{
  "best_metric": 1.4253883361816406,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.032957073411881026,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006591414682376205,
      "grad_norm": 0.6790323257446289,
      "learning_rate": 5e-05,
      "loss": 1.6222,
      "step": 1
    },
    {
      "epoch": 0.0006591414682376205,
      "eval_loss": 1.836203932762146,
      "eval_runtime": 296.9586,
      "eval_samples_per_second": 34.419,
      "eval_steps_per_second": 4.304,
      "step": 1
    },
    {
      "epoch": 0.001318282936475241,
      "grad_norm": 0.6822174191474915,
      "learning_rate": 0.0001,
      "loss": 1.6474,
      "step": 2
    },
    {
      "epoch": 0.0019774244047128615,
      "grad_norm": 0.6467229127883911,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.6169,
      "step": 3
    },
    {
      "epoch": 0.002636565872950482,
      "grad_norm": 0.545185387134552,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.5051,
      "step": 4
    },
    {
      "epoch": 0.0032957073411881027,
      "grad_norm": 0.2817743420600891,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.4512,
      "step": 5
    },
    {
      "epoch": 0.003954848809425723,
      "grad_norm": 0.4623984694480896,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.4715,
      "step": 6
    },
    {
      "epoch": 0.004613990277663344,
      "grad_norm": 0.6100432872772217,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.4865,
      "step": 7
    },
    {
      "epoch": 0.005273131745900964,
      "grad_norm": 0.46749556064605713,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.5081,
      "step": 8
    },
    {
      "epoch": 0.0059322732141385845,
      "grad_norm": 0.31567704677581787,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.6606,
      "step": 9
    },
    {
      "epoch": 0.006591414682376205,
      "grad_norm": 0.45639654994010925,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.8446,
      "step": 10
    },
    {
      "epoch": 0.007250556150613825,
      "grad_norm": 0.4724658727645874,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.8538,
      "step": 11
    },
    {
      "epoch": 0.007909697618851446,
      "grad_norm": 0.4332147538661957,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.9509,
      "step": 12
    },
    {
      "epoch": 0.008568839087089067,
      "grad_norm": 0.2523305416107178,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.3743,
      "step": 13
    },
    {
      "epoch": 0.009227980555326688,
      "grad_norm": 0.23553816974163055,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3544,
      "step": 14
    },
    {
      "epoch": 0.009887122023564307,
      "grad_norm": 0.21183012425899506,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.3465,
      "step": 15
    },
    {
      "epoch": 0.010546263491801927,
      "grad_norm": 0.16247883439064026,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.3308,
      "step": 16
    },
    {
      "epoch": 0.011205404960039548,
      "grad_norm": 0.14963077008724213,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.3331,
      "step": 17
    },
    {
      "epoch": 0.011864546428277169,
      "grad_norm": 0.1518392562866211,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3469,
      "step": 18
    },
    {
      "epoch": 0.01252368789651479,
      "grad_norm": 0.15816082060337067,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.326,
      "step": 19
    },
    {
      "epoch": 0.01318282936475241,
      "grad_norm": 0.17692376673221588,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.3788,
      "step": 20
    },
    {
      "epoch": 0.01384197083299003,
      "grad_norm": 0.19621223211288452,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.46,
      "step": 21
    },
    {
      "epoch": 0.01450111230122765,
      "grad_norm": 0.3078196048736572,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.6276,
      "step": 22
    },
    {
      "epoch": 0.015160253769465271,
      "grad_norm": 0.40529724955558777,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.6692,
      "step": 23
    },
    {
      "epoch": 0.015819395237702892,
      "grad_norm": 0.3335389792919159,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.7462,
      "step": 24
    },
    {
      "epoch": 0.016478536705940513,
      "grad_norm": 0.3342079818248749,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.7909,
      "step": 25
    },
    {
      "epoch": 0.016478536705940513,
      "eval_loss": 1.4591978788375854,
      "eval_runtime": 287.7398,
      "eval_samples_per_second": 35.522,
      "eval_steps_per_second": 4.442,
      "step": 25
    },
    {
      "epoch": 0.017137678174178134,
      "grad_norm": 0.19020310044288635,
      "learning_rate": 5e-05,
      "loss": 1.3073,
      "step": 26
    },
    {
      "epoch": 0.017796819642415754,
      "grad_norm": 0.1739782691001892,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.2809,
      "step": 27
    },
    {
      "epoch": 0.018455961110653375,
      "grad_norm": 0.1638297438621521,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.3014,
      "step": 28
    },
    {
      "epoch": 0.019115102578890996,
      "grad_norm": 0.1574772596359253,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.2768,
      "step": 29
    },
    {
      "epoch": 0.019774244047128613,
      "grad_norm": 0.13562825322151184,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.3035,
      "step": 30
    },
    {
      "epoch": 0.020433385515366234,
      "grad_norm": 0.13689446449279785,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.2952,
      "step": 31
    },
    {
      "epoch": 0.021092526983603855,
      "grad_norm": 0.12440229952335358,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.3424,
      "step": 32
    },
    {
      "epoch": 0.021751668451841476,
      "grad_norm": 0.1770576387643814,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.4069,
      "step": 33
    },
    {
      "epoch": 0.022410809920079097,
      "grad_norm": 0.2141914814710617,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5183,
      "step": 34
    },
    {
      "epoch": 0.023069951388316717,
      "grad_norm": 0.31634941697120667,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.6166,
      "step": 35
    },
    {
      "epoch": 0.023729092856554338,
      "grad_norm": 0.29751285910606384,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.6496,
      "step": 36
    },
    {
      "epoch": 0.02438823432479196,
      "grad_norm": 0.28590714931488037,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.708,
      "step": 37
    },
    {
      "epoch": 0.02504737579302958,
      "grad_norm": 0.11785943806171417,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.3091,
      "step": 38
    },
    {
      "epoch": 0.0257065172612672,
      "grad_norm": 0.10514993965625763,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.2735,
      "step": 39
    },
    {
      "epoch": 0.02636565872950482,
      "grad_norm": 0.09633257985115051,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.3116,
      "step": 40
    },
    {
      "epoch": 0.027024800197742442,
      "grad_norm": 0.10499632358551025,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.2612,
      "step": 41
    },
    {
      "epoch": 0.02768394166598006,
      "grad_norm": 0.09367036074399948,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.2759,
      "step": 42
    },
    {
      "epoch": 0.02834308313421768,
      "grad_norm": 0.105850450694561,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.2775,
      "step": 43
    },
    {
      "epoch": 0.0290022246024553,
      "grad_norm": 0.11707086116075516,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.3,
      "step": 44
    },
    {
      "epoch": 0.029661366070692922,
      "grad_norm": 0.13155709207057953,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.3426,
      "step": 45
    },
    {
      "epoch": 0.030320507538930543,
      "grad_norm": 0.17515063285827637,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.4371,
      "step": 46
    },
    {
      "epoch": 0.030979649007168163,
      "grad_norm": 0.21689704060554504,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.5299,
      "step": 47
    },
    {
      "epoch": 0.031638790475405784,
      "grad_norm": 0.2483842819929123,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.6002,
      "step": 48
    },
    {
      "epoch": 0.0322979319436434,
      "grad_norm": 0.2632664442062378,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.6981,
      "step": 49
    },
    {
      "epoch": 0.032957073411881026,
      "grad_norm": 0.30653318762779236,
      "learning_rate": 0.0,
      "loss": 1.7189,
      "step": 50
    },
    {
      "epoch": 0.032957073411881026,
      "eval_loss": 1.4253883361816406,
      "eval_runtime": 287.7518,
      "eval_samples_per_second": 35.52,
      "eval_steps_per_second": 4.441,
      "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": 5.259104775831552e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}