{
  "best_metric": 0.0017845286056399345,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.05950167348456675,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011900334696913352,
      "grad_norm": 0.4137071967124939,
      "learning_rate": 5e-05,
      "loss": 0.4674,
      "step": 1
    },
    {
      "epoch": 0.0011900334696913352,
      "eval_loss": 2.264573335647583,
      "eval_runtime": 302.3347,
      "eval_samples_per_second": 18.724,
      "eval_steps_per_second": 2.342,
      "step": 1
    },
    {
      "epoch": 0.0023800669393826703,
      "grad_norm": 0.9368460178375244,
      "learning_rate": 0.0001,
      "loss": 0.9492,
      "step": 2
    },
    {
      "epoch": 0.0035701004090740052,
      "grad_norm": 1.6849383115768433,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.4257,
      "step": 3
    },
    {
      "epoch": 0.004760133878765341,
      "grad_norm": 2.721559524536133,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.4889,
      "step": 4
    },
    {
      "epoch": 0.005950167348456675,
      "grad_norm": 1.987635612487793,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.0404,
      "step": 5
    },
    {
      "epoch": 0.0071402008181480105,
      "grad_norm": 2.352818250656128,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7934,
      "step": 6
    },
    {
      "epoch": 0.008330234287839345,
      "grad_norm": 1.760326623916626,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.5765,
      "step": 7
    },
    {
      "epoch": 0.009520267757530681,
      "grad_norm": 1.826923131942749,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.3736,
      "step": 8
    },
    {
      "epoch": 0.010710301227222016,
      "grad_norm": 2.4587562084198,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.2031,
      "step": 9
    },
    {
      "epoch": 0.01190033469691335,
      "grad_norm": 0.708000898361206,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0524,
      "step": 10
    },
    {
      "epoch": 0.013090368166604686,
      "grad_norm": 0.25198036432266235,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0243,
      "step": 11
    },
    {
      "epoch": 0.014280401636296021,
      "grad_norm": 0.2573776841163635,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.024,
      "step": 12
    },
    {
      "epoch": 0.015470435105987355,
      "grad_norm": 0.1748504489660263,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0396,
      "step": 13
    },
    {
      "epoch": 0.01666046857567869,
      "grad_norm": 0.17864415049552917,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0103,
      "step": 14
    },
    {
      "epoch": 0.017850502045370024,
      "grad_norm": 0.16126886010169983,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0058,
      "step": 15
    },
    {
      "epoch": 0.019040535515061362,
      "grad_norm": 0.14580091834068298,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0044,
      "step": 16
    },
    {
      "epoch": 0.020230568984752697,
      "grad_norm": 0.19678618013858795,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0107,
      "step": 17
    },
    {
      "epoch": 0.02142060245444403,
      "grad_norm": 0.07907175272703171,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0043,
      "step": 18
    },
    {
      "epoch": 0.022610635924135366,
      "grad_norm": 0.025601878762245178,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0011,
      "step": 19
    },
    {
      "epoch": 0.0238006693938267,
      "grad_norm": 0.029820172116160393,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0006,
      "step": 20
    },
    {
      "epoch": 0.024990702863518035,
      "grad_norm": 0.03744960203766823,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0011,
      "step": 21
    },
    {
      "epoch": 0.026180736333209373,
      "grad_norm": 0.012208701111376286,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0005,
      "step": 22
    },
    {
      "epoch": 0.027370769802900707,
      "grad_norm": 0.02207552269101143,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0012,
      "step": 23
    },
    {
      "epoch": 0.028560803272592042,
      "grad_norm": 0.016107767820358276,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0007,
      "step": 24
    },
    {
      "epoch": 0.029750836742283376,
      "grad_norm": 0.13807596266269684,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.008,
      "step": 25
    },
    {
      "epoch": 0.029750836742283376,
      "eval_loss": 0.0024142141919583082,
      "eval_runtime": 301.6014,
      "eval_samples_per_second": 18.77,
      "eval_steps_per_second": 2.347,
      "step": 25
    },
    {
      "epoch": 0.03094087021197471,
      "grad_norm": 0.11670713126659393,
      "learning_rate": 5e-05,
      "loss": 0.0092,
      "step": 26
    },
    {
      "epoch": 0.032130903681666045,
      "grad_norm": 0.025358397513628006,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0006,
      "step": 27
    },
    {
      "epoch": 0.03332093715135738,
      "grad_norm": 0.019817519932985306,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0024,
      "step": 28
    },
    {
      "epoch": 0.034510970621048714,
      "grad_norm": 0.10703627020120621,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0031,
      "step": 29
    },
    {
      "epoch": 0.03570100409074005,
      "grad_norm": 0.002817679662257433,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0001,
      "step": 30
    },
    {
      "epoch": 0.03689103756043139,
      "grad_norm": 0.01130523532629013,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0002,
      "step": 31
    },
    {
      "epoch": 0.038081071030122725,
      "grad_norm": 0.020346427336335182,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0003,
      "step": 32
    },
    {
      "epoch": 0.03927110449981406,
      "grad_norm": 0.001904260367155075,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0001,
      "step": 33
    },
    {
      "epoch": 0.040461137969505394,
      "grad_norm": 0.007746758870780468,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0002,
      "step": 34
    },
    {
      "epoch": 0.04165117143919673,
      "grad_norm": 0.004477960988879204,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0001,
      "step": 35
    },
    {
      "epoch": 0.04284120490888806,
      "grad_norm": 0.06279127299785614,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0049,
      "step": 36
    },
    {
      "epoch": 0.0440312383785794,
      "grad_norm": 0.007732586935162544,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0002,
      "step": 37
    },
    {
      "epoch": 0.04522127184827073,
      "grad_norm": 0.09072456508874893,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0066,
      "step": 38
    },
    {
      "epoch": 0.046411305317962066,
      "grad_norm": 0.04076767712831497,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0017,
      "step": 39
    },
    {
      "epoch": 0.0476013387876534,
      "grad_norm": 0.004594309721142054,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0001,
      "step": 40
    },
    {
      "epoch": 0.048791372257344735,
      "grad_norm": 0.022521473467350006,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0023,
      "step": 41
    },
    {
      "epoch": 0.04998140572703607,
      "grad_norm": 0.03882487118244171,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0002,
      "step": 42
    },
    {
      "epoch": 0.05117143919672741,
      "grad_norm": 0.023141443729400635,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0003,
      "step": 43
    },
    {
      "epoch": 0.052361472666418746,
      "grad_norm": 0.034502483904361725,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0056,
      "step": 44
    },
    {
      "epoch": 0.05355150613611008,
      "grad_norm": 0.0009720915113575757,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.054741539605801415,
      "grad_norm": 0.002274035941809416,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.05593157307549275,
      "grad_norm": 0.05807733163237572,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0067,
      "step": 47
    },
    {
      "epoch": 0.057121606545184084,
      "grad_norm": 0.009669804945588112,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0003,
      "step": 48
    },
    {
      "epoch": 0.05831164001487542,
      "grad_norm": 0.0655217170715332,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0009,
      "step": 49
    },
    {
      "epoch": 0.05950167348456675,
      "grad_norm": 0.08589838445186615,
      "learning_rate": 0.0,
      "loss": 0.0107,
      "step": 50
    },
    {
      "epoch": 0.05950167348456675,
      "eval_loss": 0.0017845286056399345,
      "eval_runtime": 301.5784,
      "eval_samples_per_second": 18.771,
      "eval_steps_per_second": 2.348,
      "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": 1.1111570021023744e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}