{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12977265992858178,
  "eval_steps": 500,
  "global_step": 60000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002162877665476363,
      "grad_norm": 2.268080472946167,
      "learning_rate": 4.9945869519559514e-05,
      "loss": 7.7847,
      "step": 1000
    },
    {
      "epoch": 0.004325755330952726,
      "grad_norm": 2.551193952560425,
      "learning_rate": 4.983760855867853e-05,
      "loss": 5.9343,
      "step": 2000
    },
    {
      "epoch": 0.006488632996429089,
      "grad_norm": 2.584500551223755,
      "learning_rate": 4.972934759779754e-05,
      "loss": 5.3418,
      "step": 3000
    },
    {
      "epoch": 0.008651510661905452,
      "grad_norm": 2.7399814128875732,
      "learning_rate": 4.962108663691656e-05,
      "loss": 4.9453,
      "step": 4000
    },
    {
      "epoch": 0.010814388327381816,
      "grad_norm": 2.7650134563446045,
      "learning_rate": 4.9512825676035575e-05,
      "loss": 4.6277,
      "step": 5000
    },
    {
      "epoch": 0.012977265992858178,
      "grad_norm": 2.8655128479003906,
      "learning_rate": 4.9404564715154586e-05,
      "loss": 4.3648,
      "step": 6000
    },
    {
      "epoch": 0.015140143658334541,
      "grad_norm": 2.8312480449676514,
      "learning_rate": 4.92963037542736e-05,
      "loss": 4.1441,
      "step": 7000
    },
    {
      "epoch": 0.017303021323810903,
      "grad_norm": 2.842963218688965,
      "learning_rate": 4.918804279339262e-05,
      "loss": 3.9787,
      "step": 8000
    },
    {
      "epoch": 0.019465898989287266,
      "grad_norm": 2.6685407161712646,
      "learning_rate": 4.907978183251164e-05,
      "loss": 3.8343,
      "step": 9000
    },
    {
      "epoch": 0.02162877665476363,
      "grad_norm": 2.7094473838806152,
      "learning_rate": 4.897152087163065e-05,
      "loss": 3.7211,
      "step": 10000
    },
    {
      "epoch": 0.023791654320239993,
      "grad_norm": 2.7870073318481445,
      "learning_rate": 4.886336817171055e-05,
      "loss": 3.6358,
      "step": 11000
    },
    {
      "epoch": 0.025954531985716355,
      "grad_norm": 2.6066818237304688,
      "learning_rate": 4.8755107210829566e-05,
      "loss": 3.5526,
      "step": 12000
    },
    {
      "epoch": 0.028117409651192717,
      "grad_norm": 2.8119983673095703,
      "learning_rate": 4.864695451090946e-05,
      "loss": 3.4758,
      "step": 13000
    },
    {
      "epoch": 0.030280287316669083,
      "grad_norm": 2.7353262901306152,
      "learning_rate": 4.853869355002847e-05,
      "loss": 3.4134,
      "step": 14000
    },
    {
      "epoch": 0.032443164982145445,
      "grad_norm": 2.6471846103668213,
      "learning_rate": 4.843054085010837e-05,
      "loss": 3.3547,
      "step": 15000
    },
    {
      "epoch": 0.03460604264762181,
      "grad_norm": 2.67105770111084,
      "learning_rate": 4.832227988922739e-05,
      "loss": 3.3033,
      "step": 16000
    },
    {
      "epoch": 0.03676892031309817,
      "grad_norm": 2.667982339859009,
      "learning_rate": 4.8214127189307287e-05,
      "loss": 3.2608,
      "step": 17000
    },
    {
      "epoch": 0.03893179797857453,
      "grad_norm": 2.588027238845825,
      "learning_rate": 4.81058662284263e-05,
      "loss": 3.2199,
      "step": 18000
    },
    {
      "epoch": 0.0410946756440509,
      "grad_norm": 2.650073289871216,
      "learning_rate": 4.799771352850619e-05,
      "loss": 3.1817,
      "step": 19000
    },
    {
      "epoch": 0.04325755330952726,
      "grad_norm": 2.4354302883148193,
      "learning_rate": 4.788945256762521e-05,
      "loss": 3.1464,
      "step": 20000
    },
    {
      "epoch": 0.045420430975003624,
      "grad_norm": 2.6227738857269287,
      "learning_rate": 4.778129986770511e-05,
      "loss": 3.1134,
      "step": 21000
    },
    {
      "epoch": 0.047583308640479986,
      "grad_norm": 2.5212135314941406,
      "learning_rate": 4.767303890682412e-05,
      "loss": 3.08,
      "step": 22000
    },
    {
      "epoch": 0.04974618630595635,
      "grad_norm": 2.4768059253692627,
      "learning_rate": 4.756488620690402e-05,
      "loss": 3.0511,
      "step": 23000
    },
    {
      "epoch": 0.05190906397143271,
      "grad_norm": 2.5772910118103027,
      "learning_rate": 4.7456625246023034e-05,
      "loss": 3.0225,
      "step": 24000
    },
    {
      "epoch": 0.05407194163690907,
      "grad_norm": 2.4655566215515137,
      "learning_rate": 4.7348472546102937e-05,
      "loss": 3.0053,
      "step": 25000
    },
    {
      "epoch": 0.056234819302385435,
      "grad_norm": 2.432565212249756,
      "learning_rate": 4.724021158522195e-05,
      "loss": 2.9726,
      "step": 26000
    },
    {
      "epoch": 0.058397696967861804,
      "grad_norm": 2.437964677810669,
      "learning_rate": 4.7131950624340964e-05,
      "loss": 2.9542,
      "step": 27000
    },
    {
      "epoch": 0.060560574633338166,
      "grad_norm": 2.498307466506958,
      "learning_rate": 4.702379792442086e-05,
      "loss": 2.9373,
      "step": 28000
    },
    {
      "epoch": 0.06272345229881453,
      "grad_norm": 2.3338165283203125,
      "learning_rate": 4.6915536963539876e-05,
      "loss": 2.9143,
      "step": 29000
    },
    {
      "epoch": 0.06488632996429089,
      "grad_norm": 2.2597150802612305,
      "learning_rate": 4.680738426361977e-05,
      "loss": 2.8947,
      "step": 30000
    },
    {
      "epoch": 0.06704920762976725,
      "grad_norm": 2.3500025272369385,
      "learning_rate": 4.669912330273879e-05,
      "loss": 2.8729,
      "step": 31000
    },
    {
      "epoch": 0.06921208529524361,
      "grad_norm": 2.592963457107544,
      "learning_rate": 4.6590970602818684e-05,
      "loss": 2.8638,
      "step": 32000
    },
    {
      "epoch": 0.07137496296071998,
      "grad_norm": 2.2916111946105957,
      "learning_rate": 4.64827096419377e-05,
      "loss": 2.8423,
      "step": 33000
    },
    {
      "epoch": 0.07353784062619634,
      "grad_norm": 2.298884153366089,
      "learning_rate": 4.63745569420176e-05,
      "loss": 2.8258,
      "step": 34000
    },
    {
      "epoch": 0.0757007182916727,
      "grad_norm": 2.2187180519104004,
      "learning_rate": 4.6266295981136614e-05,
      "loss": 2.8085,
      "step": 35000
    },
    {
      "epoch": 0.07786359595714906,
      "grad_norm": 2.3649799823760986,
      "learning_rate": 4.615814328121651e-05,
      "loss": 2.7946,
      "step": 36000
    },
    {
      "epoch": 0.08002647362262542,
      "grad_norm": 2.189671754837036,
      "learning_rate": 4.6049882320335526e-05,
      "loss": 2.7828,
      "step": 37000
    },
    {
      "epoch": 0.0821893512881018,
      "grad_norm": 2.341826915740967,
      "learning_rate": 4.594172962041542e-05,
      "loss": 2.7706,
      "step": 38000
    },
    {
      "epoch": 0.08435222895357816,
      "grad_norm": 2.3907382488250732,
      "learning_rate": 4.583346865953443e-05,
      "loss": 2.7548,
      "step": 39000
    },
    {
      "epoch": 0.08651510661905452,
      "grad_norm": 2.2284059524536133,
      "learning_rate": 4.5725315959614334e-05,
      "loss": 2.7453,
      "step": 40000
    },
    {
      "epoch": 0.08867798428453089,
      "grad_norm": 2.254753589630127,
      "learning_rate": 4.561705499873335e-05,
      "loss": 2.7335,
      "step": 41000
    },
    {
      "epoch": 0.09084086195000725,
      "grad_norm": 2.2830395698547363,
      "learning_rate": 4.550890229881325e-05,
      "loss": 2.7188,
      "step": 42000
    },
    {
      "epoch": 0.09300373961548361,
      "grad_norm": 2.2295284271240234,
      "learning_rate": 4.540064133793226e-05,
      "loss": 2.7066,
      "step": 43000
    },
    {
      "epoch": 0.09516661728095997,
      "grad_norm": 2.177199602127075,
      "learning_rate": 4.529248863801216e-05,
      "loss": 2.6916,
      "step": 44000
    },
    {
      "epoch": 0.09732949494643633,
      "grad_norm": 2.0382652282714844,
      "learning_rate": 4.5184227677131176e-05,
      "loss": 2.6852,
      "step": 45000
    },
    {
      "epoch": 0.0994923726119127,
      "grad_norm": 2.240755319595337,
      "learning_rate": 4.507607497721107e-05,
      "loss": 2.6793,
      "step": 46000
    },
    {
      "epoch": 0.10165525027738906,
      "grad_norm": 2.1940410137176514,
      "learning_rate": 4.496781401633008e-05,
      "loss": 2.6659,
      "step": 47000
    },
    {
      "epoch": 0.10381812794286542,
      "grad_norm": 2.203796148300171,
      "learning_rate": 4.4859661316409984e-05,
      "loss": 2.6526,
      "step": 48000
    },
    {
      "epoch": 0.10598100560834178,
      "grad_norm": 2.1186819076538086,
      "learning_rate": 4.4751400355529e-05,
      "loss": 2.6463,
      "step": 49000
    },
    {
      "epoch": 0.10814388327381814,
      "grad_norm": 2.13010573387146,
      "learning_rate": 4.46432476556089e-05,
      "loss": 2.6403,
      "step": 50000
    },
    {
      "epoch": 0.11030676093929451,
      "grad_norm": 2.1970157623291016,
      "learning_rate": 4.4535094955688785e-05,
      "loss": 2.6276,
      "step": 51000
    },
    {
      "epoch": 0.11246963860477087,
      "grad_norm": 2.1742944717407227,
      "learning_rate": 4.44268339948078e-05,
      "loss": 2.6178,
      "step": 52000
    },
    {
      "epoch": 0.11463251627024724,
      "grad_norm": 2.195935010910034,
      "learning_rate": 4.4318681294887705e-05,
      "loss": 2.6095,
      "step": 53000
    },
    {
      "epoch": 0.11679539393572361,
      "grad_norm": 2.0977721214294434,
      "learning_rate": 4.421042033400672e-05,
      "loss": 2.6037,
      "step": 54000
    },
    {
      "epoch": 0.11895827160119997,
      "grad_norm": 2.1214547157287598,
      "learning_rate": 4.410215937312573e-05,
      "loss": 2.5962,
      "step": 55000
    },
    {
      "epoch": 0.12112114926667633,
      "grad_norm": 2.216897964477539,
      "learning_rate": 4.399400667320563e-05,
      "loss": 2.5881,
      "step": 56000
    },
    {
      "epoch": 0.1232840269321527,
      "grad_norm": 2.1751599311828613,
      "learning_rate": 4.3885745712324644e-05,
      "loss": 2.5817,
      "step": 57000
    },
    {
      "epoch": 0.12544690459762906,
      "grad_norm": 2.1866142749786377,
      "learning_rate": 4.377748475144366e-05,
      "loss": 2.5691,
      "step": 58000
    },
    {
      "epoch": 0.1276097822631054,
      "grad_norm": 2.1192381381988525,
      "learning_rate": 4.366933205152356e-05,
      "loss": 2.5649,
      "step": 59000
    },
    {
      "epoch": 0.12977265992858178,
      "grad_norm": 1.9748364686965942,
      "learning_rate": 4.3561071090642574e-05,
      "loss": 2.5535,
      "step": 60000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 462347,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.30908615081984e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}