{
  "best_metric": 0.800472617149353,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.18412815319462345,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003682563063892469,
      "eval_loss": 2.228027582168579,
      "eval_runtime": 104.8652,
      "eval_samples_per_second": 10.909,
      "eval_steps_per_second": 2.727,
      "step": 1
    },
    {
      "epoch": 0.0036825630638924692,
      "grad_norm": 3.6284472942352295,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 4.2939,
      "step": 10
    },
    {
      "epoch": 0.0073651261277849385,
      "grad_norm": 1.8257993459701538,
      "learning_rate": 8.400000000000001e-05,
      "loss": 3.6458,
      "step": 20
    },
    {
      "epoch": 0.011047689191677408,
      "grad_norm": 2.0177488327026367,
      "learning_rate": 0.000126,
      "loss": 3.1733,
      "step": 30
    },
    {
      "epoch": 0.014730252255569877,
      "grad_norm": 1.6397349834442139,
      "learning_rate": 0.00016800000000000002,
      "loss": 2.822,
      "step": 40
    },
    {
      "epoch": 0.018412815319462345,
      "grad_norm": 1.8872606754302979,
      "learning_rate": 0.00021,
      "loss": 2.5885,
      "step": 50
    },
    {
      "epoch": 0.018412815319462345,
      "eval_loss": 1.3068158626556396,
      "eval_runtime": 104.7025,
      "eval_samples_per_second": 10.926,
      "eval_steps_per_second": 2.732,
      "step": 50
    },
    {
      "epoch": 0.022095378383354815,
      "grad_norm": 1.3547375202178955,
      "learning_rate": 0.00020974422527728155,
      "loss": 2.5193,
      "step": 60
    },
    {
      "epoch": 0.025777941447247283,
      "grad_norm": 1.4830182790756226,
      "learning_rate": 0.0002089781472178649,
      "loss": 2.4821,
      "step": 70
    },
    {
      "epoch": 0.029460504511139754,
      "grad_norm": 1.312664270401001,
      "learning_rate": 0.0002077054980770496,
      "loss": 2.3063,
      "step": 80
    },
    {
      "epoch": 0.03314306757503222,
      "grad_norm": 1.2727351188659668,
      "learning_rate": 0.00020593247807352348,
      "loss": 2.3387,
      "step": 90
    },
    {
      "epoch": 0.03682563063892469,
      "grad_norm": 1.5231223106384277,
      "learning_rate": 0.00020366772518252038,
      "loss": 2.0461,
      "step": 100
    },
    {
      "epoch": 0.03682563063892469,
      "eval_loss": 1.1203691959381104,
      "eval_runtime": 104.8463,
      "eval_samples_per_second": 10.911,
      "eval_steps_per_second": 2.728,
      "step": 100
    },
    {
      "epoch": 0.040508193702817163,
      "grad_norm": 1.1611711978912354,
      "learning_rate": 0.0002009222730524731,
      "loss": 2.1793,
      "step": 110
    },
    {
      "epoch": 0.04419075676670963,
      "grad_norm": 1.2379854917526245,
      "learning_rate": 0.00019770949725018733,
      "loss": 2.153,
      "step": 120
    },
    {
      "epoch": 0.0478733198306021,
      "grad_norm": 1.262009859085083,
      "learning_rate": 0.00019404505009642473,
      "loss": 2.1378,
      "step": 130
    },
    {
      "epoch": 0.051555882894494566,
      "grad_norm": 1.2100757360458374,
      "learning_rate": 0.0001899467844093695,
      "loss": 2.0749,
      "step": 140
    },
    {
      "epoch": 0.05523844595838704,
      "grad_norm": 1.489582896232605,
      "learning_rate": 0.00018543466652749268,
      "loss": 1.9353,
      "step": 150
    },
    {
      "epoch": 0.05523844595838704,
      "eval_loss": 1.013873815536499,
      "eval_runtime": 104.9915,
      "eval_samples_per_second": 10.896,
      "eval_steps_per_second": 2.724,
      "step": 150
    },
    {
      "epoch": 0.05892100902227951,
      "grad_norm": 1.1306333541870117,
      "learning_rate": 0.00018053067903555837,
      "loss": 2.099,
      "step": 160
    },
    {
      "epoch": 0.06260357208617198,
      "grad_norm": 1.1093506813049316,
      "learning_rate": 0.00017525871366768012,
      "loss": 2.0291,
      "step": 170
    },
    {
      "epoch": 0.06628613515006444,
      "grad_norm": 1.1496107578277588,
      "learning_rate": 0.00016964445490919413,
      "loss": 2.0047,
      "step": 180
    },
    {
      "epoch": 0.06996869821395692,
      "grad_norm": 1.0870957374572754,
      "learning_rate": 0.00016371525486442843,
      "loss": 1.969,
      "step": 190
    },
    {
      "epoch": 0.07365126127784938,
      "grad_norm": 1.6815812587738037,
      "learning_rate": 0.0001575,
      "loss": 1.8075,
      "step": 200
    },
    {
      "epoch": 0.07365126127784938,
      "eval_loss": 0.967093825340271,
      "eval_runtime": 104.7287,
      "eval_samples_per_second": 10.923,
      "eval_steps_per_second": 2.731,
      "step": 200
    },
    {
      "epoch": 0.07733382434174185,
      "grad_norm": 1.2532967329025269,
      "learning_rate": 0.00015102897041285315,
      "loss": 1.9389,
      "step": 210
    },
    {
      "epoch": 0.08101638740563433,
      "grad_norm": 1.169727087020874,
      "learning_rate": 0.00014433369230867077,
      "loss": 1.9091,
      "step": 220
    },
    {
      "epoch": 0.08469895046952679,
      "grad_norm": 1.0527361631393433,
      "learning_rate": 0.0001374467844093695,
      "loss": 1.902,
      "step": 230
    },
    {
      "epoch": 0.08838151353341926,
      "grad_norm": 1.1085879802703857,
      "learning_rate": 0.0001304017990379651,
      "loss": 1.8043,
      "step": 240
    },
    {
      "epoch": 0.09206407659731172,
      "grad_norm": 1.3278361558914185,
      "learning_rate": 0.0001232330586550277,
      "loss": 1.5737,
      "step": 250
    },
    {
      "epoch": 0.09206407659731172,
      "eval_loss": 0.9121530055999756,
      "eval_runtime": 104.8025,
      "eval_samples_per_second": 10.916,
      "eval_steps_per_second": 2.729,
      "step": 250
    },
    {
      "epoch": 0.0957466396612042,
      "grad_norm": 1.1355035305023193,
      "learning_rate": 0.00011597548864310363,
      "loss": 1.8759,
      "step": 260
    },
    {
      "epoch": 0.09942920272509667,
      "grad_norm": 1.1549241542816162,
      "learning_rate": 0.00010866444715376263,
      "loss": 1.8859,
      "step": 270
    },
    {
      "epoch": 0.10311176578898913,
      "grad_norm": 1.074413537979126,
      "learning_rate": 0.00010133555284623744,
      "loss": 1.8034,
      "step": 280
    },
    {
      "epoch": 0.1067943288528816,
      "grad_norm": 1.0826478004455566,
      "learning_rate": 9.402451135689641e-05,
      "loss": 1.8102,
      "step": 290
    },
    {
      "epoch": 0.11047689191677408,
      "grad_norm": 1.3882075548171997,
      "learning_rate": 8.676694134497232e-05,
      "loss": 1.6126,
      "step": 300
    },
    {
      "epoch": 0.11047689191677408,
      "eval_loss": 0.8696406483650208,
      "eval_runtime": 104.6164,
      "eval_samples_per_second": 10.935,
      "eval_steps_per_second": 2.734,
      "step": 300
    },
    {
      "epoch": 0.11415945498066654,
      "grad_norm": 0.9779600501060486,
      "learning_rate": 7.95982009620349e-05,
      "loss": 1.7683,
      "step": 310
    },
    {
      "epoch": 0.11784201804455902,
      "grad_norm": 1.0219613313674927,
      "learning_rate": 7.255321559063053e-05,
      "loss": 1.6802,
      "step": 320
    },
    {
      "epoch": 0.12152458110845148,
      "grad_norm": 1.0174745321273804,
      "learning_rate": 6.566630769132923e-05,
      "loss": 1.7034,
      "step": 330
    },
    {
      "epoch": 0.12520714417234396,
      "grad_norm": 1.0329629182815552,
      "learning_rate": 5.897102958714686e-05,
      "loss": 1.6781,
      "step": 340
    },
    {
      "epoch": 0.1288897072362364,
      "grad_norm": 1.218892216682434,
      "learning_rate": 5.250000000000002e-05,
      "loss": 1.4372,
      "step": 350
    },
    {
      "epoch": 0.1288897072362364,
      "eval_loss": 0.8357728123664856,
      "eval_runtime": 104.8025,
      "eval_samples_per_second": 10.916,
      "eval_steps_per_second": 2.729,
      "step": 350
    },
    {
      "epoch": 0.13257227030012889,
      "grad_norm": 1.0614081621170044,
      "learning_rate": 4.62847451355716e-05,
      "loss": 1.7161,
      "step": 360
    },
    {
      "epoch": 0.13625483336402136,
      "grad_norm": 1.2188026905059814,
      "learning_rate": 4.035554509080588e-05,
      "loss": 1.6848,
      "step": 370
    },
    {
      "epoch": 0.13993739642791383,
      "grad_norm": 1.0060714483261108,
      "learning_rate": 3.474128633231992e-05,
      "loss": 1.6229,
      "step": 380
    },
    {
      "epoch": 0.1436199594918063,
      "grad_norm": 1.1352717876434326,
      "learning_rate": 2.946932096444165e-05,
      "loss": 1.6946,
      "step": 390
    },
    {
      "epoch": 0.14730252255569876,
      "grad_norm": 1.3413875102996826,
      "learning_rate": 2.456533347250732e-05,
      "loss": 1.5453,
      "step": 400
    },
    {
      "epoch": 0.14730252255569876,
      "eval_loss": 0.8128843307495117,
      "eval_runtime": 104.9077,
      "eval_samples_per_second": 10.905,
      "eval_steps_per_second": 2.726,
      "step": 400
    },
    {
      "epoch": 0.15098508561959123,
      "grad_norm": 0.9193152189254761,
      "learning_rate": 2.005321559063053e-05,
      "loss": 1.6275,
      "step": 410
    },
    {
      "epoch": 0.1546676486834837,
      "grad_norm": 1.0370545387268066,
      "learning_rate": 1.5954949903575276e-05,
      "loss": 1.6423,
      "step": 420
    },
    {
      "epoch": 0.15835021174737618,
      "grad_norm": 0.9968223571777344,
      "learning_rate": 1.2290502749812666e-05,
      "loss": 1.5805,
      "step": 430
    },
    {
      "epoch": 0.16203277481126865,
      "grad_norm": 0.9633427858352661,
      "learning_rate": 9.077726947526898e-06,
      "loss": 1.6058,
      "step": 440
    },
    {
      "epoch": 0.1657153378751611,
      "grad_norm": 1.313849687576294,
      "learning_rate": 6.332274817479627e-06,
      "loss": 1.4868,
      "step": 450
    },
    {
      "epoch": 0.1657153378751611,
      "eval_loss": 0.8024091124534607,
      "eval_runtime": 104.8859,
      "eval_samples_per_second": 10.907,
      "eval_steps_per_second": 2.727,
      "step": 450
    },
    {
      "epoch": 0.16939790093905358,
      "grad_norm": 1.1269716024398804,
      "learning_rate": 4.067521926476516e-06,
      "loss": 1.6888,
      "step": 460
    },
    {
      "epoch": 0.17308046400294605,
      "grad_norm": 1.138323426246643,
      "learning_rate": 2.294501922950403e-06,
      "loss": 1.6791,
      "step": 470
    },
    {
      "epoch": 0.17676302706683852,
      "grad_norm": 1.0652822256088257,
      "learning_rate": 1.021852782135112e-06,
      "loss": 1.6347,
      "step": 480
    },
    {
      "epoch": 0.180445590130731,
      "grad_norm": 0.9608269333839417,
      "learning_rate": 2.5577472271845927e-07,
      "loss": 1.7125,
      "step": 490
    },
    {
      "epoch": 0.18412815319462345,
      "grad_norm": 1.3455790281295776,
      "learning_rate": 0.0,
      "loss": 1.5007,
      "step": 500
    },
    {
      "epoch": 0.18412815319462345,
      "eval_loss": 0.800472617149353,
      "eval_runtime": 104.603,
      "eval_samples_per_second": 10.937,
      "eval_steps_per_second": 2.734,
      "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": 1.5092811439276032e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}