{
  "best_metric": 0.12700584530830383,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.5437737901033171,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001087547580206634,
      "eval_loss": 2.6140365600585938,
      "eval_runtime": 22.8682,
      "eval_samples_per_second": 16.967,
      "eval_steps_per_second": 4.242,
      "step": 1
    },
    {
      "epoch": 0.010875475802066341,
      "grad_norm": 1.15413498878479,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 0.6819,
      "step": 10
    },
    {
      "epoch": 0.021750951604132682,
      "grad_norm": 1.6452891826629639,
      "learning_rate": 8.400000000000001e-05,
      "loss": 0.6379,
      "step": 20
    },
    {
      "epoch": 0.03262642740619902,
      "grad_norm": 2.625800848007202,
      "learning_rate": 0.000126,
      "loss": 0.4516,
      "step": 30
    },
    {
      "epoch": 0.043501903208265365,
      "grad_norm": 6.286452770233154,
      "learning_rate": 0.00016800000000000002,
      "loss": 0.5501,
      "step": 40
    },
    {
      "epoch": 0.054377379010331704,
      "grad_norm": 4.992573261260986,
      "learning_rate": 0.00021,
      "loss": 0.4475,
      "step": 50
    },
    {
      "epoch": 0.054377379010331704,
      "eval_loss": 0.6009775400161743,
      "eval_runtime": 22.7637,
      "eval_samples_per_second": 17.045,
      "eval_steps_per_second": 4.261,
      "step": 50
    },
    {
      "epoch": 0.06525285481239804,
      "grad_norm": 1.2332814931869507,
      "learning_rate": 0.00020974422527728155,
      "loss": 0.2856,
      "step": 60
    },
    {
      "epoch": 0.07612833061446438,
      "grad_norm": 0.9268720149993896,
      "learning_rate": 0.0002089781472178649,
      "loss": 0.2699,
      "step": 70
    },
    {
      "epoch": 0.08700380641653073,
      "grad_norm": 1.5051002502441406,
      "learning_rate": 0.0002077054980770496,
      "loss": 0.2242,
      "step": 80
    },
    {
      "epoch": 0.09787928221859707,
      "grad_norm": 4.559469223022461,
      "learning_rate": 0.00020593247807352348,
      "loss": 0.2854,
      "step": 90
    },
    {
      "epoch": 0.10875475802066341,
      "grad_norm": 2.309359073638916,
      "learning_rate": 0.00020366772518252038,
      "loss": 0.4822,
      "step": 100
    },
    {
      "epoch": 0.10875475802066341,
      "eval_loss": 0.6521262526512146,
      "eval_runtime": 22.8192,
      "eval_samples_per_second": 17.003,
      "eval_steps_per_second": 4.251,
      "step": 100
    },
    {
      "epoch": 0.11963023382272975,
      "grad_norm": 0.9215604662895203,
      "learning_rate": 0.0002009222730524731,
      "loss": 0.2915,
      "step": 110
    },
    {
      "epoch": 0.13050570962479607,
      "grad_norm": 0.9864150285720825,
      "learning_rate": 0.00019770949725018733,
      "loss": 0.2042,
      "step": 120
    },
    {
      "epoch": 0.14138118542686243,
      "grad_norm": 1.3311983346939087,
      "learning_rate": 0.00019404505009642473,
      "loss": 0.1785,
      "step": 130
    },
    {
      "epoch": 0.15225666122892875,
      "grad_norm": 2.455376386642456,
      "learning_rate": 0.0001899467844093695,
      "loss": 0.226,
      "step": 140
    },
    {
      "epoch": 0.1631321370309951,
      "grad_norm": 5.563918113708496,
      "learning_rate": 0.00018543466652749268,
      "loss": 0.2853,
      "step": 150
    },
    {
      "epoch": 0.1631321370309951,
      "eval_loss": 0.39147135615348816,
      "eval_runtime": 22.7958,
      "eval_samples_per_second": 17.021,
      "eval_steps_per_second": 4.255,
      "step": 150
    },
    {
      "epoch": 0.17400761283306146,
      "grad_norm": 0.6848308444023132,
      "learning_rate": 0.00018053067903555837,
      "loss": 0.2406,
      "step": 160
    },
    {
      "epoch": 0.18488308863512778,
      "grad_norm": 1.072629451751709,
      "learning_rate": 0.00017525871366768012,
      "loss": 0.1456,
      "step": 170
    },
    {
      "epoch": 0.19575856443719414,
      "grad_norm": 1.8140205144882202,
      "learning_rate": 0.00016964445490919413,
      "loss": 0.1917,
      "step": 180
    },
    {
      "epoch": 0.20663404023926046,
      "grad_norm": 2.534623861312866,
      "learning_rate": 0.00016371525486442843,
      "loss": 0.2614,
      "step": 190
    },
    {
      "epoch": 0.21750951604132682,
      "grad_norm": 3.094886302947998,
      "learning_rate": 0.0001575,
      "loss": 0.2873,
      "step": 200
    },
    {
      "epoch": 0.21750951604132682,
      "eval_loss": 0.3247433006763458,
      "eval_runtime": 22.7847,
      "eval_samples_per_second": 17.029,
      "eval_steps_per_second": 4.257,
      "step": 200
    },
    {
      "epoch": 0.22838499184339314,
      "grad_norm": 0.5655252933502197,
      "learning_rate": 0.00015102897041285315,
      "loss": 0.2144,
      "step": 210
    },
    {
      "epoch": 0.2392604676454595,
      "grad_norm": 0.7886796593666077,
      "learning_rate": 0.00014433369230867077,
      "loss": 0.1604,
      "step": 220
    },
    {
      "epoch": 0.2501359434475258,
      "grad_norm": 1.0239461660385132,
      "learning_rate": 0.0001374467844093695,
      "loss": 0.1419,
      "step": 230
    },
    {
      "epoch": 0.26101141924959215,
      "grad_norm": 4.1843976974487305,
      "learning_rate": 0.0001304017990379651,
      "loss": 0.2756,
      "step": 240
    },
    {
      "epoch": 0.27188689505165853,
      "grad_norm": 9.119248390197754,
      "learning_rate": 0.0001232330586550277,
      "loss": 0.2422,
      "step": 250
    },
    {
      "epoch": 0.27188689505165853,
      "eval_loss": 0.259118914604187,
      "eval_runtime": 22.8194,
      "eval_samples_per_second": 17.003,
      "eval_steps_per_second": 4.251,
      "step": 250
    },
    {
      "epoch": 0.28276237085372485,
      "grad_norm": 0.4750421941280365,
      "learning_rate": 0.00011597548864310363,
      "loss": 0.1849,
      "step": 260
    },
    {
      "epoch": 0.2936378466557912,
      "grad_norm": 0.6818949580192566,
      "learning_rate": 0.00010866444715376263,
      "loss": 0.1809,
      "step": 270
    },
    {
      "epoch": 0.3045133224578575,
      "grad_norm": 0.9162408113479614,
      "learning_rate": 0.00010133555284623744,
      "loss": 0.0971,
      "step": 280
    },
    {
      "epoch": 0.3153887982599239,
      "grad_norm": 1.3977360725402832,
      "learning_rate": 9.402451135689641e-05,
      "loss": 0.2537,
      "step": 290
    },
    {
      "epoch": 0.3262642740619902,
      "grad_norm": 3.654791831970215,
      "learning_rate": 8.676694134497232e-05,
      "loss": 0.3683,
      "step": 300
    },
    {
      "epoch": 0.3262642740619902,
      "eval_loss": 0.22318749129772186,
      "eval_runtime": 22.8297,
      "eval_samples_per_second": 16.995,
      "eval_steps_per_second": 4.249,
      "step": 300
    },
    {
      "epoch": 0.33713974986405654,
      "grad_norm": 0.3159692585468292,
      "learning_rate": 7.95982009620349e-05,
      "loss": 0.1784,
      "step": 310
    },
    {
      "epoch": 0.3480152256661229,
      "grad_norm": 0.8129618763923645,
      "learning_rate": 7.255321559063053e-05,
      "loss": 0.1069,
      "step": 320
    },
    {
      "epoch": 0.35889070146818924,
      "grad_norm": 1.2382850646972656,
      "learning_rate": 6.566630769132923e-05,
      "loss": 0.13,
      "step": 330
    },
    {
      "epoch": 0.36976617727025557,
      "grad_norm": 2.3374767303466797,
      "learning_rate": 5.897102958714686e-05,
      "loss": 0.2035,
      "step": 340
    },
    {
      "epoch": 0.3806416530723219,
      "grad_norm": 2.183784008026123,
      "learning_rate": 5.250000000000002e-05,
      "loss": 0.2272,
      "step": 350
    },
    {
      "epoch": 0.3806416530723219,
      "eval_loss": 0.16593347489833832,
      "eval_runtime": 22.788,
      "eval_samples_per_second": 17.026,
      "eval_steps_per_second": 4.257,
      "step": 350
    },
    {
      "epoch": 0.3915171288743883,
      "grad_norm": 0.5802284479141235,
      "learning_rate": 4.62847451355716e-05,
      "loss": 0.1449,
      "step": 360
    },
    {
      "epoch": 0.4023926046764546,
      "grad_norm": 2.2887635231018066,
      "learning_rate": 4.035554509080588e-05,
      "loss": 0.1412,
      "step": 370
    },
    {
      "epoch": 0.4132680804785209,
      "grad_norm": 1.0761778354644775,
      "learning_rate": 3.474128633231992e-05,
      "loss": 0.1024,
      "step": 380
    },
    {
      "epoch": 0.42414355628058725,
      "grad_norm": 1.304354190826416,
      "learning_rate": 2.946932096444165e-05,
      "loss": 0.1266,
      "step": 390
    },
    {
      "epoch": 0.43501903208265363,
      "grad_norm": 2.448615789413452,
      "learning_rate": 2.456533347250732e-05,
      "loss": 0.1724,
      "step": 400
    },
    {
      "epoch": 0.43501903208265363,
      "eval_loss": 0.1496591418981552,
      "eval_runtime": 22.6015,
      "eval_samples_per_second": 17.167,
      "eval_steps_per_second": 4.292,
      "step": 400
    },
    {
      "epoch": 0.44589450788471996,
      "grad_norm": 0.5191034078598022,
      "learning_rate": 2.005321559063053e-05,
      "loss": 0.1327,
      "step": 410
    },
    {
      "epoch": 0.4567699836867863,
      "grad_norm": 0.6500219106674194,
      "learning_rate": 1.5954949903575276e-05,
      "loss": 0.1289,
      "step": 420
    },
    {
      "epoch": 0.4676454594888526,
      "grad_norm": 0.7300875186920166,
      "learning_rate": 1.2290502749812666e-05,
      "loss": 0.0955,
      "step": 430
    },
    {
      "epoch": 0.478520935290919,
      "grad_norm": 0.7386441230773926,
      "learning_rate": 9.077726947526898e-06,
      "loss": 0.1079,
      "step": 440
    },
    {
      "epoch": 0.4893964110929853,
      "grad_norm": 1.8114835023880005,
      "learning_rate": 6.332274817479627e-06,
      "loss": 0.1624,
      "step": 450
    },
    {
      "epoch": 0.4893964110929853,
      "eval_loss": 0.1295737773180008,
      "eval_runtime": 22.5929,
      "eval_samples_per_second": 17.174,
      "eval_steps_per_second": 4.293,
      "step": 450
    },
    {
      "epoch": 0.5002718868950516,
      "grad_norm": 0.49667298793792725,
      "learning_rate": 4.067521926476516e-06,
      "loss": 0.1261,
      "step": 460
    },
    {
      "epoch": 0.511147362697118,
      "grad_norm": 0.6079006195068359,
      "learning_rate": 2.294501922950403e-06,
      "loss": 0.0965,
      "step": 470
    },
    {
      "epoch": 0.5220228384991843,
      "grad_norm": 1.0314648151397705,
      "learning_rate": 1.021852782135112e-06,
      "loss": 0.1093,
      "step": 480
    },
    {
      "epoch": 0.5328983143012507,
      "grad_norm": 0.8024740815162659,
      "learning_rate": 2.5577472271845927e-07,
      "loss": 0.1305,
      "step": 490
    },
    {
      "epoch": 0.5437737901033171,
      "grad_norm": 1.7846750020980835,
      "learning_rate": 0.0,
      "loss": 0.1485,
      "step": 500
    },
    {
      "epoch": 0.5437737901033171,
      "eval_loss": 0.12700584530830383,
      "eval_runtime": 22.7807,
      "eval_samples_per_second": 17.032,
      "eval_steps_per_second": 4.258,
      "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": 9.002332739076096e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}