{
  "best_metric": 1.303171157836914,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.055206680008281,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001380167000207025,
      "eval_loss": 2.196531057357788,
      "eval_runtime": 194.725,
      "eval_samples_per_second": 15.668,
      "eval_steps_per_second": 3.918,
      "step": 1
    },
    {
      "epoch": 0.001380167000207025,
      "grad_norm": 1.853713035583496,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 1.9047,
      "step": 10
    },
    {
      "epoch": 0.00276033400041405,
      "grad_norm": 2.0089311599731445,
      "learning_rate": 8.080000000000001e-05,
      "loss": 1.6083,
      "step": 20
    },
    {
      "epoch": 0.004140501000621075,
      "grad_norm": 1.6798384189605713,
      "learning_rate": 0.00012119999999999999,
      "loss": 1.4963,
      "step": 30
    },
    {
      "epoch": 0.0055206680008281,
      "grad_norm": 2.0184950828552246,
      "learning_rate": 0.00016160000000000002,
      "loss": 1.4766,
      "step": 40
    },
    {
      "epoch": 0.006900835001035125,
      "grad_norm": 2.2714614868164062,
      "learning_rate": 0.000202,
      "loss": 1.6766,
      "step": 50
    },
    {
      "epoch": 0.006900835001035125,
      "eval_loss": 1.5489071607589722,
      "eval_runtime": 194.1989,
      "eval_samples_per_second": 15.711,
      "eval_steps_per_second": 3.929,
      "step": 50
    },
    {
      "epoch": 0.00828100200124215,
      "grad_norm": 1.3468365669250488,
      "learning_rate": 0.00020175396907624226,
      "loss": 1.3174,
      "step": 60
    },
    {
      "epoch": 0.009661169001449175,
      "grad_norm": 1.405402421951294,
      "learning_rate": 0.0002010170749428986,
      "loss": 1.4007,
      "step": 70
    },
    {
      "epoch": 0.0110413360016562,
      "grad_norm": 1.607871174812317,
      "learning_rate": 0.00019979290767411438,
      "loss": 1.481,
      "step": 80
    },
    {
      "epoch": 0.012421503001863225,
      "grad_norm": 1.7328439950942993,
      "learning_rate": 0.0001980874312897702,
      "loss": 1.4341,
      "step": 90
    },
    {
      "epoch": 0.01380167000207025,
      "grad_norm": 1.9513015747070312,
      "learning_rate": 0.00019590895469937675,
      "loss": 1.5601,
      "step": 100
    },
    {
      "epoch": 0.01380167000207025,
      "eval_loss": 1.470448613166809,
      "eval_runtime": 194.0541,
      "eval_samples_per_second": 15.722,
      "eval_steps_per_second": 3.932,
      "step": 100
    },
    {
      "epoch": 0.015181837002277276,
      "grad_norm": 1.1693236827850342,
      "learning_rate": 0.0001932680912219027,
      "loss": 1.1405,
      "step": 110
    },
    {
      "epoch": 0.0165620040024843,
      "grad_norm": 1.6762423515319824,
      "learning_rate": 0.00019017770687875164,
      "loss": 1.4333,
      "step": 120
    },
    {
      "epoch": 0.017942171002691326,
      "grad_norm": 1.6374577283859253,
      "learning_rate": 0.000186652857711799,
      "loss": 1.4104,
      "step": 130
    },
    {
      "epoch": 0.01932233800289835,
      "grad_norm": 1.8635785579681396,
      "learning_rate": 0.00018271071643186968,
      "loss": 1.473,
      "step": 140
    },
    {
      "epoch": 0.020702505003105377,
      "grad_norm": 2.215712547302246,
      "learning_rate": 0.00017837048875501678,
      "loss": 1.591,
      "step": 150
    },
    {
      "epoch": 0.020702505003105377,
      "eval_loss": 1.4511727094650269,
      "eval_runtime": 194.0225,
      "eval_samples_per_second": 15.725,
      "eval_steps_per_second": 3.933,
      "step": 150
    },
    {
      "epoch": 0.0220826720033124,
      "grad_norm": 1.410007357597351,
      "learning_rate": 0.00017365331983420376,
      "loss": 1.2349,
      "step": 160
    },
    {
      "epoch": 0.023462839003519427,
      "grad_norm": 1.6017369031906128,
      "learning_rate": 0.0001685821912422447,
      "loss": 1.3995,
      "step": 170
    },
    {
      "epoch": 0.02484300600372645,
      "grad_norm": 1.6010783910751343,
      "learning_rate": 0.00016318180900789148,
      "loss": 1.3827,
      "step": 180
    },
    {
      "epoch": 0.026223173003933477,
      "grad_norm": 1.8045480251312256,
      "learning_rate": 0.00015747848325054544,
      "loss": 1.4918,
      "step": 190
    },
    {
      "epoch": 0.0276033400041405,
      "grad_norm": 1.9998146295547485,
      "learning_rate": 0.0001515,
      "loss": 1.4707,
      "step": 200
    },
    {
      "epoch": 0.0276033400041405,
      "eval_loss": 1.4300576448440552,
      "eval_runtime": 193.9168,
      "eval_samples_per_second": 15.734,
      "eval_steps_per_second": 3.935,
      "step": 200
    },
    {
      "epoch": 0.028983507004347524,
      "grad_norm": 1.4455054998397827,
      "learning_rate": 0.00014527548582569683,
      "loss": 1.1305,
      "step": 210
    },
    {
      "epoch": 0.03036367400455455,
      "grad_norm": 1.4689016342163086,
      "learning_rate": 0.00013883526593500714,
      "loss": 1.3947,
      "step": 220
    },
    {
      "epoch": 0.031743841004761575,
      "grad_norm": 1.685587763786316,
      "learning_rate": 0.0001322107164318697,
      "loss": 1.3514,
      "step": 230
    },
    {
      "epoch": 0.0331240080049686,
      "grad_norm": 1.8048762083053589,
      "learning_rate": 0.00012543411145556643,
      "loss": 1.4504,
      "step": 240
    },
    {
      "epoch": 0.03450417500517563,
      "grad_norm": 2.7551028728485107,
      "learning_rate": 0.00011853846594435998,
      "loss": 1.5985,
      "step": 250
    },
    {
      "epoch": 0.03450417500517563,
      "eval_loss": 1.4250391721725464,
      "eval_runtime": 194.211,
      "eval_samples_per_second": 15.71,
      "eval_steps_per_second": 3.929,
      "step": 250
    },
    {
      "epoch": 0.03588434200538265,
      "grad_norm": 1.2140876054763794,
      "learning_rate": 0.00011155737479003301,
      "loss": 1.1542,
      "step": 260
    },
    {
      "epoch": 0.037264509005589676,
      "grad_norm": 1.2436723709106445,
      "learning_rate": 0.00010452484916695262,
      "loss": 1.3743,
      "step": 270
    },
    {
      "epoch": 0.0386446760057967,
      "grad_norm": 1.5601242780685425,
      "learning_rate": 9.747515083304742e-05,
      "loss": 1.3219,
      "step": 280
    },
    {
      "epoch": 0.04002484300600373,
      "grad_norm": 1.6851481199264526,
      "learning_rate": 9.044262520996702e-05,
      "loss": 1.3735,
      "step": 290
    },
    {
      "epoch": 0.04140501000621075,
      "grad_norm": 1.7231396436691284,
      "learning_rate": 8.346153405564004e-05,
      "loss": 1.4879,
      "step": 300
    },
    {
      "epoch": 0.04140501000621075,
      "eval_loss": 1.3670674562454224,
      "eval_runtime": 194.5478,
      "eval_samples_per_second": 15.683,
      "eval_steps_per_second": 3.922,
      "step": 300
    },
    {
      "epoch": 0.04278517700641778,
      "grad_norm": 1.1776810884475708,
      "learning_rate": 7.656588854443357e-05,
      "loss": 1.0798,
      "step": 310
    },
    {
      "epoch": 0.0441653440066248,
      "grad_norm": 1.2887829542160034,
      "learning_rate": 6.978928356813031e-05,
      "loss": 1.3379,
      "step": 320
    },
    {
      "epoch": 0.045545511006831824,
      "grad_norm": 1.455325961112976,
      "learning_rate": 6.316473406499288e-05,
      "loss": 1.3066,
      "step": 330
    },
    {
      "epoch": 0.046925678007038854,
      "grad_norm": 1.5977486371994019,
      "learning_rate": 5.672451417430317e-05,
      "loss": 1.3588,
      "step": 340
    },
    {
      "epoch": 0.04830584500724588,
      "grad_norm": 1.935961127281189,
      "learning_rate": 5.050000000000002e-05,
      "loss": 1.4722,
      "step": 350
    },
    {
      "epoch": 0.04830584500724588,
      "eval_loss": 1.3290566205978394,
      "eval_runtime": 193.6171,
      "eval_samples_per_second": 15.758,
      "eval_steps_per_second": 3.941,
      "step": 350
    },
    {
      "epoch": 0.0496860120074529,
      "grad_norm": 1.0178029537200928,
      "learning_rate": 4.452151674945458e-05,
      "loss": 1.0677,
      "step": 360
    },
    {
      "epoch": 0.051066179007659925,
      "grad_norm": 1.2846441268920898,
      "learning_rate": 3.8818190992108515e-05,
      "loss": 1.3573,
      "step": 370
    },
    {
      "epoch": 0.052446346007866955,
      "grad_norm": 1.4894729852676392,
      "learning_rate": 3.3417808757755355e-05,
      "loss": 1.2733,
      "step": 380
    },
    {
      "epoch": 0.05382651300807398,
      "grad_norm": 1.49921452999115,
      "learning_rate": 2.8346680165796253e-05,
      "loss": 1.304,
      "step": 390
    },
    {
      "epoch": 0.055206680008281,
      "grad_norm": 2.0546510219573975,
      "learning_rate": 2.362951124498323e-05,
      "loss": 1.4644,
      "step": 400
    },
    {
      "epoch": 0.055206680008281,
      "eval_loss": 1.303171157836914,
      "eval_runtime": 194.2964,
      "eval_samples_per_second": 15.703,
      "eval_steps_per_second": 3.927,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.881983448947098e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}