens_seen": 23068672,
      "step": 11
    },
    {
      "epoch": 0.25196850393700787,
      "grad_norm": 0.2664271891117096,
      "learning_rate": 4.2379810691866064e-05,
      "loss": 0.719,
      "num_input_tokens_seen": 25165824,
      "step": 12
    },
    {
      "epoch": 0.27296587926509186,
      "grad_norm": 0.21707402169704437,
      "learning_rate": 4.114069628897006e-05,
      "loss": 0.7129,
      "num_input_tokens_seen": 27262976,
      "step": 13
    },
    {
      "epoch": 0.29396325459317585,
      "grad_norm": 0.19864299893379211,
      "learning_rate": 3.982949361823388e-05,
      "loss": 0.7029,
      "num_input_tokens_seen": 29360128,
      "step": 14
    },
    {
      "epoch": 0.31496062992125984,
      "grad_norm": 0.20525172352790833,
      "learning_rate": 3.845205882908432e-05,
      "loss": 0.693,
      "num_input_tokens_seen": 31457280,
      "step": 15
    },
    {
      "epoch": 0.3359580052493438,
      "grad_norm": 0.18027806282043457,
      "learning_rate": 3.7014543879667094e-05,
      "loss": 0.689,
      "num_input_tokens_seen": 33554432,
      "step": 16
    },
    {
      "epoch": 0.3569553805774278,
      "grad_norm": 0.16686110198497772,
      "learning_rate": 3.552336906070838e-05,
      "loss": 0.6898,
      "num_input_tokens_seen": 35651584,
      "step": 17
    },
    {
      "epoch": 0.3779527559055118,
      "grad_norm": 0.15808887779712677,
      "learning_rate": 3.398519432093782e-05,
      "loss": 0.6596,
      "num_input_tokens_seen": 37748736,
      "step": 18
    },
    {
      "epoch": 0.3989501312335958,
      "grad_norm": 0.15036313235759735,
      "learning_rate": 3.2406889522140856e-05,
      "loss": 0.6796,
      "num_input_tokens_seen": 39845888,
      "step": 19
    },
    {
      "epoch": 0.4199475065616798,
      "grad_norm": 0.13290229439735413,
      "learning_rate": 3.079550375668821e-05,
      "loss": 0.6595,
      "num_input_tokens_seen": 41943040,
      "step": 20
    },
    {
      "epoch": 0.4409448818897638,
      "grad_norm": 0.12948521971702576,
      "learning_rate": 2.9158233864578254e-05,
      "loss": 0.655,
      "num_input_tokens_seen": 44040192,
      "step": 21
    },
    {
      "epoch": 0.46194225721784776,
      "grad_norm": 0.12121973931789398,
      "learning_rate": 2.7502392290602463e-05,
      "loss": 0.6566,
      "num_input_tokens_seen": 46137344,
      "step": 22
    },
    {
      "epoch": 0.48293963254593175,
      "grad_norm": 0.11144606024026871,
      "learning_rate": 2.5835374425191866e-05,
      "loss": 0.6483,
      "num_input_tokens_seen": 48234496,
      "step": 23
    },
    {
      "epoch": 0.5039370078740157,
      "grad_norm": 0.09845685958862305,
      "learning_rate": 2.4164625574808146e-05,
      "loss": 0.6319,
      "num_input_tokens_seen": 50331648,
      "step": 24
    },
    {
      "epoch": 0.5249343832020997,
      "grad_norm": 0.10502230376005173,
      "learning_rate": 2.2497607709397543e-05,
      "loss": 0.6479,
      "num_input_tokens_seen": 52428800,
      "step": 25
    },
    {
      "epoch": 0.5459317585301837,
      "grad_norm": 0.103838250041008,
      "learning_rate": 2.0841766135421752e-05,
      "loss": 0.6253,
      "num_input_tokens_seen": 54525952,
      "step": 26
    },
    {
      "epoch": 0.5669291338582677,
      "grad_norm": 0.09724501520395279,
      "learning_rate": 1.920449624331179e-05,
      "loss": 0.6248,
      "num_input_tokens_seen": 56623104,
      "step": 27
    },
    {
      "epoch": 0.5879265091863517,
      "grad_norm": 0.09455479681491852,
      "learning_rate": 1.7593110477859153e-05,
      "loss": 0.6237,
      "num_input_tokens_seen": 58720256,
      "step": 28
    },
    {
      "epoch": 0.6089238845144357,
      "grad_norm": 0.09271286427974701,
      "learning_rate": 1.6014805679062185e-05,
      "loss": 0.63,
      "num_input_tokens_seen": 60817408,
      "step": 29
    },
    {
      "epoch": 0.6299212598425197,
      "grad_norm": 0.09387161582708359,
      "learning_rate": 1.447663093929163e-05,
      "loss": 0.6241,
      "num_input_tokens_seen": 62914560,
      "step": 30
    },
    {
      "epoch": 0.6509186351706037,
      "grad_norm": 0.09017566591501236,
      "learning_rate": 1.2985456120332906e-05,
      "loss": 0.6062,
      "num_input_tokens_seen": 65011712,
      "step": 31
    },
    {
      "epoch": 0.6719160104986877,
      "grad_norm": 0.09072048217058182,
      "learning_rate": 1.1547941170915686e-05,
      "loss": 0.6356,
      "num_input_tokens_seen": 67108864,
      "step": 32
    },
    {
      "epoch": 0.6929133858267716,
      "grad_norm": 0.09561938792467117,
      "learning_rate": 1.0170506381766121e-05,
      "loss": 0.6151,
      "num_input_tokens_seen": 69206016,
      "step": 33
    },
    {
      "epoch": 0.7139107611548556,
      "grad_norm": 0.0859409049153328,
      "learning_rate": 8.85930371102994e-06,
      "loss": 0.6198,
      "num_input_tokens_seen": 71303168,
      "step": 34
    },
    {
      "epoch": 0.7349081364829396,
      "grad_norm": 0.08907345682382584,
      "learning_rate": 7.620189308133943e-06,
      "loss": 0.5952,
      "num_input_tokens_seen": 73400320,
      "step": 35
    },
    {
      "epoch": 0.7559055118110236,
      "grad_norm": 0.08716382831335068,
      "learning_rate": 6.458697358801061e-06,
      "loss": 0.6126,
      "num_input_tokens_seen": 75497472,
      "step": 36
    },
    {
      "epoch": 0.7769028871391076,
      "grad_norm": 0.08723893016576767,
      "learning_rate": 5.380015368033476e-06,
      "loss": 0.637,
      "num_input_tokens_seen": 77594624,
      "step": 37
    },
    {
      "epoch": 0.7979002624671916,
      "grad_norm": 0.09199921041727066,
      "learning_rate": 4.388960991455998e-06,
      "loss": 0.6432,
      "num_input_tokens_seen": 79691776,
      "step": 38
    },
    {
      "epoch": 0.8188976377952756,
      "grad_norm": 0.08754907548427582,
      "learning_rate": 3.489960518496521e-06,
      "loss": 0.6329,
      "num_input_tokens_seen": 81788928,
      "step": 39
    },
    {
      "epoch": 0.8398950131233596,
      "grad_norm": 0.08782719820737839,
      "learning_rate": 2.687029103502972e-06,
      "loss": 0.629,
      "num_input_tokens_seen": 83886080,
      "step": 40
    },
    {
      "epoch": 0.8608923884514436,
      "grad_norm": 0.08878407627344131,
      "learning_rate": 1.983752833089278e-06,
      "loss": 0.6277,
      "num_input_tokens_seen": 85983232,
      "step": 41
    },
    {
      "epoch": 0.8818897637795275,
      "grad_norm": 0.08673521876335144,
      "learning_rate": 1.3832727098020332e-06,
      "loss": 0.6192,
      "num_input_tokens_seen": 88080384,
      "step": 42
    },
    {
      "epoch": 0.9028871391076115,
      "grad_norm": 0.09247046709060669,
      "learning_rate": 8.882706236405886e-07,
      "loss": 0.6203,
      "num_input_tokens_seen": 90177536,
      "step": 43
    },
    {
      "epoch": 0.9238845144356955,
      "grad_norm": 0.08419251441955566,
      "learning_rate": 5.009573740853313e-07,
      "loss": 0.6155,
      "num_input_tokens_seen": 92274688,
      "step": 44
    },
    {
      "epoch": 0.9448818897637795,
      "grad_norm": 0.08720867335796356,
      "learning_rate": 2.230627961304993e-07,
      "loss": 0.6273,
      "num_input_tokens_seen": 94371840,
      "step": 45
    },
    {
      "epoch": 0.9658792650918635,
      "grad_norm": 0.08411751687526703,
      "learning_rate": 5.5828034421170907e-08,
      "loss": 0.624,
      "num_input_tokens_seen": 96468992,
      "step": 46
    },
    {
      "epoch": 0.9868766404199475,
      "grad_norm": 0.08487113565206528,
      "learning_rate": 0.0,
      "loss": 0.6356,
      "num_input_tokens_seen": 98566144,
      "step": 47
    },
    {
      "epoch": 0.9868766404199475,
      "num_input_tokens_seen": 98566144,
      "step": 47,
      "total_flos": 4.361803532655919e+18,
      "train_loss": 0.6996991406095788,
      "train_runtime": 8190.5414,
      "train_samples_per_second": 2.973,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 47,
  "num_input_tokens_seen": 98566144,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.361803532655919e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}