{
  "best_metric": 11.879236221313477,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.3941663381947182,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007883326763894363,
      "eval_loss": 11.92764663696289,
      "eval_runtime": 7.1099,
      "eval_samples_per_second": 75.247,
      "eval_steps_per_second": 18.847,
      "step": 1
    },
    {
      "epoch": 0.007883326763894364,
      "grad_norm": 0.07368365675210953,
      "learning_rate": 4.02e-05,
      "loss": 11.9274,
      "step": 10
    },
    {
      "epoch": 0.015766653527788728,
      "grad_norm": 0.07584132999181747,
      "learning_rate": 8.04e-05,
      "loss": 11.9287,
      "step": 20
    },
    {
      "epoch": 0.023649980291683092,
      "grad_norm": 0.09191010147333145,
      "learning_rate": 0.0001206,
      "loss": 11.9281,
      "step": 30
    },
    {
      "epoch": 0.031533307055577456,
      "grad_norm": 0.16363732516765594,
      "learning_rate": 0.0001608,
      "loss": 11.93,
      "step": 40
    },
    {
      "epoch": 0.039416633819471816,
      "grad_norm": 0.2393222153186798,
      "learning_rate": 0.000201,
      "loss": 11.9072,
      "step": 50
    },
    {
      "epoch": 0.039416633819471816,
      "eval_loss": 11.909907341003418,
      "eval_runtime": 6.7429,
      "eval_samples_per_second": 79.343,
      "eval_steps_per_second": 19.873,
      "step": 50
    },
    {
      "epoch": 0.047299960583366184,
      "grad_norm": 0.14083291590213776,
      "learning_rate": 0.00020075518705111234,
      "loss": 11.9181,
      "step": 60
    },
    {
      "epoch": 0.055183287347260544,
      "grad_norm": 0.1786942332983017,
      "learning_rate": 0.00020002194090852784,
      "loss": 11.9084,
      "step": 70
    },
    {
      "epoch": 0.06306661411115491,
      "grad_norm": 0.3063865900039673,
      "learning_rate": 0.00019880383387374748,
      "loss": 11.8998,
      "step": 80
    },
    {
      "epoch": 0.07094994087504927,
      "grad_norm": 0.29278698563575745,
      "learning_rate": 0.00019710680044180106,
      "loss": 11.8871,
      "step": 90
    },
    {
      "epoch": 0.07883326763894363,
      "grad_norm": 0.24070513248443604,
      "learning_rate": 0.0001949391083889838,
      "loss": 11.8757,
      "step": 100
    },
    {
      "epoch": 0.07883326763894363,
      "eval_loss": 11.89173698425293,
      "eval_runtime": 6.9854,
      "eval_samples_per_second": 76.589,
      "eval_steps_per_second": 19.183,
      "step": 100
    },
    {
      "epoch": 0.086716594402838,
      "grad_norm": 0.11940794438123703,
      "learning_rate": 0.00019231131849308138,
      "loss": 11.9059,
      "step": 110
    },
    {
      "epoch": 0.09459992116673237,
      "grad_norm": 0.11173859983682632,
      "learning_rate": 0.00018923623308232218,
      "loss": 11.8996,
      "step": 120
    },
    {
      "epoch": 0.10248324793062673,
      "grad_norm": 0.18088971078395844,
      "learning_rate": 0.00018572883366372081,
      "loss": 11.8945,
      "step": 130
    },
    {
      "epoch": 0.11036657469452109,
      "grad_norm": 0.2551112771034241,
      "learning_rate": 0.00018180620793468224,
      "loss": 11.8876,
      "step": 140
    },
    {
      "epoch": 0.11824990145841545,
      "grad_norm": 0.24974049627780914,
      "learning_rate": 0.00017748746653345728,
      "loss": 11.8724,
      "step": 150
    },
    {
      "epoch": 0.11824990145841545,
      "eval_loss": 11.8869047164917,
      "eval_runtime": 7.2467,
      "eval_samples_per_second": 73.826,
      "eval_steps_per_second": 18.491,
      "step": 150
    },
    {
      "epoch": 0.12613322822230982,
      "grad_norm": 0.10702640563249588,
      "learning_rate": 0.00017279364993403443,
      "loss": 11.9001,
      "step": 160
    },
    {
      "epoch": 0.13401655498620418,
      "grad_norm": 0.16987697780132294,
      "learning_rate": 0.00016774762593906525,
      "loss": 11.8924,
      "step": 170
    },
    {
      "epoch": 0.14189988175009854,
      "grad_norm": 0.19377273321151733,
      "learning_rate": 0.00016237397827022866,
      "loss": 11.8923,
      "step": 180
    },
    {
      "epoch": 0.1497832085139929,
      "grad_norm": 0.20443686842918396,
      "learning_rate": 0.00015669888679881007,
      "loss": 11.8788,
      "step": 190
    },
    {
      "epoch": 0.15766653527788727,
      "grad_norm": 0.28372666239738464,
      "learning_rate": 0.00015075,
      "loss": 11.8638,
      "step": 200
    },
    {
      "epoch": 0.15766653527788727,
      "eval_loss": 11.884162902832031,
      "eval_runtime": 7.0156,
      "eval_samples_per_second": 76.258,
      "eval_steps_per_second": 19.1,
      "step": 200
    },
    {
      "epoch": 0.16554986204178163,
      "grad_norm": 0.08742058277130127,
      "learning_rate": 0.00014455630025230227,
      "loss": 11.8971,
      "step": 210
    },
    {
      "epoch": 0.173433188805676,
      "grad_norm": 0.17662465572357178,
      "learning_rate": 0.00013814796263829918,
      "loss": 11.8937,
      "step": 220
    },
    {
      "epoch": 0.18131651556957035,
      "grad_norm": 0.21377001702785492,
      "learning_rate": 0.00013155620793468223,
      "loss": 11.8888,
      "step": 230
    },
    {
      "epoch": 0.18919984233346474,
      "grad_norm": 0.2640247941017151,
      "learning_rate": 0.0001248131505077666,
      "loss": 11.8752,
      "step": 240
    },
    {
      "epoch": 0.1970831690973591,
      "grad_norm": 0.3643070161342621,
      "learning_rate": 0.00011795164185552652,
      "loss": 11.8626,
      "step": 250
    },
    {
      "epoch": 0.1970831690973591,
      "eval_loss": 11.881659507751465,
      "eval_runtime": 6.7952,
      "eval_samples_per_second": 78.732,
      "eval_steps_per_second": 19.72,
      "step": 250
    },
    {
      "epoch": 0.20496649586125346,
      "grad_norm": 0.08927304297685623,
      "learning_rate": 0.00011100511055839919,
      "loss": 11.8957,
      "step": 260
    },
    {
      "epoch": 0.21284982262514782,
      "grad_norm": 0.1372813731431961,
      "learning_rate": 0.00010400739941860137,
      "loss": 11.8902,
      "step": 270
    },
    {
      "epoch": 0.22073314938904218,
      "grad_norm": 0.22779017686843872,
      "learning_rate": 9.699260058139868e-05,
      "loss": 11.8869,
      "step": 280
    },
    {
      "epoch": 0.22861647615293654,
      "grad_norm": 0.24806085228919983,
      "learning_rate": 8.999488944160085e-05,
      "loss": 11.8799,
      "step": 290
    },
    {
      "epoch": 0.2364998029168309,
      "grad_norm": 0.2623824179172516,
      "learning_rate": 8.30483581444735e-05,
      "loss": 11.8597,
      "step": 300
    },
    {
      "epoch": 0.2364998029168309,
      "eval_loss": 11.880826950073242,
      "eval_runtime": 7.0977,
      "eval_samples_per_second": 75.377,
      "eval_steps_per_second": 18.879,
      "step": 300
    },
    {
      "epoch": 0.24438312968072526,
      "grad_norm": 0.10820131003856659,
      "learning_rate": 7.618684949223341e-05,
      "loss": 11.8955,
      "step": 310
    },
    {
      "epoch": 0.25226645644461965,
      "grad_norm": 0.16028447449207306,
      "learning_rate": 6.94437920653178e-05,
      "loss": 11.8891,
      "step": 320
    },
    {
      "epoch": 0.260149783208514,
      "grad_norm": 0.21786223351955414,
      "learning_rate": 6.285203736170084e-05,
      "loss": 11.8818,
      "step": 330
    },
    {
      "epoch": 0.26803310997240837,
      "grad_norm": 0.2079205960035324,
      "learning_rate": 5.6443699747697714e-05,
      "loss": 11.8724,
      "step": 340
    },
    {
      "epoch": 0.27591643673630273,
      "grad_norm": 0.3210531771183014,
      "learning_rate": 5.025000000000002e-05,
      "loss": 11.8598,
      "step": 350
    },
    {
      "epoch": 0.27591643673630273,
      "eval_loss": 11.880062103271484,
      "eval_runtime": 7.0148,
      "eval_samples_per_second": 76.267,
      "eval_steps_per_second": 19.102,
      "step": 350
    },
    {
      "epoch": 0.2837997635001971,
      "grad_norm": 0.0896448940038681,
      "learning_rate": 4.430111320118996e-05,
      "loss": 11.8917,
      "step": 360
    },
    {
      "epoch": 0.29168309026409145,
      "grad_norm": 0.1952148824930191,
      "learning_rate": 3.862602172977134e-05,
      "loss": 11.8869,
      "step": 370
    },
    {
      "epoch": 0.2995664170279858,
      "grad_norm": 0.20794124901294708,
      "learning_rate": 3.325237406093478e-05,
      "loss": 11.8858,
      "step": 380
    },
    {
      "epoch": 0.30744974379188017,
      "grad_norm": 0.34835031628608704,
      "learning_rate": 2.820635006596558e-05,
      "loss": 11.871,
      "step": 390
    },
    {
      "epoch": 0.31533307055577453,
      "grad_norm": 0.43546953797340393,
      "learning_rate": 2.351253346654272e-05,
      "loss": 11.8622,
      "step": 400
    },
    {
      "epoch": 0.31533307055577453,
      "eval_loss": 11.879236221313477,
      "eval_runtime": 6.9599,
      "eval_samples_per_second": 76.868,
      "eval_steps_per_second": 19.253,
      "step": 400
    },
    {
      "epoch": 0.3232163973196689,
      "grad_norm": 0.10507825762033463,
      "learning_rate": 1.9193792065317794e-05,
      "loss": 11.8928,
      "step": 410
    },
    {
      "epoch": 0.33109972408356325,
      "grad_norm": 0.19336579740047455,
      "learning_rate": 1.5271166336279193e-05,
      "loss": 11.8913,
      "step": 420
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 0.21657152473926544,
      "learning_rate": 1.1763766917677837e-05,
      "loss": 11.8834,
      "step": 430
    },
    {
      "epoch": 0.346866377611352,
      "grad_norm": 0.3501337766647339,
      "learning_rate": 8.688681506918602e-06,
      "loss": 11.8705,
      "step": 440
    },
    {
      "epoch": 0.35474970437524633,
      "grad_norm": 0.3057042360305786,
      "learning_rate": 6.060891611016215e-06,
      "loss": 11.8628,
      "step": 450
    },
    {
      "epoch": 0.35474970437524633,
      "eval_loss": 11.879561424255371,
      "eval_runtime": 7.0964,
      "eval_samples_per_second": 75.39,
      "eval_steps_per_second": 18.883,
      "step": 450
    },
    {
      "epoch": 0.3626330311391407,
      "grad_norm": 0.10696567595005035,
      "learning_rate": 3.893199558198952e-06,
      "loss": 11.8918,
      "step": 460
    },
    {
      "epoch": 0.37051635790303505,
      "grad_norm": 0.20454297959804535,
      "learning_rate": 2.1961661262525285e-06,
      "loss": 11.8865,
      "step": 470
    },
    {
      "epoch": 0.37839968466692947,
      "grad_norm": 0.21538551151752472,
      "learning_rate": 9.780590914721787e-07,
      "loss": 11.8861,
      "step": 480
    },
    {
      "epoch": 0.38628301143082383,
      "grad_norm": 0.281142920255661,
      "learning_rate": 2.4481294888766817e-07,
      "loss": 11.8759,
      "step": 490
    },
    {
      "epoch": 0.3941663381947182,
      "grad_norm": 0.4691304564476013,
      "learning_rate": 0.0,
      "loss": 11.8598,
      "step": 500
    },
    {
      "epoch": 0.3941663381947182,
      "eval_loss": 11.87945556640625,
      "eval_runtime": 7.1342,
      "eval_samples_per_second": 74.991,
      "eval_steps_per_second": 18.783,
      "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": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 342278799360.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}