{
  "best_metric": 10.364259719848633,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.1310615989515072,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002621231979030144,
      "grad_norm": 0.0983472689986229,
      "learning_rate": 5e-05,
      "loss": 10.3797,
      "step": 1
    },
    {
      "epoch": 0.002621231979030144,
      "eval_loss": 10.380081176757812,
      "eval_runtime": 8.9595,
      "eval_samples_per_second": 286.959,
      "eval_steps_per_second": 143.535,
      "step": 1
    },
    {
      "epoch": 0.005242463958060288,
      "grad_norm": 0.09700549393892288,
      "learning_rate": 0.0001,
      "loss": 10.3796,
      "step": 2
    },
    {
      "epoch": 0.007863695937090432,
      "grad_norm": 0.09336814284324646,
      "learning_rate": 9.989294616193017e-05,
      "loss": 10.3799,
      "step": 3
    },
    {
      "epoch": 0.010484927916120577,
      "grad_norm": 0.09867435693740845,
      "learning_rate": 9.957224306869053e-05,
      "loss": 10.3801,
      "step": 4
    },
    {
      "epoch": 0.01310615989515072,
      "grad_norm": 0.09715370833873749,
      "learning_rate": 9.903926402016153e-05,
      "loss": 10.3797,
      "step": 5
    },
    {
      "epoch": 0.015727391874180863,
      "grad_norm": 0.10556021332740784,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.3784,
      "step": 6
    },
    {
      "epoch": 0.01834862385321101,
      "grad_norm": 0.10574877262115479,
      "learning_rate": 9.73465064747553e-05,
      "loss": 10.3773,
      "step": 7
    },
    {
      "epoch": 0.020969855832241154,
      "grad_norm": 0.10671475529670715,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3762,
      "step": 8
    },
    {
      "epoch": 0.023591087811271297,
      "grad_norm": 0.10671234875917435,
      "learning_rate": 9.484363707663442e-05,
      "loss": 10.3758,
      "step": 9
    },
    {
      "epoch": 0.02621231979030144,
      "grad_norm": 0.11303173005580902,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3748,
      "step": 10
    },
    {
      "epoch": 0.028833551769331587,
      "grad_norm": 0.10760895162820816,
      "learning_rate": 9.157348061512727e-05,
      "loss": 10.3747,
      "step": 11
    },
    {
      "epoch": 0.03145478374836173,
      "grad_norm": 0.10080239921808243,
      "learning_rate": 8.966766701456177e-05,
      "loss": 10.3732,
      "step": 12
    },
    {
      "epoch": 0.03407601572739188,
      "grad_norm": 0.1232990175485611,
      "learning_rate": 8.759199037394887e-05,
      "loss": 10.3735,
      "step": 13
    },
    {
      "epoch": 0.03669724770642202,
      "grad_norm": 0.13050110638141632,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3727,
      "step": 14
    },
    {
      "epoch": 0.039318479685452164,
      "grad_norm": 0.12770453095436096,
      "learning_rate": 8.296729075500344e-05,
      "loss": 10.3726,
      "step": 15
    },
    {
      "epoch": 0.04193971166448231,
      "grad_norm": 0.12612299621105194,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.3723,
      "step": 16
    },
    {
      "epoch": 0.04456094364351245,
      "grad_norm": 0.12636294960975647,
      "learning_rate": 7.777851165098012e-05,
      "loss": 10.3726,
      "step": 17
    },
    {
      "epoch": 0.047182175622542594,
      "grad_norm": 0.1317187249660492,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3704,
      "step": 18
    },
    {
      "epoch": 0.04980340760157274,
      "grad_norm": 0.13668107986450195,
      "learning_rate": 7.211443451095007e-05,
      "loss": 10.3773,
      "step": 19
    },
    {
      "epoch": 0.05242463958060288,
      "grad_norm": 0.14118903875350952,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3728,
      "step": 20
    },
    {
      "epoch": 0.05504587155963303,
      "grad_norm": 0.16648933291435242,
      "learning_rate": 6.607197326515808e-05,
      "loss": 10.3702,
      "step": 21
    },
    {
      "epoch": 0.057667103538663174,
      "grad_norm": 0.1857651323080063,
      "learning_rate": 6.294095225512603e-05,
      "loss": 10.368,
      "step": 22
    },
    {
      "epoch": 0.06028833551769332,
      "grad_norm": 0.21679675579071045,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 10.3668,
      "step": 23
    },
    {
      "epoch": 0.06290956749672345,
      "grad_norm": 0.26074954867362976,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 10.3705,
      "step": 24
    },
    {
      "epoch": 0.0655307994757536,
      "grad_norm": 0.32028478384017944,
      "learning_rate": 5.327015646150716e-05,
      "loss": 10.3763,
      "step": 25
    },
    {
      "epoch": 0.0655307994757536,
      "eval_loss": 10.368563652038574,
      "eval_runtime": 8.8771,
      "eval_samples_per_second": 289.621,
      "eval_steps_per_second": 144.867,
      "step": 25
    },
    {
      "epoch": 0.06815203145478375,
      "grad_norm": 0.14264819025993347,
      "learning_rate": 5e-05,
      "loss": 10.3697,
      "step": 26
    },
    {
      "epoch": 0.07077326343381389,
      "grad_norm": 0.1584285944700241,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 10.369,
      "step": 27
    },
    {
      "epoch": 0.07339449541284404,
      "grad_norm": 0.15768349170684814,
      "learning_rate": 4.347369038899744e-05,
      "loss": 10.3671,
      "step": 28
    },
    {
      "epoch": 0.07601572739187418,
      "grad_norm": 0.16855980455875397,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 10.3688,
      "step": 29
    },
    {
      "epoch": 0.07863695937090433,
      "grad_norm": 0.163541778922081,
      "learning_rate": 3.705904774487396e-05,
      "loss": 10.3682,
      "step": 30
    },
    {
      "epoch": 0.08125819134993446,
      "grad_norm": 0.1631956547498703,
      "learning_rate": 3.392802673484193e-05,
      "loss": 10.3675,
      "step": 31
    },
    {
      "epoch": 0.08387942332896461,
      "grad_norm": 0.17039114236831665,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3654,
      "step": 32
    },
    {
      "epoch": 0.08650065530799476,
      "grad_norm": 0.17132709920406342,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 10.3645,
      "step": 33
    },
    {
      "epoch": 0.0891218872870249,
      "grad_norm": 0.17489856481552124,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.3652,
      "step": 34
    },
    {
      "epoch": 0.09174311926605505,
      "grad_norm": 0.16200144588947296,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 10.3653,
      "step": 35
    },
    {
      "epoch": 0.09436435124508519,
      "grad_norm": 0.1544119119644165,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 10.3636,
      "step": 36
    },
    {
      "epoch": 0.09698558322411534,
      "grad_norm": 0.1636291891336441,
      "learning_rate": 1.703270924499656e-05,
      "loss": 10.3637,
      "step": 37
    },
    {
      "epoch": 0.09960681520314547,
      "grad_norm": 0.16712762415409088,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3642,
      "step": 38
    },
    {
      "epoch": 0.10222804718217562,
      "grad_norm": 0.17674000561237335,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 10.3625,
      "step": 39
    },
    {
      "epoch": 0.10484927916120576,
      "grad_norm": 0.16372479498386383,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 10.3628,
      "step": 40
    },
    {
      "epoch": 0.10747051114023591,
      "grad_norm": 0.1757289469242096,
      "learning_rate": 8.426519384872733e-06,
      "loss": 10.3636,
      "step": 41
    },
    {
      "epoch": 0.11009174311926606,
      "grad_norm": 0.18390248715877533,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3635,
      "step": 42
    },
    {
      "epoch": 0.1127129750982962,
      "grad_norm": 0.18096409738063812,
      "learning_rate": 5.156362923365588e-06,
      "loss": 10.3631,
      "step": 43
    },
    {
      "epoch": 0.11533420707732635,
      "grad_norm": 0.17069672048091888,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3631,
      "step": 44
    },
    {
      "epoch": 0.11795543905635648,
      "grad_norm": 0.18754449486732483,
      "learning_rate": 2.653493525244721e-06,
      "loss": 10.3618,
      "step": 45
    },
    {
      "epoch": 0.12057667103538663,
      "grad_norm": 0.19172361493110657,
      "learning_rate": 1.70370868554659e-06,
      "loss": 10.3629,
      "step": 46
    },
    {
      "epoch": 0.12319790301441677,
      "grad_norm": 0.2101452797651291,
      "learning_rate": 9.607359798384785e-07,
      "loss": 10.3615,
      "step": 47
    },
    {
      "epoch": 0.1258191349934469,
      "grad_norm": 0.25174856185913086,
      "learning_rate": 4.277569313094809e-07,
      "loss": 10.3608,
      "step": 48
    },
    {
      "epoch": 0.12844036697247707,
      "grad_norm": 0.2769647538661957,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 10.3619,
      "step": 49
    },
    {
      "epoch": 0.1310615989515072,
      "grad_norm": 0.35829517245292664,
      "learning_rate": 0.0,
      "loss": 10.3717,
      "step": 50
    },
    {
      "epoch": 0.1310615989515072,
      "eval_loss": 10.364259719848633,
      "eval_runtime": 8.8336,
      "eval_samples_per_second": 291.048,
      "eval_steps_per_second": 145.581,
      "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": 84569751552000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}