{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 96,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010471204188481676,
      "grad_norm": 47.982173919677734,
      "learning_rate": 1e-07,
      "loss": 1.7413017749786377,
      "step": 1,
      "token_acc": 0.7888167748377434
    },
    {
      "epoch": 0.05235602094240838,
      "grad_norm": 50.94432067871094,
      "learning_rate": 5e-07,
      "loss": 1.879357933998108,
      "step": 5,
      "token_acc": 0.776773720845036
    },
    {
      "epoch": 0.10471204188481675,
      "grad_norm": 48.849647521972656,
      "learning_rate": 4.962847472542185e-07,
      "loss": 1.821310043334961,
      "step": 10,
      "token_acc": 0.7765751836103595
    },
    {
      "epoch": 0.15706806282722513,
      "grad_norm": 39.60130310058594,
      "learning_rate": 4.852494138405941e-07,
      "loss": 1.4696194648742675,
      "step": 15,
      "token_acc": 0.7860804416403786
    },
    {
      "epoch": 0.2094240837696335,
      "grad_norm": 20.00335693359375,
      "learning_rate": 4.6722199218125165e-07,
      "loss": 1.3047430992126465,
      "step": 20,
      "token_acc": 0.7964089775561097
    },
    {
      "epoch": 0.2617801047120419,
      "grad_norm": 15.745766639709473,
      "learning_rate": 4.4273829369874486e-07,
      "loss": 1.0165138244628906,
      "step": 25,
      "token_acc": 0.8169903377020951
    },
    {
      "epoch": 0.31413612565445026,
      "grad_norm": 11.822181701660156,
      "learning_rate": 4.12526023417186e-07,
      "loss": 0.9544364929199218,
      "step": 30,
      "token_acc": 0.8224739374498797
    },
    {
      "epoch": 0.36649214659685864,
      "grad_norm": 10.846026420593262,
      "learning_rate": 3.77483151097534e-07,
      "loss": 0.8972492218017578,
      "step": 35,
      "token_acc": 0.8303642121931908
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 9.654153823852539,
      "learning_rate": 3.3865122176063385e-07,
      "loss": 0.7362692832946778,
      "step": 40,
      "token_acc": 0.8384876393601551
    },
    {
      "epoch": 0.4712041884816754,
      "grad_norm": 8.551219940185547,
      "learning_rate": 2.9718439886322915e-07,
      "loss": 0.6027413368225097,
      "step": 45,
      "token_acc": 0.8445121951219512
    },
    {
      "epoch": 0.5235602094240838,
      "grad_norm": 8.043594360351562,
      "learning_rate": 2.5431516022634714e-07,
      "loss": 0.5235415935516358,
      "step": 50,
      "token_acc": 0.8558808933002482
    },
    {
      "epoch": 0.5759162303664922,
      "grad_norm": 6.330442428588867,
      "learning_rate": 2.1131766630242964e-07,
      "loss": 0.5125304222106933,
      "step": 55,
      "token_acc": 0.8577164120642381
    },
    {
      "epoch": 0.6282722513089005,
      "grad_norm": 5.42710018157959,
      "learning_rate": 1.6946988955037738e-07,
      "loss": 0.47348899841308595,
      "step": 60,
      "token_acc": 0.8619181809347974
    },
    {
      "epoch": 0.680628272251309,
      "grad_norm": 4.45565128326416,
      "learning_rate": 1.3001563051005346e-07,
      "loss": 0.40836124420166015,
      "step": 65,
      "token_acc": 0.8791852955787381
    },
    {
      "epoch": 0.7329842931937173,
      "grad_norm": 4.402743339538574,
      "learning_rate": 9.412754953531663e-08,
      "loss": 0.37663998603820803,
      "step": 70,
      "token_acc": 0.8872172960047823
    },
    {
      "epoch": 0.7853403141361257,
      "grad_norm": 4.535104751586914,
      "learning_rate": 6.28723129572247e-08,
      "loss": 0.40417027473449707,
      "step": 75,
      "token_acc": 0.8783559504051548
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 4.095034122467041,
      "learning_rate": 3.7178889603912216e-08,
      "loss": 0.4013843059539795,
      "step": 80,
      "token_acc": 0.8795386158475427
    },
    {
      "epoch": 0.8900523560209425,
      "grad_norm": 4.874212741851807,
      "learning_rate": 1.7810939968674416e-08,
      "loss": 0.42403125762939453,
      "step": 85,
      "token_acc": 0.8744140625
    },
    {
      "epoch": 0.9424083769633508,
      "grad_norm": 4.154896259307861,
      "learning_rate": 5.344118676011172e-09,
      "loss": 0.41933584213256836,
      "step": 90,
      "token_acc": 0.8789355687688859
    },
    {
      "epoch": 0.9947643979057592,
      "grad_norm": 4.3949971199035645,
      "learning_rate": 1.4896486223239802e-10,
      "loss": 0.4075876235961914,
      "step": 95,
      "token_acc": 0.8777237354085603
    }
  ],
  "logging_steps": 5,
  "max_steps": 96,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.0101394588513075e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}