{
  "best_metric": 0.0012522473698481917,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.09178522257916476,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018357044515832951,
      "grad_norm": 0.2928873896598816,
      "learning_rate": 5e-05,
      "loss": 0.1753,
      "step": 1
    },
    {
      "epoch": 0.0018357044515832951,
      "eval_loss": 0.38865751028060913,
      "eval_runtime": 41.2309,
      "eval_samples_per_second": 89.011,
      "eval_steps_per_second": 11.132,
      "step": 1
    },
    {
      "epoch": 0.0036714089031665903,
      "grad_norm": 0.4267287254333496,
      "learning_rate": 0.0001,
      "loss": 0.248,
      "step": 2
    },
    {
      "epoch": 0.005507113354749885,
      "grad_norm": 0.6412559747695923,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.2586,
      "step": 3
    },
    {
      "epoch": 0.0073428178063331805,
      "grad_norm": 0.802036464214325,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.2316,
      "step": 4
    },
    {
      "epoch": 0.009178522257916476,
      "grad_norm": 0.7878978848457336,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.1949,
      "step": 5
    },
    {
      "epoch": 0.01101422670949977,
      "grad_norm": 1.0017526149749756,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.1515,
      "step": 6
    },
    {
      "epoch": 0.012849931161083065,
      "grad_norm": 1.1407560110092163,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.0956,
      "step": 7
    },
    {
      "epoch": 0.014685635612666361,
      "grad_norm": 0.523012638092041,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.031,
      "step": 8
    },
    {
      "epoch": 0.016521340064249657,
      "grad_norm": 0.5377586483955383,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.0279,
      "step": 9
    },
    {
      "epoch": 0.018357044515832952,
      "grad_norm": 0.22875626385211945,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0156,
      "step": 10
    },
    {
      "epoch": 0.020192748967416244,
      "grad_norm": 0.1998831033706665,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.0123,
      "step": 11
    },
    {
      "epoch": 0.02202845341899954,
      "grad_norm": 0.15149080753326416,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0101,
      "step": 12
    },
    {
      "epoch": 0.023864157870582835,
      "grad_norm": 0.1921183168888092,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.0073,
      "step": 13
    },
    {
      "epoch": 0.02569986232216613,
      "grad_norm": 0.12274091690778732,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0074,
      "step": 14
    },
    {
      "epoch": 0.027535566773749427,
      "grad_norm": 0.09888946264982224,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0037,
      "step": 15
    },
    {
      "epoch": 0.029371271225332722,
      "grad_norm": 0.15110571682453156,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0048,
      "step": 16
    },
    {
      "epoch": 0.031206975676916018,
      "grad_norm": 0.08197781443595886,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0043,
      "step": 17
    },
    {
      "epoch": 0.03304268012849931,
      "grad_norm": 0.07734855264425278,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0041,
      "step": 18
    },
    {
      "epoch": 0.034878384580082605,
      "grad_norm": 0.1509590893983841,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.004,
      "step": 19
    },
    {
      "epoch": 0.036714089031665904,
      "grad_norm": 0.03136239945888519,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0029,
      "step": 20
    },
    {
      "epoch": 0.038549793483249196,
      "grad_norm": 0.15574848651885986,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0044,
      "step": 21
    },
    {
      "epoch": 0.04038549793483249,
      "grad_norm": 0.018918730318546295,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0011,
      "step": 22
    },
    {
      "epoch": 0.04222120238641579,
      "grad_norm": 0.07930710166692734,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0016,
      "step": 23
    },
    {
      "epoch": 0.04405690683799908,
      "grad_norm": 0.020364737138152122,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0012,
      "step": 24
    },
    {
      "epoch": 0.04589261128958238,
      "grad_norm": 0.14952942728996277,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.005,
      "step": 25
    },
    {
      "epoch": 0.04589261128958238,
      "eval_loss": 0.002253216225653887,
      "eval_runtime": 43.9756,
      "eval_samples_per_second": 83.455,
      "eval_steps_per_second": 10.438,
      "step": 25
    },
    {
      "epoch": 0.04772831574116567,
      "grad_norm": 0.054946526885032654,
      "learning_rate": 5e-05,
      "loss": 0.0035,
      "step": 26
    },
    {
      "epoch": 0.04956402019274897,
      "grad_norm": 0.049321189522743225,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0019,
      "step": 27
    },
    {
      "epoch": 0.05139972464433226,
      "grad_norm": 0.04542066156864166,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.002,
      "step": 28
    },
    {
      "epoch": 0.05323542909591556,
      "grad_norm": 0.09802614152431488,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0021,
      "step": 29
    },
    {
      "epoch": 0.05507113354749885,
      "grad_norm": 0.061021555215120316,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0039,
      "step": 30
    },
    {
      "epoch": 0.056906837999082145,
      "grad_norm": 0.03209061920642853,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.0015,
      "step": 31
    },
    {
      "epoch": 0.058742542450665444,
      "grad_norm": 0.03987056016921997,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0019,
      "step": 32
    },
    {
      "epoch": 0.060578246902248736,
      "grad_norm": 0.014652871526777744,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0009,
      "step": 33
    },
    {
      "epoch": 0.062413951353832035,
      "grad_norm": 0.03821863979101181,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0016,
      "step": 34
    },
    {
      "epoch": 0.06424965580541533,
      "grad_norm": 0.03729190304875374,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0019,
      "step": 35
    },
    {
      "epoch": 0.06608536025699863,
      "grad_norm": 0.029762962833046913,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.001,
      "step": 36
    },
    {
      "epoch": 0.06792106470858192,
      "grad_norm": 0.01879103109240532,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0009,
      "step": 37
    },
    {
      "epoch": 0.06975676916016521,
      "grad_norm": 0.0443434864282608,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0026,
      "step": 38
    },
    {
      "epoch": 0.0715924736117485,
      "grad_norm": 0.07768885791301727,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0028,
      "step": 39
    },
    {
      "epoch": 0.07342817806333181,
      "grad_norm": 0.03938576206564903,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0016,
      "step": 40
    },
    {
      "epoch": 0.0752638825149151,
      "grad_norm": 0.03616311401128769,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0009,
      "step": 41
    },
    {
      "epoch": 0.07709958696649839,
      "grad_norm": 0.01792808808386326,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0009,
      "step": 42
    },
    {
      "epoch": 0.07893529141808169,
      "grad_norm": 0.0829036682844162,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0011,
      "step": 43
    },
    {
      "epoch": 0.08077099586966498,
      "grad_norm": 0.03096242994070053,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0035,
      "step": 44
    },
    {
      "epoch": 0.08260670032124828,
      "grad_norm": 0.05540601536631584,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0009,
      "step": 45
    },
    {
      "epoch": 0.08444240477283158,
      "grad_norm": 0.021263469010591507,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0007,
      "step": 46
    },
    {
      "epoch": 0.08627810922441487,
      "grad_norm": 0.05774582549929619,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.0023,
      "step": 47
    },
    {
      "epoch": 0.08811381367599816,
      "grad_norm": 0.03489619493484497,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0011,
      "step": 48
    },
    {
      "epoch": 0.08994951812758147,
      "grad_norm": 0.017400847747921944,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0012,
      "step": 49
    },
    {
      "epoch": 0.09178522257916476,
      "grad_norm": 0.07380491495132446,
      "learning_rate": 0.0,
      "loss": 0.0036,
      "step": 50
    },
    {
      "epoch": 0.09178522257916476,
      "eval_loss": 0.0012522473698481917,
      "eval_runtime": 41.0872,
      "eval_samples_per_second": 89.322,
      "eval_steps_per_second": 11.171,
      "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": 1.0598674582837658e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}