{
  "best_metric": 1.575398325920105,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.40526849037487334,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008105369807497468,
      "grad_norm": 8.006129264831543,
      "learning_rate": 5e-05,
      "loss": 2.4502,
      "step": 1
    },
    {
      "epoch": 0.008105369807497468,
      "eval_loss": 3.2280056476593018,
      "eval_runtime": 23.9456,
      "eval_samples_per_second": 34.704,
      "eval_steps_per_second": 4.343,
      "step": 1
    },
    {
      "epoch": 0.016210739614994935,
      "grad_norm": 8.873369216918945,
      "learning_rate": 0.0001,
      "loss": 2.439,
      "step": 2
    },
    {
      "epoch": 0.0243161094224924,
      "grad_norm": 4.674134254455566,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.4121,
      "step": 3
    },
    {
      "epoch": 0.03242147922998987,
      "grad_norm": 4.291029930114746,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.0236,
      "step": 4
    },
    {
      "epoch": 0.040526849037487336,
      "grad_norm": 1.8941280841827393,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.8312,
      "step": 5
    },
    {
      "epoch": 0.0486322188449848,
      "grad_norm": 1.9628219604492188,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.8453,
      "step": 6
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 1.2366397380828857,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.824,
      "step": 7
    },
    {
      "epoch": 0.06484295845997974,
      "grad_norm": 1.1271775960922241,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.947,
      "step": 8
    },
    {
      "epoch": 0.0729483282674772,
      "grad_norm": 1.2037513256072998,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.9343,
      "step": 9
    },
    {
      "epoch": 0.08105369807497467,
      "grad_norm": 0.6210329532623291,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.043,
      "step": 10
    },
    {
      "epoch": 0.08915906788247213,
      "grad_norm": 1.6234967708587646,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.0205,
      "step": 11
    },
    {
      "epoch": 0.0972644376899696,
      "grad_norm": 2.5917980670928955,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.3495,
      "step": 12
    },
    {
      "epoch": 0.10536980749746708,
      "grad_norm": 0.6617282032966614,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.5079,
      "step": 13
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 1.0603861808776855,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4059,
      "step": 14
    },
    {
      "epoch": 0.12158054711246201,
      "grad_norm": 0.2410304695367813,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.2882,
      "step": 15
    },
    {
      "epoch": 0.12968591691995948,
      "grad_norm": 1.0002857446670532,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.309,
      "step": 16
    },
    {
      "epoch": 0.13779128672745694,
      "grad_norm": 0.21932756900787354,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.3477,
      "step": 17
    },
    {
      "epoch": 0.1458966565349544,
      "grad_norm": 0.8311377167701721,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3537,
      "step": 18
    },
    {
      "epoch": 0.1540020263424519,
      "grad_norm": 0.36103275418281555,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.4662,
      "step": 19
    },
    {
      "epoch": 0.16210739614994935,
      "grad_norm": 0.5048967599868774,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.553,
      "step": 20
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.49071255326271057,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.6798,
      "step": 21
    },
    {
      "epoch": 0.17831813576494426,
      "grad_norm": 0.23048630356788635,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.7716,
      "step": 22
    },
    {
      "epoch": 0.18642350557244175,
      "grad_norm": 0.5144177675247192,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.8874,
      "step": 23
    },
    {
      "epoch": 0.1945288753799392,
      "grad_norm": 0.3754597306251526,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 2.0819,
      "step": 24
    },
    {
      "epoch": 0.20263424518743667,
      "grad_norm": 0.4944089353084564,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.3222,
      "step": 25
    },
    {
      "epoch": 0.20263424518743667,
      "eval_loss": 1.610286831855774,
      "eval_runtime": 23.9512,
      "eval_samples_per_second": 34.696,
      "eval_steps_per_second": 4.342,
      "step": 25
    },
    {
      "epoch": 0.21073961499493415,
      "grad_norm": 0.4609486758708954,
      "learning_rate": 5e-05,
      "loss": 1.4097,
      "step": 26
    },
    {
      "epoch": 0.2188449848024316,
      "grad_norm": 0.4215725362300873,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.3428,
      "step": 27
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 0.1735449880361557,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.356,
      "step": 28
    },
    {
      "epoch": 0.23505572441742653,
      "grad_norm": 0.34462130069732666,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.255,
      "step": 29
    },
    {
      "epoch": 0.24316109422492402,
      "grad_norm": 0.4521256387233734,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.454,
      "step": 30
    },
    {
      "epoch": 0.2512664640324215,
      "grad_norm": 0.31536778807640076,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.5345,
      "step": 31
    },
    {
      "epoch": 0.25937183383991896,
      "grad_norm": 0.24369029700756073,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.4908,
      "step": 32
    },
    {
      "epoch": 0.2674772036474164,
      "grad_norm": 0.26428598165512085,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.6715,
      "step": 33
    },
    {
      "epoch": 0.2755825734549139,
      "grad_norm": 0.5214453935623169,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.6503,
      "step": 34
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.5043501257896423,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.7385,
      "step": 35
    },
    {
      "epoch": 0.2917933130699088,
      "grad_norm": 0.3178763687610626,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.9422,
      "step": 36
    },
    {
      "epoch": 0.2998986828774063,
      "grad_norm": 0.3138425946235657,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.891,
      "step": 37
    },
    {
      "epoch": 0.3080040526849038,
      "grad_norm": 0.2134198397397995,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4375,
      "step": 38
    },
    {
      "epoch": 0.3161094224924012,
      "grad_norm": 0.17055901885032654,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.2945,
      "step": 39
    },
    {
      "epoch": 0.3242147922998987,
      "grad_norm": 0.2024005800485611,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.2328,
      "step": 40
    },
    {
      "epoch": 0.3323201621073962,
      "grad_norm": 0.24119697511196136,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.2443,
      "step": 41
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 0.264860600233078,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.3573,
      "step": 42
    },
    {
      "epoch": 0.3485309017223911,
      "grad_norm": 0.2475137561559677,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.3693,
      "step": 43
    },
    {
      "epoch": 0.3566362715298885,
      "grad_norm": 0.263443261384964,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.4624,
      "step": 44
    },
    {
      "epoch": 0.364741641337386,
      "grad_norm": 0.245119109749794,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.5382,
      "step": 45
    },
    {
      "epoch": 0.3728470111448835,
      "grad_norm": 0.2825349271297455,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.6151,
      "step": 46
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.22986000776290894,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.6462,
      "step": 47
    },
    {
      "epoch": 0.3890577507598784,
      "grad_norm": 0.2516135275363922,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.8061,
      "step": 48
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 0.27178332209587097,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.9348,
      "step": 49
    },
    {
      "epoch": 0.40526849037487334,
      "grad_norm": 0.5136006474494934,
      "learning_rate": 0.0,
      "loss": 2.1856,
      "step": 50
    },
    {
      "epoch": 0.40526849037487334,
      "eval_loss": 1.575398325920105,
      "eval_runtime": 23.9252,
      "eval_samples_per_second": 34.733,
      "eval_steps_per_second": 4.347,
      "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": 5.305284264198144e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}