{
  "best_global_step": 24806,
  "best_metric": 0.13123206794261932,
  "best_model_checkpoint": "Model1-v1-Rival/checkpoint-24806",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 24806,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04031282754172378,
      "grad_norm": 35.80685043334961,
      "learning_rate": 2.011285771866183e-07,
      "loss": 0.7492,
      "step": 500
    },
    {
      "epoch": 0.08062565508344756,
      "grad_norm": 27.830657958984375,
      "learning_rate": 4.0266021765417167e-07,
      "loss": 0.564,
      "step": 1000
    },
    {
      "epoch": 0.12093848262517133,
      "grad_norm": 22.993253707885742,
      "learning_rate": 6.041918581217252e-07,
      "loss": 0.497,
      "step": 1500
    },
    {
      "epoch": 0.16125131016689512,
      "grad_norm": 31.184377670288086,
      "learning_rate": 8.057234985892785e-07,
      "loss": 0.4362,
      "step": 2000
    },
    {
      "epoch": 0.2015641377086189,
      "grad_norm": 31.91282844543457,
      "learning_rate": 9.991937290033595e-07,
      "loss": 0.41,
      "step": 2500
    },
    {
      "epoch": 0.24187696525034266,
      "grad_norm": 42.18364715576172,
      "learning_rate": 9.767973124300112e-07,
      "loss": 0.3815,
      "step": 3000
    },
    {
      "epoch": 0.28218979279206646,
      "grad_norm": 31.624061584472656,
      "learning_rate": 9.544008958566627e-07,
      "loss": 0.3568,
      "step": 3500
    },
    {
      "epoch": 0.32250262033379024,
      "grad_norm": 36.55485534667969,
      "learning_rate": 9.320044792833146e-07,
      "loss": 0.341,
      "step": 4000
    },
    {
      "epoch": 0.362815447875514,
      "grad_norm": 34.942264556884766,
      "learning_rate": 9.096080627099664e-07,
      "loss": 0.3293,
      "step": 4500
    },
    {
      "epoch": 0.4031282754172378,
      "grad_norm": 30.162443161010742,
      "learning_rate": 8.872116461366181e-07,
      "loss": 0.3184,
      "step": 5000
    },
    {
      "epoch": 0.44344110295896155,
      "grad_norm": 42.151607513427734,
      "learning_rate": 8.648152295632698e-07,
      "loss": 0.3149,
      "step": 5500
    },
    {
      "epoch": 0.4837539305006853,
      "grad_norm": 21.629465103149414,
      "learning_rate": 8.424188129899216e-07,
      "loss": 0.2969,
      "step": 6000
    },
    {
      "epoch": 0.5240667580424091,
      "grad_norm": 45.252803802490234,
      "learning_rate": 8.200223964165734e-07,
      "loss": 0.2962,
      "step": 6500
    },
    {
      "epoch": 0.5643795855841329,
      "grad_norm": 31.193838119506836,
      "learning_rate": 7.97625979843225e-07,
      "loss": 0.2858,
      "step": 7000
    },
    {
      "epoch": 0.6046924131258566,
      "grad_norm": 96.9237289428711,
      "learning_rate": 7.752295632698768e-07,
      "loss": 0.268,
      "step": 7500
    },
    {
      "epoch": 0.6450052406675805,
      "grad_norm": 21.470144271850586,
      "learning_rate": 7.528331466965285e-07,
      "loss": 0.2622,
      "step": 8000
    },
    {
      "epoch": 0.6853180682093042,
      "grad_norm": 35.70467758178711,
      "learning_rate": 7.304367301231803e-07,
      "loss": 0.2741,
      "step": 8500
    },
    {
      "epoch": 0.725630895751028,
      "grad_norm": 19.73318862915039,
      "learning_rate": 7.080403135498319e-07,
      "loss": 0.2626,
      "step": 9000
    },
    {
      "epoch": 0.7659437232927517,
      "grad_norm": 23.529918670654297,
      "learning_rate": 6.856438969764838e-07,
      "loss": 0.2518,
      "step": 9500
    },
    {
      "epoch": 0.8062565508344756,
      "grad_norm": 41.51838302612305,
      "learning_rate": 6.632474804031355e-07,
      "loss": 0.2495,
      "step": 10000
    },
    {
      "epoch": 0.8465693783761993,
      "grad_norm": 14.217453956604004,
      "learning_rate": 6.408510638297872e-07,
      "loss": 0.2437,
      "step": 10500
    },
    {
      "epoch": 0.8868822059179231,
      "grad_norm": 18.972307205200195,
      "learning_rate": 6.184546472564389e-07,
      "loss": 0.2482,
      "step": 11000
    },
    {
      "epoch": 0.9271950334596468,
      "grad_norm": 47.28855514526367,
      "learning_rate": 5.960582306830907e-07,
      "loss": 0.2419,
      "step": 11500
    },
    {
      "epoch": 0.9675078610013707,
      "grad_norm": 48.309165954589844,
      "learning_rate": 5.736618141097424e-07,
      "loss": 0.2421,
      "step": 12000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9340860036526648,
      "eval_loss": 0.17090356349945068,
      "eval_model_preparation_time": 0.0026,
      "eval_runtime": 109.2506,
      "eval_samples_per_second": 441.087,
      "eval_steps_per_second": 55.139,
      "step": 12403
    },
    {
      "epoch": 1.0078206885430945,
      "grad_norm": 47.087913513183594,
      "learning_rate": 5.512653975363942e-07,
      "loss": 0.2372,
      "step": 12500
    },
    {
      "epoch": 1.0481335160848182,
      "grad_norm": 40.675697326660156,
      "learning_rate": 5.288689809630459e-07,
      "loss": 0.2249,
      "step": 13000
    },
    {
      "epoch": 1.088446343626542,
      "grad_norm": 46.77396774291992,
      "learning_rate": 5.064725643896977e-07,
      "loss": 0.2207,
      "step": 13500
    },
    {
      "epoch": 1.1287591711682659,
      "grad_norm": 69.7470703125,
      "learning_rate": 4.840761478163493e-07,
      "loss": 0.2276,
      "step": 14000
    },
    {
      "epoch": 1.1690719987099896,
      "grad_norm": 35.32638168334961,
      "learning_rate": 4.6167973124300107e-07,
      "loss": 0.2235,
      "step": 14500
    },
    {
      "epoch": 1.2093848262517133,
      "grad_norm": 63.080291748046875,
      "learning_rate": 4.3928331466965287e-07,
      "loss": 0.2219,
      "step": 15000
    },
    {
      "epoch": 1.249697653793437,
      "grad_norm": 45.029239654541016,
      "learning_rate": 4.1688689809630457e-07,
      "loss": 0.2184,
      "step": 15500
    },
    {
      "epoch": 1.2900104813351607,
      "grad_norm": 20.416336059570312,
      "learning_rate": 3.944904815229563e-07,
      "loss": 0.2081,
      "step": 16000
    },
    {
      "epoch": 1.3303233088768847,
      "grad_norm": 28.367952346801758,
      "learning_rate": 3.72094064949608e-07,
      "loss": 0.2157,
      "step": 16500
    },
    {
      "epoch": 1.3706361364186084,
      "grad_norm": 13.548885345458984,
      "learning_rate": 3.4969764837625977e-07,
      "loss": 0.212,
      "step": 17000
    },
    {
      "epoch": 1.4109489639603323,
      "grad_norm": 94.12673950195312,
      "learning_rate": 3.273012318029115e-07,
      "loss": 0.2075,
      "step": 17500
    },
    {
      "epoch": 1.451261791502056,
      "grad_norm": 38.12338638305664,
      "learning_rate": 3.049048152295632e-07,
      "loss": 0.2148,
      "step": 18000
    },
    {
      "epoch": 1.4915746190437797,
      "grad_norm": 45.156455993652344,
      "learning_rate": 2.82508398656215e-07,
      "loss": 0.2075,
      "step": 18500
    },
    {
      "epoch": 1.5318874465855035,
      "grad_norm": 18.083568572998047,
      "learning_rate": 2.601119820828667e-07,
      "loss": 0.2092,
      "step": 19000
    },
    {
      "epoch": 1.5722002741272272,
      "grad_norm": 27.93409538269043,
      "learning_rate": 2.3771556550951847e-07,
      "loss": 0.205,
      "step": 19500
    },
    {
      "epoch": 1.612513101668951,
      "grad_norm": 39.768192291259766,
      "learning_rate": 2.153191489361702e-07,
      "loss": 0.2039,
      "step": 20000
    },
    {
      "epoch": 1.6528259292106748,
      "grad_norm": 28.78324317932129,
      "learning_rate": 1.9292273236282195e-07,
      "loss": 0.204,
      "step": 20500
    },
    {
      "epoch": 1.6931387567523988,
      "grad_norm": 94.95115661621094,
      "learning_rate": 1.7052631578947368e-07,
      "loss": 0.2154,
      "step": 21000
    },
    {
      "epoch": 1.7334515842941225,
      "grad_norm": 51.76600646972656,
      "learning_rate": 1.4812989921612543e-07,
      "loss": 0.208,
      "step": 21500
    },
    {
      "epoch": 1.7737644118358462,
      "grad_norm": 24.089155197143555,
      "learning_rate": 1.2573348264277713e-07,
      "loss": 0.2071,
      "step": 22000
    },
    {
      "epoch": 1.81407723937757,
      "grad_norm": 46.96974182128906,
      "learning_rate": 1.0333706606942888e-07,
      "loss": 0.198,
      "step": 22500
    },
    {
      "epoch": 1.8543900669192936,
      "grad_norm": 66.37223815917969,
      "learning_rate": 8.094064949608062e-08,
      "loss": 0.2015,
      "step": 23000
    },
    {
      "epoch": 1.8947028944610174,
      "grad_norm": 42.39664077758789,
      "learning_rate": 5.854423292273236e-08,
      "loss": 0.1982,
      "step": 23500
    },
    {
      "epoch": 1.9350157220027413,
      "grad_norm": 42.68307113647461,
      "learning_rate": 3.61478163493841e-08,
      "loss": 0.1958,
      "step": 24000
    },
    {
      "epoch": 1.975328549544465,
      "grad_norm": 17.30171012878418,
      "learning_rate": 1.3751399776035833e-08,
      "loss": 0.2024,
      "step": 24500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9520795284741823,
      "eval_loss": 0.13123206794261932,
      "eval_model_preparation_time": 0.0026,
      "eval_runtime": 100.8699,
      "eval_samples_per_second": 477.734,
      "eval_steps_per_second": 59.72,
      "step": 24806
    }
  ],
  "logging_steps": 500,
  "max_steps": 24806,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 6.6484442538990895e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}