{
  "best_metric": 1.1211003065109253,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.45146726862302483,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009029345372460496,
      "grad_norm": 0.31618043780326843,
      "learning_rate": 5e-05,
      "loss": 1.7419,
      "step": 1
    },
    {
      "epoch": 0.009029345372460496,
      "eval_loss": 1.421186089515686,
      "eval_runtime": 20.1307,
      "eval_samples_per_second": 37.058,
      "eval_steps_per_second": 4.669,
      "step": 1
    },
    {
      "epoch": 0.01805869074492099,
      "grad_norm": 0.5828431844711304,
      "learning_rate": 0.0001,
      "loss": 1.6562,
      "step": 2
    },
    {
      "epoch": 0.02708803611738149,
      "grad_norm": 0.6117285490036011,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.6931,
      "step": 3
    },
    {
      "epoch": 0.03611738148984198,
      "grad_norm": 0.53819340467453,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.7842,
      "step": 4
    },
    {
      "epoch": 0.045146726862302484,
      "grad_norm": 0.5887128114700317,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.5996,
      "step": 5
    },
    {
      "epoch": 0.05417607223476298,
      "grad_norm": 0.3885045051574707,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.7137,
      "step": 6
    },
    {
      "epoch": 0.06320541760722348,
      "grad_norm": 0.5125159621238708,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.5119,
      "step": 7
    },
    {
      "epoch": 0.07223476297968397,
      "grad_norm": 0.507826030254364,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.3669,
      "step": 8
    },
    {
      "epoch": 0.08126410835214447,
      "grad_norm": 0.3450145423412323,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.2044,
      "step": 9
    },
    {
      "epoch": 0.09029345372460497,
      "grad_norm": 0.5278269648551941,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0264,
      "step": 10
    },
    {
      "epoch": 0.09932279909706546,
      "grad_norm": 0.5407944321632385,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.8404,
      "step": 11
    },
    {
      "epoch": 0.10835214446952596,
      "grad_norm": 0.6161919832229614,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5914,
      "step": 12
    },
    {
      "epoch": 0.11738148984198646,
      "grad_norm": 0.43572109937667847,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.4473,
      "step": 13
    },
    {
      "epoch": 0.12641083521444696,
      "grad_norm": 0.5435495972633362,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4405,
      "step": 14
    },
    {
      "epoch": 0.13544018058690746,
      "grad_norm": 0.6744799613952637,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.6233,
      "step": 15
    },
    {
      "epoch": 0.14446952595936793,
      "grad_norm": 0.5321604013442993,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.5787,
      "step": 16
    },
    {
      "epoch": 0.15349887133182843,
      "grad_norm": 0.34596696496009827,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.6304,
      "step": 17
    },
    {
      "epoch": 0.16252821670428894,
      "grad_norm": 0.3103005588054657,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.5096,
      "step": 18
    },
    {
      "epoch": 0.17155756207674944,
      "grad_norm": 0.2984153926372528,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.648,
      "step": 19
    },
    {
      "epoch": 0.18058690744920994,
      "grad_norm": 0.2474711388349533,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5307,
      "step": 20
    },
    {
      "epoch": 0.18961625282167044,
      "grad_norm": 0.24473999440670013,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.2279,
      "step": 21
    },
    {
      "epoch": 0.1986455981941309,
      "grad_norm": 0.2649778127670288,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.221,
      "step": 22
    },
    {
      "epoch": 0.2076749435665914,
      "grad_norm": 0.4170401394367218,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.1055,
      "step": 23
    },
    {
      "epoch": 0.21670428893905191,
      "grad_norm": 0.5601091980934143,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.7104,
      "step": 24
    },
    {
      "epoch": 0.22573363431151242,
      "grad_norm": 0.8927808403968811,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.5798,
      "step": 25
    },
    {
      "epoch": 0.22573363431151242,
      "eval_loss": 1.1319423913955688,
      "eval_runtime": 20.1289,
      "eval_samples_per_second": 37.061,
      "eval_steps_per_second": 4.67,
      "step": 25
    },
    {
      "epoch": 0.23476297968397292,
      "grad_norm": 0.3029966354370117,
      "learning_rate": 5e-05,
      "loss": 1.5864,
      "step": 26
    },
    {
      "epoch": 0.24379232505643342,
      "grad_norm": 0.3005797266960144,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.6568,
      "step": 27
    },
    {
      "epoch": 0.2528216704288939,
      "grad_norm": 0.24547135829925537,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.4648,
      "step": 28
    },
    {
      "epoch": 0.2618510158013544,
      "grad_norm": 0.19365021586418152,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.6744,
      "step": 29
    },
    {
      "epoch": 0.2708803611738149,
      "grad_norm": 0.19894447922706604,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.4961,
      "step": 30
    },
    {
      "epoch": 0.2799097065462754,
      "grad_norm": 0.2252543866634369,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.6705,
      "step": 31
    },
    {
      "epoch": 0.28893905191873587,
      "grad_norm": 0.25827154517173767,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.5442,
      "step": 32
    },
    {
      "epoch": 0.2979683972911964,
      "grad_norm": 0.2601383328437805,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.3812,
      "step": 33
    },
    {
      "epoch": 0.30699774266365687,
      "grad_norm": 0.2715680003166199,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.1781,
      "step": 34
    },
    {
      "epoch": 0.3160270880361174,
      "grad_norm": 0.3026103377342224,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.1607,
      "step": 35
    },
    {
      "epoch": 0.32505643340857787,
      "grad_norm": 0.42034703493118286,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.784,
      "step": 36
    },
    {
      "epoch": 0.3340857787810384,
      "grad_norm": 0.37357938289642334,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.5649,
      "step": 37
    },
    {
      "epoch": 0.3431151241534989,
      "grad_norm": 0.15997634828090668,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.6707,
      "step": 38
    },
    {
      "epoch": 0.35214446952595935,
      "grad_norm": 0.15511050820350647,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.4331,
      "step": 39
    },
    {
      "epoch": 0.3611738148984199,
      "grad_norm": 0.1680152416229248,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.6783,
      "step": 40
    },
    {
      "epoch": 0.37020316027088035,
      "grad_norm": 0.19817280769348145,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.4853,
      "step": 41
    },
    {
      "epoch": 0.3792325056433409,
      "grad_norm": 0.19002708792686462,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.5314,
      "step": 42
    },
    {
      "epoch": 0.38826185101580135,
      "grad_norm": 0.20888566970825195,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.5721,
      "step": 43
    },
    {
      "epoch": 0.3972911963882618,
      "grad_norm": 0.1991356760263443,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.5912,
      "step": 44
    },
    {
      "epoch": 0.40632054176072235,
      "grad_norm": 0.21265777945518494,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.5148,
      "step": 45
    },
    {
      "epoch": 0.4153498871331828,
      "grad_norm": 0.21502944827079773,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.2986,
      "step": 46
    },
    {
      "epoch": 0.42437923250564336,
      "grad_norm": 0.23923197388648987,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.1442,
      "step": 47
    },
    {
      "epoch": 0.43340857787810383,
      "grad_norm": 0.26049110293388367,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.1479,
      "step": 48
    },
    {
      "epoch": 0.44243792325056436,
      "grad_norm": 0.35071879625320435,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.6991,
      "step": 49
    },
    {
      "epoch": 0.45146726862302483,
      "grad_norm": 0.3658585250377655,
      "learning_rate": 0.0,
      "loss": 0.4838,
      "step": 50
    },
    {
      "epoch": 0.45146726862302483,
      "eval_loss": 1.1211003065109253,
      "eval_runtime": 20.125,
      "eval_samples_per_second": 37.068,
      "eval_steps_per_second": 4.671,
      "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": 1.0621851944353792e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}