{
  "best_metric": 0.78855299949646,
  "best_model_checkpoint": "./results_v1/checkpoint-3724",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 3724,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10741138560687433,
      "grad_norm": 12224.1005859375,
      "learning_rate": 0.0004865735767991407,
      "loss": 0.9019,
      "step": 100
    },
    {
      "epoch": 0.21482277121374865,
      "grad_norm": 11560.216796875,
      "learning_rate": 0.00047314715359828143,
      "loss": 0.9088,
      "step": 200
    },
    {
      "epoch": 0.322234156820623,
      "grad_norm": 10229.27734375,
      "learning_rate": 0.0004597207303974221,
      "loss": 0.9132,
      "step": 300
    },
    {
      "epoch": 0.4296455424274973,
      "grad_norm": 23398.751953125,
      "learning_rate": 0.00044629430719656286,
      "loss": 0.9093,
      "step": 400
    },
    {
      "epoch": 0.5370569280343717,
      "grad_norm": 9462.7333984375,
      "learning_rate": 0.00043286788399570354,
      "loss": 0.9045,
      "step": 500
    },
    {
      "epoch": 0.644468313641246,
      "grad_norm": 11711.173828125,
      "learning_rate": 0.00041944146079484423,
      "loss": 0.9007,
      "step": 600
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 12136.8037109375,
      "learning_rate": 0.00040601503759398497,
      "loss": 0.896,
      "step": 700
    },
    {
      "epoch": 0.8592910848549946,
      "grad_norm": 17582.23828125,
      "learning_rate": 0.00039258861439312565,
      "loss": 0.8989,
      "step": 800
    },
    {
      "epoch": 0.966702470461869,
      "grad_norm": 10597.923828125,
      "learning_rate": 0.0003791621911922664,
      "loss": 0.8925,
      "step": 900
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8314220905303955,
      "eval_runtime": 18.8784,
      "eval_samples_per_second": 423.764,
      "eval_steps_per_second": 3.337,
      "step": 931
    },
    {
      "epoch": 1.0741138560687433,
      "grad_norm": 10806.78125,
      "learning_rate": 0.00036573576799140713,
      "loss": 0.8738,
      "step": 1000
    },
    {
      "epoch": 1.1815252416756177,
      "grad_norm": 11682.1171875,
      "learning_rate": 0.0003523093447905478,
      "loss": 0.8611,
      "step": 1100
    },
    {
      "epoch": 1.2889366272824918,
      "grad_norm": 14700.29296875,
      "learning_rate": 0.00033888292158968855,
      "loss": 0.8755,
      "step": 1200
    },
    {
      "epoch": 1.3963480128893662,
      "grad_norm": 11728.32421875,
      "learning_rate": 0.00032545649838882924,
      "loss": 0.8683,
      "step": 1300
    },
    {
      "epoch": 1.5037593984962405,
      "grad_norm": 12242.0029296875,
      "learning_rate": 0.0003120300751879699,
      "loss": 0.8745,
      "step": 1400
    },
    {
      "epoch": 1.6111707841031149,
      "grad_norm": 11073.6376953125,
      "learning_rate": 0.00029860365198711066,
      "loss": 0.848,
      "step": 1500
    },
    {
      "epoch": 1.7185821697099892,
      "grad_norm": 10194.4599609375,
      "learning_rate": 0.00028517722878625135,
      "loss": 0.8516,
      "step": 1600
    },
    {
      "epoch": 1.8259935553168636,
      "grad_norm": 12174.0341796875,
      "learning_rate": 0.00027175080558539203,
      "loss": 0.8597,
      "step": 1700
    },
    {
      "epoch": 1.933404940923738,
      "grad_norm": 11925.640625,
      "learning_rate": 0.00025832438238453277,
      "loss": 0.859,
      "step": 1800
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8080422878265381,
      "eval_runtime": 19.478,
      "eval_samples_per_second": 410.72,
      "eval_steps_per_second": 3.234,
      "step": 1862
    },
    {
      "epoch": 2.0408163265306123,
      "grad_norm": 12538.783203125,
      "learning_rate": 0.00024489795918367346,
      "loss": 0.8473,
      "step": 1900
    },
    {
      "epoch": 2.1482277121374866,
      "grad_norm": 11984.9697265625,
      "learning_rate": 0.00023147153598281417,
      "loss": 0.8413,
      "step": 2000
    },
    {
      "epoch": 2.255639097744361,
      "grad_norm": 12034.09765625,
      "learning_rate": 0.00021804511278195488,
      "loss": 0.8344,
      "step": 2100
    },
    {
      "epoch": 2.3630504833512354,
      "grad_norm": 10639.9912109375,
      "learning_rate": 0.00020461868958109562,
      "loss": 0.8344,
      "step": 2200
    },
    {
      "epoch": 2.4704618689581097,
      "grad_norm": 10943.125,
      "learning_rate": 0.0001911922663802363,
      "loss": 0.8309,
      "step": 2300
    },
    {
      "epoch": 2.5778732545649836,
      "grad_norm": 12608.966796875,
      "learning_rate": 0.00017776584317937702,
      "loss": 0.835,
      "step": 2400
    },
    {
      "epoch": 2.685284640171858,
      "grad_norm": 12656.138671875,
      "learning_rate": 0.00016433941997851773,
      "loss": 0.8338,
      "step": 2500
    },
    {
      "epoch": 2.7926960257787323,
      "grad_norm": 13147.025390625,
      "learning_rate": 0.00015091299677765844,
      "loss": 0.8361,
      "step": 2600
    },
    {
      "epoch": 2.9001074113856067,
      "grad_norm": 11629.3115234375,
      "learning_rate": 0.00013748657357679915,
      "loss": 0.8314,
      "step": 2700
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.793174684047699,
      "eval_runtime": 18.8558,
      "eval_samples_per_second": 424.272,
      "eval_steps_per_second": 3.341,
      "step": 2793
    },
    {
      "epoch": 3.007518796992481,
      "grad_norm": 11106.541015625,
      "learning_rate": 0.00012406015037593984,
      "loss": 0.8261,
      "step": 2800
    },
    {
      "epoch": 3.1149301825993554,
      "grad_norm": 11267.052734375,
      "learning_rate": 0.00011063372717508056,
      "loss": 0.8172,
      "step": 2900
    },
    {
      "epoch": 3.2223415682062297,
      "grad_norm": 10196.681640625,
      "learning_rate": 9.720730397422128e-05,
      "loss": 0.8162,
      "step": 3000
    },
    {
      "epoch": 3.329752953813104,
      "grad_norm": 11563.2431640625,
      "learning_rate": 8.378088077336197e-05,
      "loss": 0.8181,
      "step": 3100
    },
    {
      "epoch": 3.4371643394199785,
      "grad_norm": 12632.6240234375,
      "learning_rate": 7.035445757250269e-05,
      "loss": 0.8176,
      "step": 3200
    },
    {
      "epoch": 3.544575725026853,
      "grad_norm": 13568.869140625,
      "learning_rate": 5.692803437164339e-05,
      "loss": 0.8165,
      "step": 3300
    },
    {
      "epoch": 3.651987110633727,
      "grad_norm": 12489.8134765625,
      "learning_rate": 4.35016111707841e-05,
      "loss": 0.8205,
      "step": 3400
    },
    {
      "epoch": 3.7593984962406015,
      "grad_norm": 10397.326171875,
      "learning_rate": 3.007518796992481e-05,
      "loss": 0.819,
      "step": 3500
    },
    {
      "epoch": 3.866809881847476,
      "grad_norm": 9453.00390625,
      "learning_rate": 1.664876476906552e-05,
      "loss": 0.8167,
      "step": 3600
    },
    {
      "epoch": 3.9742212674543502,
      "grad_norm": 11430.806640625,
      "learning_rate": 3.22234156820623e-06,
      "loss": 0.8097,
      "step": 3700
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.78855299949646,
      "eval_runtime": 18.9148,
      "eval_samples_per_second": 422.95,
      "eval_steps_per_second": 3.331,
      "step": 3724
    }
  ],
  "logging_steps": 100,
  "max_steps": 3724,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6121847720443904e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}