{
  "best_metric": 0.2678118944168091,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.4784688995215311,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009569377990430622,
      "grad_norm": 2.8137314319610596,
      "learning_rate": 5e-05,
      "loss": 1.2054,
      "step": 1
    },
    {
      "epoch": 0.009569377990430622,
      "eval_loss": 1.7987078428268433,
      "eval_runtime": 5.5361,
      "eval_samples_per_second": 127.166,
      "eval_steps_per_second": 15.896,
      "step": 1
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 2.8290939331054688,
      "learning_rate": 0.0001,
      "loss": 1.3459,
      "step": 2
    },
    {
      "epoch": 0.028708133971291867,
      "grad_norm": 2.1697356700897217,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.2941,
      "step": 3
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 1.7272006273269653,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.1967,
      "step": 4
    },
    {
      "epoch": 0.04784688995215311,
      "grad_norm": 1.7534210681915283,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.1186,
      "step": 5
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 1.8180071115493774,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0057,
      "step": 6
    },
    {
      "epoch": 0.06698564593301436,
      "grad_norm": 1.7432036399841309,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.8953,
      "step": 7
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 1.5547484159469604,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.7465,
      "step": 8
    },
    {
      "epoch": 0.0861244019138756,
      "grad_norm": 1.4408551454544067,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.6385,
      "step": 9
    },
    {
      "epoch": 0.09569377990430622,
      "grad_norm": 1.8555291891098022,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6297,
      "step": 10
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.4187091588974,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.5862,
      "step": 11
    },
    {
      "epoch": 0.11483253588516747,
      "grad_norm": 1.4970670938491821,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5088,
      "step": 12
    },
    {
      "epoch": 0.12440191387559808,
      "grad_norm": 1.7118096351623535,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.4849,
      "step": 13
    },
    {
      "epoch": 0.1339712918660287,
      "grad_norm": 1.1661502122879028,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.4955,
      "step": 14
    },
    {
      "epoch": 0.14354066985645933,
      "grad_norm": 1.0327798128128052,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.4694,
      "step": 15
    },
    {
      "epoch": 0.15311004784688995,
      "grad_norm": 0.877717137336731,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.4417,
      "step": 16
    },
    {
      "epoch": 0.16267942583732056,
      "grad_norm": 0.7002546191215515,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.4206,
      "step": 17
    },
    {
      "epoch": 0.1722488038277512,
      "grad_norm": 0.7912804484367371,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4092,
      "step": 18
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.8266118168830872,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.3737,
      "step": 19
    },
    {
      "epoch": 0.19138755980861244,
      "grad_norm": 0.6468063592910767,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3844,
      "step": 20
    },
    {
      "epoch": 0.20095693779904306,
      "grad_norm": 0.752920925617218,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.3473,
      "step": 21
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.8479627370834351,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.3678,
      "step": 22
    },
    {
      "epoch": 0.22009569377990432,
      "grad_norm": 0.6467729806900024,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.359,
      "step": 23
    },
    {
      "epoch": 0.22966507177033493,
      "grad_norm": 0.846888542175293,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.3486,
      "step": 24
    },
    {
      "epoch": 0.23923444976076555,
      "grad_norm": 1.4948647022247314,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.3624,
      "step": 25
    },
    {
      "epoch": 0.23923444976076555,
      "eval_loss": 0.3310394585132599,
      "eval_runtime": 5.5159,
      "eval_samples_per_second": 127.632,
      "eval_steps_per_second": 15.954,
      "step": 25
    },
    {
      "epoch": 0.24880382775119617,
      "grad_norm": 0.550075113773346,
      "learning_rate": 5e-05,
      "loss": 0.2946,
      "step": 26
    },
    {
      "epoch": 0.2583732057416268,
      "grad_norm": 0.6220561265945435,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.3003,
      "step": 27
    },
    {
      "epoch": 0.2679425837320574,
      "grad_norm": 0.550743579864502,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.2996,
      "step": 28
    },
    {
      "epoch": 0.27751196172248804,
      "grad_norm": 0.5144545435905457,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.3006,
      "step": 29
    },
    {
      "epoch": 0.28708133971291866,
      "grad_norm": 0.5131386518478394,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.2989,
      "step": 30
    },
    {
      "epoch": 0.2966507177033493,
      "grad_norm": 0.5182365775108337,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.2806,
      "step": 31
    },
    {
      "epoch": 0.3062200956937799,
      "grad_norm": 0.5407494306564331,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.2921,
      "step": 32
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.5603722929954529,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.281,
      "step": 33
    },
    {
      "epoch": 0.3253588516746411,
      "grad_norm": 0.532714307308197,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.26,
      "step": 34
    },
    {
      "epoch": 0.3349282296650718,
      "grad_norm": 0.5404855012893677,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.2831,
      "step": 35
    },
    {
      "epoch": 0.3444976076555024,
      "grad_norm": 0.7140843272209167,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.2761,
      "step": 36
    },
    {
      "epoch": 0.35406698564593303,
      "grad_norm": 1.1513055562973022,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.272,
      "step": 37
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.7768696546554565,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2692,
      "step": 38
    },
    {
      "epoch": 0.37320574162679426,
      "grad_norm": 0.4334043860435486,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.263,
      "step": 39
    },
    {
      "epoch": 0.3827751196172249,
      "grad_norm": 0.4151334762573242,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.265,
      "step": 40
    },
    {
      "epoch": 0.3923444976076555,
      "grad_norm": 0.46699267625808716,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.2688,
      "step": 41
    },
    {
      "epoch": 0.4019138755980861,
      "grad_norm": 0.4230937063694,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2582,
      "step": 42
    },
    {
      "epoch": 0.41148325358851673,
      "grad_norm": 0.4443204402923584,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.2508,
      "step": 43
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.501763105392456,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.2547,
      "step": 44
    },
    {
      "epoch": 0.430622009569378,
      "grad_norm": 0.6074100732803345,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.2675,
      "step": 45
    },
    {
      "epoch": 0.44019138755980863,
      "grad_norm": 0.5926224589347839,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.2775,
      "step": 46
    },
    {
      "epoch": 0.44976076555023925,
      "grad_norm": 0.6422264575958252,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.2847,
      "step": 47
    },
    {
      "epoch": 0.45933014354066987,
      "grad_norm": 0.6994796395301819,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.2657,
      "step": 48
    },
    {
      "epoch": 0.4688995215311005,
      "grad_norm": 0.72403484582901,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.2674,
      "step": 49
    },
    {
      "epoch": 0.4784688995215311,
      "grad_norm": 0.8881353139877319,
      "learning_rate": 0.0,
      "loss": 0.2547,
      "step": 50
    },
    {
      "epoch": 0.4784688995215311,
      "eval_loss": 0.2678118944168091,
      "eval_runtime": 5.5157,
      "eval_samples_per_second": 127.637,
      "eval_steps_per_second": 15.955,
      "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": 7.832875685432525e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}