{
  "best_metric": 5.284039497375488,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.22560631697687536,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0045121263395375075,
      "grad_norm": 0.7971600294113159,
      "learning_rate": 5e-05,
      "loss": 5.4973,
      "step": 1
    },
    {
      "epoch": 0.0045121263395375075,
      "eval_loss": 5.5700364112854,
      "eval_runtime": 17.1198,
      "eval_samples_per_second": 87.209,
      "eval_steps_per_second": 10.923,
      "step": 1
    },
    {
      "epoch": 0.009024252679075015,
      "grad_norm": 0.752615213394165,
      "learning_rate": 0.0001,
      "loss": 5.4864,
      "step": 2
    },
    {
      "epoch": 0.01353637901861252,
      "grad_norm": 0.6319518089294434,
      "learning_rate": 9.989294616193017e-05,
      "loss": 5.4513,
      "step": 3
    },
    {
      "epoch": 0.01804850535815003,
      "grad_norm": 1.4322975873947144,
      "learning_rate": 9.957224306869053e-05,
      "loss": 5.5335,
      "step": 4
    },
    {
      "epoch": 0.022560631697687534,
      "grad_norm": 0.8182398676872253,
      "learning_rate": 9.903926402016153e-05,
      "loss": 5.4645,
      "step": 5
    },
    {
      "epoch": 0.02707275803722504,
      "grad_norm": 0.38687223196029663,
      "learning_rate": 9.829629131445342e-05,
      "loss": 5.4091,
      "step": 6
    },
    {
      "epoch": 0.03158488437676255,
      "grad_norm": 0.3614707887172699,
      "learning_rate": 9.73465064747553e-05,
      "loss": 5.4116,
      "step": 7
    },
    {
      "epoch": 0.03609701071630006,
      "grad_norm": 0.3375658690929413,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.4517,
      "step": 8
    },
    {
      "epoch": 0.04060913705583756,
      "grad_norm": 0.3556500971317291,
      "learning_rate": 9.484363707663442e-05,
      "loss": 5.4722,
      "step": 9
    },
    {
      "epoch": 0.04512126339537507,
      "grad_norm": 0.34546974301338196,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.4698,
      "step": 10
    },
    {
      "epoch": 0.049633389734912575,
      "grad_norm": 0.3231700658798218,
      "learning_rate": 9.157348061512727e-05,
      "loss": 5.4668,
      "step": 11
    },
    {
      "epoch": 0.05414551607445008,
      "grad_norm": 0.37886548042297363,
      "learning_rate": 8.966766701456177e-05,
      "loss": 5.4336,
      "step": 12
    },
    {
      "epoch": 0.05865764241398759,
      "grad_norm": 0.3194134533405304,
      "learning_rate": 8.759199037394887e-05,
      "loss": 5.4119,
      "step": 13
    },
    {
      "epoch": 0.0631697687535251,
      "grad_norm": 0.4925616681575775,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.3697,
      "step": 14
    },
    {
      "epoch": 0.0676818950930626,
      "grad_norm": 0.5019106268882751,
      "learning_rate": 8.296729075500344e-05,
      "loss": 5.3329,
      "step": 15
    },
    {
      "epoch": 0.07219402143260012,
      "grad_norm": 0.36174947023391724,
      "learning_rate": 8.043807145043604e-05,
      "loss": 5.3869,
      "step": 16
    },
    {
      "epoch": 0.07670614777213762,
      "grad_norm": 0.35029304027557373,
      "learning_rate": 7.777851165098012e-05,
      "loss": 5.39,
      "step": 17
    },
    {
      "epoch": 0.08121827411167512,
      "grad_norm": 0.375354140996933,
      "learning_rate": 7.500000000000001e-05,
      "loss": 5.3349,
      "step": 18
    },
    {
      "epoch": 0.08573040045121263,
      "grad_norm": 0.37326130270957947,
      "learning_rate": 7.211443451095007e-05,
      "loss": 5.3235,
      "step": 19
    },
    {
      "epoch": 0.09024252679075014,
      "grad_norm": 0.36527517437934875,
      "learning_rate": 6.91341716182545e-05,
      "loss": 5.3454,
      "step": 20
    },
    {
      "epoch": 0.09475465313028765,
      "grad_norm": 0.3761279284954071,
      "learning_rate": 6.607197326515808e-05,
      "loss": 5.3628,
      "step": 21
    },
    {
      "epoch": 0.09926677946982515,
      "grad_norm": 0.34267348051071167,
      "learning_rate": 6.294095225512603e-05,
      "loss": 5.3636,
      "step": 22
    },
    {
      "epoch": 0.10377890580936266,
      "grad_norm": 0.42194825410842896,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 5.391,
      "step": 23
    },
    {
      "epoch": 0.10829103214890017,
      "grad_norm": 0.440165638923645,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 5.3327,
      "step": 24
    },
    {
      "epoch": 0.11280315848843768,
      "grad_norm": 0.5531956553459167,
      "learning_rate": 5.327015646150716e-05,
      "loss": 5.3381,
      "step": 25
    },
    {
      "epoch": 0.11280315848843768,
      "eval_loss": 5.3223090171813965,
      "eval_runtime": 17.0908,
      "eval_samples_per_second": 87.357,
      "eval_steps_per_second": 10.942,
      "step": 25
    },
    {
      "epoch": 0.11731528482797518,
      "grad_norm": 0.5369961857795715,
      "learning_rate": 5e-05,
      "loss": 5.3638,
      "step": 26
    },
    {
      "epoch": 0.1218274111675127,
      "grad_norm": 0.6307934522628784,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 5.2757,
      "step": 27
    },
    {
      "epoch": 0.1263395375070502,
      "grad_norm": 0.5815184116363525,
      "learning_rate": 4.347369038899744e-05,
      "loss": 5.3124,
      "step": 28
    },
    {
      "epoch": 0.1308516638465877,
      "grad_norm": 0.6315267086029053,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 5.3607,
      "step": 29
    },
    {
      "epoch": 0.1353637901861252,
      "grad_norm": 0.5649288892745972,
      "learning_rate": 3.705904774487396e-05,
      "loss": 5.3044,
      "step": 30
    },
    {
      "epoch": 0.13987591652566272,
      "grad_norm": 0.5160035490989685,
      "learning_rate": 3.392802673484193e-05,
      "loss": 5.2899,
      "step": 31
    },
    {
      "epoch": 0.14438804286520024,
      "grad_norm": 0.4791766107082367,
      "learning_rate": 3.086582838174551e-05,
      "loss": 5.273,
      "step": 32
    },
    {
      "epoch": 0.14890016920473773,
      "grad_norm": 0.49125534296035767,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 5.3027,
      "step": 33
    },
    {
      "epoch": 0.15341229554427524,
      "grad_norm": 0.4462452828884125,
      "learning_rate": 2.500000000000001e-05,
      "loss": 5.3172,
      "step": 34
    },
    {
      "epoch": 0.15792442188381275,
      "grad_norm": 0.5070551037788391,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 5.3515,
      "step": 35
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 0.45972564816474915,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 5.3145,
      "step": 36
    },
    {
      "epoch": 0.16694867456288776,
      "grad_norm": 0.5956875085830688,
      "learning_rate": 1.703270924499656e-05,
      "loss": 5.3125,
      "step": 37
    },
    {
      "epoch": 0.17146080090242527,
      "grad_norm": 0.5553387403488159,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 5.3294,
      "step": 38
    },
    {
      "epoch": 0.17597292724196278,
      "grad_norm": 0.5477205514907837,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 5.3052,
      "step": 39
    },
    {
      "epoch": 0.18048505358150027,
      "grad_norm": 0.6556831002235413,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 5.2196,
      "step": 40
    },
    {
      "epoch": 0.18499717992103779,
      "grad_norm": 0.5919263362884521,
      "learning_rate": 8.426519384872733e-06,
      "loss": 5.3095,
      "step": 41
    },
    {
      "epoch": 0.1895093062605753,
      "grad_norm": 0.5120022296905518,
      "learning_rate": 6.698729810778065e-06,
      "loss": 5.3153,
      "step": 42
    },
    {
      "epoch": 0.19402143260011281,
      "grad_norm": 0.4234735369682312,
      "learning_rate": 5.156362923365588e-06,
      "loss": 5.2862,
      "step": 43
    },
    {
      "epoch": 0.1985335589396503,
      "grad_norm": 0.4140225350856781,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 5.2435,
      "step": 44
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 0.4339873790740967,
      "learning_rate": 2.653493525244721e-06,
      "loss": 5.2891,
      "step": 45
    },
    {
      "epoch": 0.20755781161872533,
      "grad_norm": 0.3964301645755768,
      "learning_rate": 1.70370868554659e-06,
      "loss": 5.3019,
      "step": 46
    },
    {
      "epoch": 0.21206993795826284,
      "grad_norm": 0.3804386854171753,
      "learning_rate": 9.607359798384785e-07,
      "loss": 5.3065,
      "step": 47
    },
    {
      "epoch": 0.21658206429780033,
      "grad_norm": 0.4895821809768677,
      "learning_rate": 4.277569313094809e-07,
      "loss": 5.306,
      "step": 48
    },
    {
      "epoch": 0.22109419063733785,
      "grad_norm": 0.5049368739128113,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 5.3006,
      "step": 49
    },
    {
      "epoch": 0.22560631697687536,
      "grad_norm": 0.6009631156921387,
      "learning_rate": 0.0,
      "loss": 5.2781,
      "step": 50
    },
    {
      "epoch": 0.22560631697687536,
      "eval_loss": 5.284039497375488,
      "eval_runtime": 17.1469,
      "eval_samples_per_second": 87.071,
      "eval_steps_per_second": 10.906,
      "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": 1.059536353886208e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}