{
  "best_metric": 1.5063753128051758,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.42955326460481097,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000859106529209622,
      "eval_loss": 1.95401132106781,
      "eval_runtime": 27.5604,
      "eval_samples_per_second": 17.779,
      "eval_steps_per_second": 4.463,
      "step": 1
    },
    {
      "epoch": 0.00859106529209622,
      "grad_norm": 0.9405553936958313,
      "learning_rate": 4.36e-05,
      "loss": 1.9074,
      "step": 10
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 1.0190926790237427,
      "learning_rate": 8.72e-05,
      "loss": 1.6901,
      "step": 20
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 1.3096411228179932,
      "learning_rate": 0.0001308,
      "loss": 1.5987,
      "step": 30
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 1.06441330909729,
      "learning_rate": 0.0001744,
      "loss": 1.5752,
      "step": 40
    },
    {
      "epoch": 0.0429553264604811,
      "grad_norm": 3.1200854778289795,
      "learning_rate": 0.000218,
      "loss": 1.4327,
      "step": 50
    },
    {
      "epoch": 0.0429553264604811,
      "eval_loss": 1.7293239831924438,
      "eval_runtime": 27.5653,
      "eval_samples_per_second": 17.776,
      "eval_steps_per_second": 4.462,
      "step": 50
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 0.7793288230895996,
      "learning_rate": 0.00021773448147832086,
      "loss": 1.7899,
      "step": 60
    },
    {
      "epoch": 0.06013745704467354,
      "grad_norm": 1.007460117340088,
      "learning_rate": 0.0002169392194928312,
      "loss": 1.6296,
      "step": 70
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 1.0640578269958496,
      "learning_rate": 0.00021561808847998484,
      "loss": 1.6155,
      "step": 80
    },
    {
      "epoch": 0.07731958762886598,
      "grad_norm": 1.191985011100769,
      "learning_rate": 0.00021377752485727676,
      "loss": 1.5215,
      "step": 90
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 3.72426176071167,
      "learning_rate": 0.00021142649566566402,
      "loss": 1.4125,
      "step": 100
    },
    {
      "epoch": 0.0859106529209622,
      "eval_loss": 1.7307857275009155,
      "eval_runtime": 27.621,
      "eval_samples_per_second": 17.74,
      "eval_steps_per_second": 4.453,
      "step": 100
    },
    {
      "epoch": 0.09450171821305842,
      "grad_norm": 0.9484879970550537,
      "learning_rate": 0.0002085764548830435,
      "loss": 1.7982,
      "step": 110
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.964938759803772,
      "learning_rate": 0.00020524128762162305,
      "loss": 1.7195,
      "step": 120
    },
    {
      "epoch": 0.11168384879725086,
      "grad_norm": 1.1392478942871094,
      "learning_rate": 0.00020143724248105043,
      "loss": 1.5898,
      "step": 130
    },
    {
      "epoch": 0.12027491408934708,
      "grad_norm": 1.2410438060760498,
      "learning_rate": 0.0001971828523868693,
      "loss": 1.4812,
      "step": 140
    },
    {
      "epoch": 0.12886597938144329,
      "grad_norm": 3.722848892211914,
      "learning_rate": 0.0001924988442999686,
      "loss": 1.4084,
      "step": 150
    },
    {
      "epoch": 0.12886597938144329,
      "eval_loss": 1.7576016187667847,
      "eval_runtime": 27.7184,
      "eval_samples_per_second": 17.678,
      "eval_steps_per_second": 4.437,
      "step": 150
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 1.0603128671646118,
      "learning_rate": 0.00018740803823691298,
      "loss": 1.7395,
      "step": 160
    },
    {
      "epoch": 0.14604810996563575,
      "grad_norm": 1.1844924688339233,
      "learning_rate": 0.00018193523609311556,
      "loss": 1.5991,
      "step": 170
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 1.127656102180481,
      "learning_rate": 0.00017610710081049675,
      "loss": 1.5951,
      "step": 180
    },
    {
      "epoch": 0.16323024054982818,
      "grad_norm": 1.5854954719543457,
      "learning_rate": 0.00016995202647831142,
      "loss": 1.5208,
      "step": 190
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 3.6740827560424805,
      "learning_rate": 0.00016350000000000002,
      "loss": 1.3948,
      "step": 200
    },
    {
      "epoch": 0.1718213058419244,
      "eval_loss": 1.6833069324493408,
      "eval_runtime": 27.6079,
      "eval_samples_per_second": 17.749,
      "eval_steps_per_second": 4.455,
      "step": 200
    },
    {
      "epoch": 0.18041237113402062,
      "grad_norm": 0.8244263529777527,
      "learning_rate": 0.00015678245500000943,
      "loss": 1.78,
      "step": 210
    },
    {
      "epoch": 0.18900343642611683,
      "grad_norm": 0.9824907779693604,
      "learning_rate": 0.00014983211868233444,
      "loss": 1.6569,
      "step": 220
    },
    {
      "epoch": 0.19759450171821305,
      "grad_norm": 1.210037350654602,
      "learning_rate": 0.00014268285238686927,
      "loss": 1.6465,
      "step": 230
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 1.3609579801559448,
      "learning_rate": 0.00013536948662036378,
      "loss": 1.4355,
      "step": 240
    },
    {
      "epoch": 0.21477663230240548,
      "grad_norm": 2.412757396697998,
      "learning_rate": 0.00012792765136569544,
      "loss": 1.4067,
      "step": 250
    },
    {
      "epoch": 0.21477663230240548,
      "eval_loss": 1.633361577987671,
      "eval_runtime": 27.6613,
      "eval_samples_per_second": 17.714,
      "eval_steps_per_second": 4.447,
      "step": 250
    },
    {
      "epoch": 0.22336769759450173,
      "grad_norm": 0.8555697202682495,
      "learning_rate": 0.00012039360249617425,
      "loss": 1.7972,
      "step": 260
    },
    {
      "epoch": 0.23195876288659795,
      "grad_norm": 0.9596598744392395,
      "learning_rate": 0.00011280404514057264,
      "loss": 1.6636,
      "step": 270
    },
    {
      "epoch": 0.24054982817869416,
      "grad_norm": 1.0088611841201782,
      "learning_rate": 0.00010519595485942743,
      "loss": 1.5343,
      "step": 280
    },
    {
      "epoch": 0.24914089347079038,
      "grad_norm": 1.1968733072280884,
      "learning_rate": 9.76063975038258e-05,
      "loss": 1.4937,
      "step": 290
    },
    {
      "epoch": 0.25773195876288657,
      "grad_norm": 4.135494709014893,
      "learning_rate": 9.00723486343046e-05,
      "loss": 1.479,
      "step": 300
    },
    {
      "epoch": 0.25773195876288657,
      "eval_loss": 1.582470417022705,
      "eval_runtime": 27.5946,
      "eval_samples_per_second": 17.757,
      "eval_steps_per_second": 4.457,
      "step": 300
    },
    {
      "epoch": 0.2663230240549828,
      "grad_norm": 0.7815156579017639,
      "learning_rate": 8.263051337963623e-05,
      "loss": 1.711,
      "step": 310
    },
    {
      "epoch": 0.27491408934707906,
      "grad_norm": 0.9176328778266907,
      "learning_rate": 7.531714761313074e-05,
      "loss": 1.6178,
      "step": 320
    },
    {
      "epoch": 0.28350515463917525,
      "grad_norm": 1.0819611549377441,
      "learning_rate": 6.816788131766559e-05,
      "loss": 1.5278,
      "step": 330
    },
    {
      "epoch": 0.2920962199312715,
      "grad_norm": 1.2202140092849731,
      "learning_rate": 6.121754499999055e-05,
      "loss": 1.4741,
      "step": 340
    },
    {
      "epoch": 0.3006872852233677,
      "grad_norm": 3.0831830501556396,
      "learning_rate": 5.450000000000003e-05,
      "loss": 1.447,
      "step": 350
    },
    {
      "epoch": 0.3006872852233677,
      "eval_loss": 1.5370266437530518,
      "eval_runtime": 27.5847,
      "eval_samples_per_second": 17.763,
      "eval_steps_per_second": 4.459,
      "step": 350
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 0.7905786037445068,
      "learning_rate": 4.804797352168861e-05,
      "loss": 1.7401,
      "step": 360
    },
    {
      "epoch": 0.3178694158075601,
      "grad_norm": 0.8707358241081238,
      "learning_rate": 4.189289918950325e-05,
      "loss": 1.5886,
      "step": 370
    },
    {
      "epoch": 0.32646048109965636,
      "grad_norm": 1.027565360069275,
      "learning_rate": 3.606476390688449e-05,
      "loss": 1.5207,
      "step": 380
    },
    {
      "epoch": 0.33505154639175255,
      "grad_norm": 1.4600329399108887,
      "learning_rate": 3.0591961763087043e-05,
      "loss": 1.4404,
      "step": 390
    },
    {
      "epoch": 0.3436426116838488,
      "grad_norm": 3.2995972633361816,
      "learning_rate": 2.550115570003141e-05,
      "loss": 1.1546,
      "step": 400
    },
    {
      "epoch": 0.3436426116838488,
      "eval_loss": 1.5103766918182373,
      "eval_runtime": 27.585,
      "eval_samples_per_second": 17.763,
      "eval_steps_per_second": 4.459,
      "step": 400
    },
    {
      "epoch": 0.35223367697594504,
      "grad_norm": 0.7793974280357361,
      "learning_rate": 2.081714761313074e-05,
      "loss": 1.6656,
      "step": 410
    },
    {
      "epoch": 0.36082474226804123,
      "grad_norm": 0.9348426461219788,
      "learning_rate": 1.656275751894957e-05,
      "loss": 1.5795,
      "step": 420
    },
    {
      "epoch": 0.3694158075601375,
      "grad_norm": 1.0919979810714722,
      "learning_rate": 1.275871237837696e-05,
      "loss": 1.4984,
      "step": 430
    },
    {
      "epoch": 0.37800687285223367,
      "grad_norm": 1.2562652826309204,
      "learning_rate": 9.423545116956494e-06,
      "loss": 1.4936,
      "step": 440
    },
    {
      "epoch": 0.3865979381443299,
      "grad_norm": 2.6799798011779785,
      "learning_rate": 6.573504334335994e-06,
      "loss": 1.2333,
      "step": 450
    },
    {
      "epoch": 0.3865979381443299,
      "eval_loss": 1.5094099044799805,
      "eval_runtime": 27.6177,
      "eval_samples_per_second": 17.742,
      "eval_steps_per_second": 4.454,
      "step": 450
    },
    {
      "epoch": 0.3951890034364261,
      "grad_norm": 0.8970940709114075,
      "learning_rate": 4.22247514272324e-06,
      "loss": 1.6966,
      "step": 460
    },
    {
      "epoch": 0.40378006872852235,
      "grad_norm": 0.8676711320877075,
      "learning_rate": 2.38191152001518e-06,
      "loss": 1.5938,
      "step": 470
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 1.022979736328125,
      "learning_rate": 1.0607805071688306e-06,
      "loss": 1.5255,
      "step": 480
    },
    {
      "epoch": 0.4209621993127148,
      "grad_norm": 1.4544559717178345,
      "learning_rate": 2.655185216791625e-07,
      "loss": 1.3489,
      "step": 490
    },
    {
      "epoch": 0.42955326460481097,
      "grad_norm": 2.9970974922180176,
      "learning_rate": 0.0,
      "loss": 1.3885,
      "step": 500
    },
    {
      "epoch": 0.42955326460481097,
      "eval_loss": 1.5063753128051758,
      "eval_runtime": 27.5708,
      "eval_samples_per_second": 17.772,
      "eval_steps_per_second": 4.461,
      "step": 500
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.886804283392e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}