{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1755,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017094017094017094,
      "grad_norm": 15.0625,
      "learning_rate": 5.681818181818182e-08,
      "loss": 1.3066431283950806,
      "step": 1,
      "token_acc": 0.7159380060143419
    },
    {
      "epoch": 0.08547008547008547,
      "grad_norm": 7.46875,
      "learning_rate": 2.8409090909090916e-06,
      "loss": 1.2084802900041853,
      "step": 50,
      "token_acc": 0.7292212264173042
    },
    {
      "epoch": 0.17094017094017094,
      "grad_norm": 2.890625,
      "learning_rate": 4.999360732624273e-06,
      "loss": 0.9122968292236329,
      "step": 100,
      "token_acc": 0.753969500240032
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 2.921875,
      "learning_rate": 4.9829537920824185e-06,
      "loss": 0.8321476745605468,
      "step": 150,
      "token_acc": 0.7675780382260687
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 3.015625,
      "learning_rate": 4.944516784287853e-06,
      "loss": 0.8292338562011718,
      "step": 200,
      "token_acc": 0.7674050705465351
    },
    {
      "epoch": 0.42735042735042733,
      "grad_norm": 3.09375,
      "learning_rate": 4.884390742516911e-06,
      "loss": 0.7959442901611328,
      "step": 250,
      "token_acc": 0.7729205563645134
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 2.53125,
      "learning_rate": 4.803109136521662e-06,
      "loss": 0.7765541076660156,
      "step": 300,
      "token_acc": 0.7768116204435069
    },
    {
      "epoch": 0.5982905982905983,
      "grad_norm": 3.171875,
      "learning_rate": 4.701393139306689e-06,
      "loss": 0.7773086547851562,
      "step": 350,
      "token_acc": 0.778023227333016
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 3.28125,
      "learning_rate": 4.5801452285042655e-06,
      "loss": 0.7690617370605469,
      "step": 400,
      "token_acc": 0.7791949190530791
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 3.109375,
      "learning_rate": 4.440441179119851e-06,
      "loss": 0.7732680511474609,
      "step": 450,
      "token_acc": 0.7783357143196153
    },
    {
      "epoch": 0.8547008547008547,
      "grad_norm": 2.765625,
      "learning_rate": 4.28352051869247e-06,
      "loss": 0.776756591796875,
      "step": 500,
      "token_acc": 0.7770325603100023
    },
    {
      "epoch": 0.9401709401709402,
      "grad_norm": 2.9375,
      "learning_rate": 4.110775529556807e-06,
      "loss": 0.7824362945556641,
      "step": 550,
      "token_acc": 0.7757224632997877
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 2.78125,
      "learning_rate": 3.923738895784698e-06,
      "loss": 0.7578450775146485,
      "step": 600,
      "token_acc": 0.7808272094745979
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 2.859375,
      "learning_rate": 3.7240701044088277e-06,
      "loss": 0.7588211059570312,
      "step": 650,
      "token_acc": 0.7814435027994716
    },
    {
      "epoch": 1.1965811965811965,
      "grad_norm": 3.46875,
      "learning_rate": 3.5135407215841166e-06,
      "loss": 0.7481551361083985,
      "step": 700,
      "token_acc": 0.7833868291553018
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 2.921875,
      "learning_rate": 3.294018674324384e-06,
      "loss": 0.753250732421875,
      "step": 750,
      "token_acc": 0.7816448681001995
    },
    {
      "epoch": 1.3675213675213675,
      "grad_norm": 3.390625,
      "learning_rate": 3.0674516772749886e-06,
      "loss": 0.7472420501708984,
      "step": 800,
      "token_acc": 0.7838917921918229
    },
    {
      "epoch": 1.452991452991453,
      "grad_norm": 3.140625,
      "learning_rate": 2.835849951567775e-06,
      "loss": 0.7469297027587891,
      "step": 850,
      "token_acc": 0.7837927886809676
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 3.078125,
      "learning_rate": 2.60126838908573e-06,
      "loss": 0.7334256744384766,
      "step": 900,
      "token_acc": 0.7865374697051991
    },
    {
      "epoch": 1.623931623931624,
      "grad_norm": 3.3125,
      "learning_rate": 2.365788320385306e-06,
      "loss": 0.7391526031494141,
      "step": 950,
      "token_acc": 0.783706698418852
    },
    {
      "epoch": 1.7094017094017095,
      "grad_norm": 2.890625,
      "learning_rate": 2.131499048040996e-06,
      "loss": 0.7512391662597656,
      "step": 1000,
      "token_acc": 0.7837811052849704
    },
    {
      "epoch": 1.7948717948717947,
      "grad_norm": 2.984375,
      "learning_rate": 1.9004793092579756e-06,
      "loss": 0.7405524444580078,
      "step": 1050,
      "token_acc": 0.7852440708156427
    },
    {
      "epoch": 1.8803418803418803,
      "grad_norm": 3.21875,
      "learning_rate": 1.6747788322262437e-06,
      "loss": 0.7450194549560547,
      "step": 1100,
      "token_acc": 0.7843423893486866
    },
    {
      "epoch": 1.965811965811966,
      "grad_norm": 2.859375,
      "learning_rate": 1.4564001498579425e-06,
      "loss": 0.7450698089599609,
      "step": 1150,
      "token_acc": 0.7845538037725732
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 3.3125,
      "learning_rate": 1.247280832265926e-06,
      "loss": 0.7369001770019531,
      "step": 1200,
      "token_acc": 0.7857595940374247
    },
    {
      "epoch": 2.1367521367521367,
      "grad_norm": 2.890625,
      "learning_rate": 1.0492762956263162e-06,
      "loss": 0.7386644744873047,
      "step": 1250,
      "token_acc": 0.7860841155134701
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 2.59375,
      "learning_rate": 8.641433399538466e-07,
      "loss": 0.7391439056396485,
      "step": 1300,
      "token_acc": 0.7862151522825112
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 3.03125,
      "learning_rate": 6.935245618514666e-07,
      "loss": 0.7429191589355468,
      "step": 1350,
      "token_acc": 0.7847435690017797
    },
    {
      "epoch": 2.393162393162393,
      "grad_norm": 2.71875,
      "learning_rate": 5.389337805324687e-07,
      "loss": 0.7441853332519531,
      "step": 1400,
      "token_acc": 0.7835661798058605
    },
    {
      "epoch": 2.4786324786324787,
      "grad_norm": 3.265625,
      "learning_rate": 4.017426064230995e-07,
      "loss": 0.7286052703857422,
      "step": 1450,
      "token_acc": 0.7877004145766489
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 2.984375,
      "learning_rate": 2.8316827151605444e-07,
      "loss": 0.7406098175048829,
      "step": 1500,
      "token_acc": 0.7840002165547049
    },
    {
      "epoch": 2.6495726495726495,
      "grad_norm": 3.390625,
      "learning_rate": 1.8426282945033957e-07,
      "loss": 0.7333684539794922,
      "step": 1550,
      "token_acc": 0.7866899334919993
    },
    {
      "epoch": 2.735042735042735,
      "grad_norm": 3.140625,
      "learning_rate": 1.0590382114005481e-07,
      "loss": 0.7373855590820313,
      "step": 1600,
      "token_acc": 0.7864740649587948
    },
    {
      "epoch": 2.8205128205128203,
      "grad_norm": 3.625,
      "learning_rate": 4.878648877151643e-08,
      "loss": 0.7367401123046875,
      "step": 1650,
      "token_acc": 0.7855127723260985
    },
    {
      "epoch": 2.905982905982906,
      "grad_norm": 2.546875,
      "learning_rate": 1.3417607250237053e-08,
      "loss": 0.7399304962158203,
      "step": 1700,
      "token_acc": 0.7852329450915141
    },
    {
      "epoch": 2.9914529914529915,
      "grad_norm": 3.140625,
      "learning_rate": 1.1098782838336874e-10,
      "loss": 0.7475210571289063,
      "step": 1750,
      "token_acc": 0.7824921559838638
    }
  ],
  "logging_steps": 50,
  "max_steps": 1755,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.872592034540954e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}