{
  "best_metric": 1.8198388814926147,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 1.0633303808680248,
  "eval_steps": 100,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001771479185119575,
      "eval_loss": 4.6529459953308105,
      "eval_runtime": 16.7798,
      "eval_samples_per_second": 56.675,
      "eval_steps_per_second": 14.184,
      "step": 1
    },
    {
      "epoch": 0.01771479185119575,
      "grad_norm": 6.935274124145508,
      "learning_rate": 0.0002,
      "loss": 3.5332,
      "step": 10
    },
    {
      "epoch": 0.0354295837023915,
      "grad_norm": 3.5101845264434814,
      "learning_rate": 0.0001998582695676762,
      "loss": 2.1451,
      "step": 20
    },
    {
      "epoch": 0.053144375553587246,
      "grad_norm": 2.828544855117798,
      "learning_rate": 0.00019943348002101371,
      "loss": 2.034,
      "step": 30
    },
    {
      "epoch": 0.070859167404783,
      "grad_norm": 2.610250234603882,
      "learning_rate": 0.00019872683547213446,
      "loss": 1.9515,
      "step": 40
    },
    {
      "epoch": 0.08857395925597875,
      "grad_norm": 2.671312093734741,
      "learning_rate": 0.00019774033898178667,
      "loss": 1.9134,
      "step": 50
    },
    {
      "epoch": 0.10628875110717449,
      "grad_norm": 2.4686455726623535,
      "learning_rate": 0.0001964767868814516,
      "loss": 2.0368,
      "step": 60
    },
    {
      "epoch": 0.12400354295837024,
      "grad_norm": 2.524057388305664,
      "learning_rate": 0.00019493976084683813,
      "loss": 2.0019,
      "step": 70
    },
    {
      "epoch": 0.141718334809566,
      "grad_norm": 2.3468284606933594,
      "learning_rate": 0.00019313361774523385,
      "loss": 1.9573,
      "step": 80
    },
    {
      "epoch": 0.15943312666076173,
      "grad_norm": 2.1679277420043945,
      "learning_rate": 0.00019106347728549135,
      "loss": 1.8797,
      "step": 90
    },
    {
      "epoch": 0.1771479185119575,
      "grad_norm": 2.4932808876037598,
      "learning_rate": 0.00018873520750565718,
      "loss": 1.897,
      "step": 100
    },
    {
      "epoch": 0.1771479185119575,
      "eval_loss": 1.960958480834961,
      "eval_runtime": 16.7821,
      "eval_samples_per_second": 56.667,
      "eval_steps_per_second": 14.182,
      "step": 100
    },
    {
      "epoch": 0.19486271036315322,
      "grad_norm": 2.1805710792541504,
      "learning_rate": 0.0001861554081393806,
      "loss": 2.0712,
      "step": 110
    },
    {
      "epoch": 0.21257750221434898,
      "grad_norm": 2.5120718479156494,
      "learning_rate": 0.0001833313919082515,
      "loss": 1.9858,
      "step": 120
    },
    {
      "epoch": 0.23029229406554472,
      "grad_norm": 2.521531343460083,
      "learning_rate": 0.00018027116379309638,
      "loss": 1.8546,
      "step": 130
    },
    {
      "epoch": 0.24800708591674048,
      "grad_norm": 2.148980140686035,
      "learning_rate": 0.00017698339834299061,
      "loss": 1.8414,
      "step": 140
    },
    {
      "epoch": 0.2657218777679362,
      "grad_norm": 2.597273111343384,
      "learning_rate": 0.00017347741508630672,
      "loss": 1.8544,
      "step": 150
    },
    {
      "epoch": 0.283436669619132,
      "grad_norm": 2.2320265769958496,
      "learning_rate": 0.0001697631521134985,
      "loss": 1.9321,
      "step": 160
    },
    {
      "epoch": 0.30115146147032773,
      "grad_norm": 2.263096570968628,
      "learning_rate": 0.00016585113790650388,
      "loss": 1.9933,
      "step": 170
    },
    {
      "epoch": 0.31886625332152346,
      "grad_norm": 3.2061798572540283,
      "learning_rate": 0.0001617524614946192,
      "loss": 1.9608,
      "step": 180
    },
    {
      "epoch": 0.3365810451727192,
      "grad_norm": 2.643886089324951,
      "learning_rate": 0.0001574787410214407,
      "loss": 1.8959,
      "step": 190
    },
    {
      "epoch": 0.354295837023915,
      "grad_norm": 2.0563578605651855,
      "learning_rate": 0.00015304209081197425,
      "loss": 1.8635,
      "step": 200
    },
    {
      "epoch": 0.354295837023915,
      "eval_loss": 1.9041333198547363,
      "eval_runtime": 16.8326,
      "eval_samples_per_second": 56.498,
      "eval_steps_per_second": 14.139,
      "step": 200
    },
    {
      "epoch": 0.3720106288751107,
      "grad_norm": 2.665921926498413,
      "learning_rate": 0.00014845508703326504,
      "loss": 1.9161,
      "step": 210
    },
    {
      "epoch": 0.38972542072630645,
      "grad_norm": 2.691920518875122,
      "learning_rate": 0.00014373073204588556,
      "loss": 1.9337,
      "step": 220
    },
    {
      "epoch": 0.40744021257750224,
      "grad_norm": 2.107774257659912,
      "learning_rate": 0.00013888241754733208,
      "loss": 1.8728,
      "step": 230
    },
    {
      "epoch": 0.42515500442869797,
      "grad_norm": 2.2913401126861572,
      "learning_rate": 0.00013392388661180303,
      "loss": 1.9039,
      "step": 240
    },
    {
      "epoch": 0.4428697962798937,
      "grad_norm": 2.163093328475952,
      "learning_rate": 0.0001288691947339621,
      "loss": 1.7768,
      "step": 250
    },
    {
      "epoch": 0.46058458813108943,
      "grad_norm": 2.8082563877105713,
      "learning_rate": 0.0001237326699871115,
      "loss": 1.932,
      "step": 260
    },
    {
      "epoch": 0.4782993799822852,
      "grad_norm": 2.1630780696868896,
      "learning_rate": 0.00011852887240871145,
      "loss": 1.8789,
      "step": 270
    },
    {
      "epoch": 0.49601417183348095,
      "grad_norm": 2.2900702953338623,
      "learning_rate": 0.00011327255272837221,
      "loss": 1.8839,
      "step": 280
    },
    {
      "epoch": 0.5137289636846767,
      "grad_norm": 2.1130764484405518,
      "learning_rate": 0.00010797861055530831,
      "loss": 1.8992,
      "step": 290
    },
    {
      "epoch": 0.5314437555358724,
      "grad_norm": 2.1182191371917725,
      "learning_rate": 0.00010266205214377748,
      "loss": 1.8728,
      "step": 300
    },
    {
      "epoch": 0.5314437555358724,
      "eval_loss": 1.8754034042358398,
      "eval_runtime": 16.7499,
      "eval_samples_per_second": 56.776,
      "eval_steps_per_second": 14.209,
      "step": 300
    },
    {
      "epoch": 0.5491585473870682,
      "grad_norm": 2.364851951599121,
      "learning_rate": 9.733794785622253e-05,
      "loss": 1.9063,
      "step": 310
    },
    {
      "epoch": 0.566873339238264,
      "grad_norm": 2.248103380203247,
      "learning_rate": 9.202138944469168e-05,
      "loss": 1.8951,
      "step": 320
    },
    {
      "epoch": 0.5845881310894597,
      "grad_norm": 2.0723376274108887,
      "learning_rate": 8.672744727162781e-05,
      "loss": 1.8764,
      "step": 330
    },
    {
      "epoch": 0.6023029229406555,
      "grad_norm": 2.1202616691589355,
      "learning_rate": 8.147112759128859e-05,
      "loss": 1.8705,
      "step": 340
    },
    {
      "epoch": 0.6200177147918512,
      "grad_norm": 2.483820915222168,
      "learning_rate": 7.626733001288851e-05,
      "loss": 1.8853,
      "step": 350
    },
    {
      "epoch": 0.6377325066430469,
      "grad_norm": 2.218118906021118,
      "learning_rate": 7.113080526603792e-05,
      "loss": 1.8008,
      "step": 360
    },
    {
      "epoch": 0.6554472984942427,
      "grad_norm": 2.155637502670288,
      "learning_rate": 6.607611338819697e-05,
      "loss": 1.896,
      "step": 370
    },
    {
      "epoch": 0.6731620903454384,
      "grad_norm": 2.509552001953125,
      "learning_rate": 6.111758245266794e-05,
      "loss": 1.828,
      "step": 380
    },
    {
      "epoch": 0.6908768821966342,
      "grad_norm": 1.92943274974823,
      "learning_rate": 5.626926795411447e-05,
      "loss": 1.8035,
      "step": 390
    },
    {
      "epoch": 0.70859167404783,
      "grad_norm": 2.5901525020599365,
      "learning_rate": 5.1544912966734994e-05,
      "loss": 1.8291,
      "step": 400
    },
    {
      "epoch": 0.70859167404783,
      "eval_loss": 1.8369861841201782,
      "eval_runtime": 16.8518,
      "eval_samples_per_second": 56.433,
      "eval_steps_per_second": 14.123,
      "step": 400
    },
    {
      "epoch": 0.7263064658990257,
      "grad_norm": 2.4062066078186035,
      "learning_rate": 4.695790918802576e-05,
      "loss": 1.7516,
      "step": 410
    },
    {
      "epoch": 0.7440212577502214,
      "grad_norm": 2.545196294784546,
      "learning_rate": 4.252125897855932e-05,
      "loss": 1.8523,
      "step": 420
    },
    {
      "epoch": 0.7617360496014172,
      "grad_norm": 2.172696352005005,
      "learning_rate": 3.824753850538082e-05,
      "loss": 1.8045,
      "step": 430
    },
    {
      "epoch": 0.7794508414526129,
      "grad_norm": 2.218444347381592,
      "learning_rate": 3.414886209349615e-05,
      "loss": 1.7085,
      "step": 440
    },
    {
      "epoch": 0.7971656333038086,
      "grad_norm": 1.9435523748397827,
      "learning_rate": 3.0236847886501542e-05,
      "loss": 1.776,
      "step": 450
    },
    {
      "epoch": 0.8148804251550045,
      "grad_norm": 1.9952267408370972,
      "learning_rate": 2.6522584913693294e-05,
      "loss": 1.7882,
      "step": 460
    },
    {
      "epoch": 0.8325952170062002,
      "grad_norm": 2.478018283843994,
      "learning_rate": 2.301660165700936e-05,
      "loss": 1.867,
      "step": 470
    },
    {
      "epoch": 0.8503100088573959,
      "grad_norm": 2.3368334770202637,
      "learning_rate": 1.9728836206903656e-05,
      "loss": 1.6999,
      "step": 480
    },
    {
      "epoch": 0.8680248007085917,
      "grad_norm": 2.051180362701416,
      "learning_rate": 1.6668608091748495e-05,
      "loss": 1.8281,
      "step": 490
    },
    {
      "epoch": 0.8857395925597874,
      "grad_norm": 2.087390422821045,
      "learning_rate": 1.3844591860619383e-05,
      "loss": 1.7554,
      "step": 500
    },
    {
      "epoch": 0.8857395925597874,
      "eval_loss": 1.8198388814926147,
      "eval_runtime": 16.7054,
      "eval_samples_per_second": 56.928,
      "eval_steps_per_second": 14.247,
      "step": 500
    },
    {
      "epoch": 0.9034543844109831,
      "grad_norm": 2.305307388305664,
      "learning_rate": 1.1264792494342857e-05,
      "loss": 1.8523,
      "step": 510
    },
    {
      "epoch": 0.9211691762621789,
      "grad_norm": 3.0362179279327393,
      "learning_rate": 8.936522714508678e-06,
      "loss": 1.8562,
      "step": 520
    },
    {
      "epoch": 0.9388839681133747,
      "grad_norm": 2.4378557205200195,
      "learning_rate": 6.866382254766157e-06,
      "loss": 1.8373,
      "step": 530
    },
    {
      "epoch": 0.9565987599645704,
      "grad_norm": 3.080037832260132,
      "learning_rate": 5.060239153161872e-06,
      "loss": 1.7831,
      "step": 540
    },
    {
      "epoch": 0.9743135518157662,
      "grad_norm": 2.2773683071136475,
      "learning_rate": 3.5232131185484076e-06,
      "loss": 1.7235,
      "step": 550
    },
    {
      "epoch": 0.9920283436669619,
      "grad_norm": 1.843621850013733,
      "learning_rate": 2.259661018213333e-06,
      "loss": 1.7343,
      "step": 560
    },
    {
      "epoch": 1.0101860053144376,
      "grad_norm": 2.412452220916748,
      "learning_rate": 1.2731645278655445e-06,
      "loss": 1.7645,
      "step": 570
    },
    {
      "epoch": 1.0279007971656333,
      "grad_norm": 1.848340392112732,
      "learning_rate": 5.665199789862907e-07,
      "loss": 1.5955,
      "step": 580
    },
    {
      "epoch": 1.045615589016829,
      "grad_norm": 1.5862144231796265,
      "learning_rate": 1.4173043232380557e-07,
      "loss": 1.4961,
      "step": 590
    },
    {
      "epoch": 1.0633303808680248,
      "grad_norm": 1.902883768081665,
      "learning_rate": 0.0,
      "loss": 1.517,
      "step": 600
    },
    {
      "epoch": 1.0633303808680248,
      "eval_loss": 1.8240644931793213,
      "eval_runtime": 16.7359,
      "eval_samples_per_second": 56.824,
      "eval_steps_per_second": 14.221,
      "step": 600
    }
  ],
  "logging_steps": 10,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.42951368966144e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}