{
  "best_metric": 10.360050201416016,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.016361256544502618,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003272251308900524,
      "grad_norm": 0.03769031912088394,
      "learning_rate": 5e-05,
      "loss": 10.3683,
      "step": 1
    },
    {
      "epoch": 0.0003272251308900524,
      "eval_loss": 10.367464065551758,
      "eval_runtime": 19.643,
      "eval_samples_per_second": 1048.108,
      "eval_steps_per_second": 131.039,
      "step": 1
    },
    {
      "epoch": 0.0006544502617801048,
      "grad_norm": 0.041657455265522,
      "learning_rate": 0.0001,
      "loss": 10.3716,
      "step": 2
    },
    {
      "epoch": 0.000981675392670157,
      "grad_norm": 0.03957965597510338,
      "learning_rate": 9.989294616193017e-05,
      "loss": 10.3662,
      "step": 3
    },
    {
      "epoch": 0.0013089005235602095,
      "grad_norm": 0.04342247545719147,
      "learning_rate": 9.957224306869053e-05,
      "loss": 10.3679,
      "step": 4
    },
    {
      "epoch": 0.0016361256544502618,
      "grad_norm": 0.04622041806578636,
      "learning_rate": 9.903926402016153e-05,
      "loss": 10.3719,
      "step": 5
    },
    {
      "epoch": 0.001963350785340314,
      "grad_norm": 0.0497346930205822,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.3676,
      "step": 6
    },
    {
      "epoch": 0.0022905759162303663,
      "grad_norm": 0.04874146357178688,
      "learning_rate": 9.73465064747553e-05,
      "loss": 10.3664,
      "step": 7
    },
    {
      "epoch": 0.002617801047120419,
      "grad_norm": 0.05379088968038559,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3682,
      "step": 8
    },
    {
      "epoch": 0.0029450261780104713,
      "grad_norm": 0.05579537898302078,
      "learning_rate": 9.484363707663442e-05,
      "loss": 10.3698,
      "step": 9
    },
    {
      "epoch": 0.0032722513089005235,
      "grad_norm": 0.05927934870123863,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3648,
      "step": 10
    },
    {
      "epoch": 0.003599476439790576,
      "grad_norm": 0.0640878900885582,
      "learning_rate": 9.157348061512727e-05,
      "loss": 10.364,
      "step": 11
    },
    {
      "epoch": 0.003926701570680628,
      "grad_norm": 0.08353476226329803,
      "learning_rate": 8.966766701456177e-05,
      "loss": 10.3593,
      "step": 12
    },
    {
      "epoch": 0.004253926701570681,
      "grad_norm": 0.05146829038858414,
      "learning_rate": 8.759199037394887e-05,
      "loss": 10.3637,
      "step": 13
    },
    {
      "epoch": 0.004581151832460733,
      "grad_norm": 0.04255501553416252,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3699,
      "step": 14
    },
    {
      "epoch": 0.004908376963350785,
      "grad_norm": 0.045842889696359634,
      "learning_rate": 8.296729075500344e-05,
      "loss": 10.3667,
      "step": 15
    },
    {
      "epoch": 0.005235602094240838,
      "grad_norm": 0.043058060109615326,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.3656,
      "step": 16
    },
    {
      "epoch": 0.00556282722513089,
      "grad_norm": 0.04620865359902382,
      "learning_rate": 7.777851165098012e-05,
      "loss": 10.368,
      "step": 17
    },
    {
      "epoch": 0.0058900523560209425,
      "grad_norm": 0.048817455768585205,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3667,
      "step": 18
    },
    {
      "epoch": 0.006217277486910994,
      "grad_norm": 0.055263690650463104,
      "learning_rate": 7.211443451095007e-05,
      "loss": 10.3637,
      "step": 19
    },
    {
      "epoch": 0.006544502617801047,
      "grad_norm": 0.05442475900053978,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3608,
      "step": 20
    },
    {
      "epoch": 0.0068717277486911,
      "grad_norm": 0.06926178932189941,
      "learning_rate": 6.607197326515808e-05,
      "loss": 10.3645,
      "step": 21
    },
    {
      "epoch": 0.007198952879581152,
      "grad_norm": 0.07124587893486023,
      "learning_rate": 6.294095225512603e-05,
      "loss": 10.358,
      "step": 22
    },
    {
      "epoch": 0.007526178010471204,
      "grad_norm": 0.08000573515892029,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 10.3588,
      "step": 23
    },
    {
      "epoch": 0.007853403141361256,
      "grad_norm": 0.09068429470062256,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 10.3565,
      "step": 24
    },
    {
      "epoch": 0.008180628272251309,
      "grad_norm": 0.13074612617492676,
      "learning_rate": 5.327015646150716e-05,
      "loss": 10.3503,
      "step": 25
    },
    {
      "epoch": 0.008180628272251309,
      "eval_loss": 10.362049102783203,
      "eval_runtime": 19.6449,
      "eval_samples_per_second": 1048.008,
      "eval_steps_per_second": 131.026,
      "step": 25
    },
    {
      "epoch": 0.008507853403141362,
      "grad_norm": 0.0465715155005455,
      "learning_rate": 5e-05,
      "loss": 10.3673,
      "step": 26
    },
    {
      "epoch": 0.008835078534031414,
      "grad_norm": 0.0531485453248024,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 10.3679,
      "step": 27
    },
    {
      "epoch": 0.009162303664921465,
      "grad_norm": 0.04927300289273262,
      "learning_rate": 4.347369038899744e-05,
      "loss": 10.367,
      "step": 28
    },
    {
      "epoch": 0.009489528795811518,
      "grad_norm": 0.053813155740499496,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 10.3641,
      "step": 29
    },
    {
      "epoch": 0.00981675392670157,
      "grad_norm": 0.05822814628481865,
      "learning_rate": 3.705904774487396e-05,
      "loss": 10.3658,
      "step": 30
    },
    {
      "epoch": 0.010143979057591623,
      "grad_norm": 0.07245771586894989,
      "learning_rate": 3.392802673484193e-05,
      "loss": 10.3648,
      "step": 31
    },
    {
      "epoch": 0.010471204188481676,
      "grad_norm": 0.06997586041688919,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3608,
      "step": 32
    },
    {
      "epoch": 0.010798429319371727,
      "grad_norm": 0.0739465206861496,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 10.3633,
      "step": 33
    },
    {
      "epoch": 0.01112565445026178,
      "grad_norm": 0.08442109823226929,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3608,
      "step": 34
    },
    {
      "epoch": 0.011452879581151832,
      "grad_norm": 0.08695055544376373,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 10.3621,
      "step": 35
    },
    {
      "epoch": 0.011780104712041885,
      "grad_norm": 0.09437209367752075,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 10.3534,
      "step": 36
    },
    {
      "epoch": 0.012107329842931938,
      "grad_norm": 0.10353465378284454,
      "learning_rate": 1.703270924499656e-05,
      "loss": 10.3544,
      "step": 37
    },
    {
      "epoch": 0.012434554973821989,
      "grad_norm": 0.06279531121253967,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3637,
      "step": 38
    },
    {
      "epoch": 0.012761780104712041,
      "grad_norm": 0.060497626662254333,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 10.3668,
      "step": 39
    },
    {
      "epoch": 0.013089005235602094,
      "grad_norm": 0.05795399472117424,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 10.3645,
      "step": 40
    },
    {
      "epoch": 0.013416230366492147,
      "grad_norm": 0.05940159037709236,
      "learning_rate": 8.426519384872733e-06,
      "loss": 10.3635,
      "step": 41
    },
    {
      "epoch": 0.0137434554973822,
      "grad_norm": 0.061443179845809937,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3669,
      "step": 42
    },
    {
      "epoch": 0.01407068062827225,
      "grad_norm": 0.0652313157916069,
      "learning_rate": 5.156362923365588e-06,
      "loss": 10.3625,
      "step": 43
    },
    {
      "epoch": 0.014397905759162303,
      "grad_norm": 0.06856326758861542,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3601,
      "step": 44
    },
    {
      "epoch": 0.014725130890052356,
      "grad_norm": 0.06705807894468307,
      "learning_rate": 2.653493525244721e-06,
      "loss": 10.3607,
      "step": 45
    },
    {
      "epoch": 0.015052356020942409,
      "grad_norm": 0.07734378427267075,
      "learning_rate": 1.70370868554659e-06,
      "loss": 10.3589,
      "step": 46
    },
    {
      "epoch": 0.015379581151832461,
      "grad_norm": 0.0883852019906044,
      "learning_rate": 9.607359798384785e-07,
      "loss": 10.3599,
      "step": 47
    },
    {
      "epoch": 0.015706806282722512,
      "grad_norm": 0.08160966634750366,
      "learning_rate": 4.277569313094809e-07,
      "loss": 10.3601,
      "step": 48
    },
    {
      "epoch": 0.016034031413612565,
      "grad_norm": 0.09474560618400574,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 10.3526,
      "step": 49
    },
    {
      "epoch": 0.016361256544502618,
      "grad_norm": 0.1311928927898407,
      "learning_rate": 0.0,
      "loss": 10.3484,
      "step": 50
    },
    {
      "epoch": 0.016361256544502618,
      "eval_loss": 10.360050201416016,
      "eval_runtime": 19.6493,
      "eval_samples_per_second": 1047.772,
      "eval_steps_per_second": 130.997,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 42768059596800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}