{
  "best_metric": 4.109295845031738,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.13635588886995056,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027271177773990113,
      "grad_norm": 23.99407196044922,
      "learning_rate": 5e-05,
      "loss": 6.5334,
      "step": 1
    },
    {
      "epoch": 0.0027271177773990113,
      "eval_loss": 7.971259593963623,
      "eval_runtime": 22.6821,
      "eval_samples_per_second": 108.897,
      "eval_steps_per_second": 13.623,
      "step": 1
    },
    {
      "epoch": 0.005454235554798023,
      "grad_norm": 31.678979873657227,
      "learning_rate": 0.0001,
      "loss": 6.9307,
      "step": 2
    },
    {
      "epoch": 0.008181353332197034,
      "grad_norm": 14.564484596252441,
      "learning_rate": 9.989294616193017e-05,
      "loss": 6.7517,
      "step": 3
    },
    {
      "epoch": 0.010908471109596045,
      "grad_norm": 16.406156539916992,
      "learning_rate": 9.957224306869053e-05,
      "loss": 6.6504,
      "step": 4
    },
    {
      "epoch": 0.013635588886995058,
      "grad_norm": 8.475127220153809,
      "learning_rate": 9.903926402016153e-05,
      "loss": 6.5568,
      "step": 5
    },
    {
      "epoch": 0.01636270666439407,
      "grad_norm": 17.04689598083496,
      "learning_rate": 9.829629131445342e-05,
      "loss": 6.3192,
      "step": 6
    },
    {
      "epoch": 0.01908982444179308,
      "grad_norm": 18.254878997802734,
      "learning_rate": 9.73465064747553e-05,
      "loss": 5.9378,
      "step": 7
    },
    {
      "epoch": 0.02181694221919209,
      "grad_norm": 9.73586368560791,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.8095,
      "step": 8
    },
    {
      "epoch": 0.0245440599965911,
      "grad_norm": 6.178478240966797,
      "learning_rate": 9.484363707663442e-05,
      "loss": 5.6911,
      "step": 9
    },
    {
      "epoch": 0.027271177773990116,
      "grad_norm": 10.496391296386719,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.5548,
      "step": 10
    },
    {
      "epoch": 0.029998295551389127,
      "grad_norm": 10.32470989227295,
      "learning_rate": 9.157348061512727e-05,
      "loss": 5.4559,
      "step": 11
    },
    {
      "epoch": 0.03272541332878814,
      "grad_norm": 6.1552557945251465,
      "learning_rate": 8.966766701456177e-05,
      "loss": 5.7297,
      "step": 12
    },
    {
      "epoch": 0.03545253110618715,
      "grad_norm": 8.280558586120605,
      "learning_rate": 8.759199037394887e-05,
      "loss": 4.9186,
      "step": 13
    },
    {
      "epoch": 0.03817964888358616,
      "grad_norm": 5.852046012878418,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.5106,
      "step": 14
    },
    {
      "epoch": 0.040906766660985174,
      "grad_norm": 3.1694095134735107,
      "learning_rate": 8.296729075500344e-05,
      "loss": 4.3904,
      "step": 15
    },
    {
      "epoch": 0.04363388443838418,
      "grad_norm": 3.3688089847564697,
      "learning_rate": 8.043807145043604e-05,
      "loss": 4.3411,
      "step": 16
    },
    {
      "epoch": 0.046361002215783195,
      "grad_norm": 3.222318410873413,
      "learning_rate": 7.777851165098012e-05,
      "loss": 4.3691,
      "step": 17
    },
    {
      "epoch": 0.0490881199931822,
      "grad_norm": 4.088284969329834,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.3977,
      "step": 18
    },
    {
      "epoch": 0.05181523777058122,
      "grad_norm": 2.59112286567688,
      "learning_rate": 7.211443451095007e-05,
      "loss": 4.3705,
      "step": 19
    },
    {
      "epoch": 0.05454235554798023,
      "grad_norm": 3.207937717437744,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.4536,
      "step": 20
    },
    {
      "epoch": 0.05726947332537924,
      "grad_norm": 2.292299270629883,
      "learning_rate": 6.607197326515808e-05,
      "loss": 4.2739,
      "step": 21
    },
    {
      "epoch": 0.05999659110277825,
      "grad_norm": 2.331582546234131,
      "learning_rate": 6.294095225512603e-05,
      "loss": 4.4515,
      "step": 22
    },
    {
      "epoch": 0.06272370888017727,
      "grad_norm": 2.8186817169189453,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 4.4827,
      "step": 23
    },
    {
      "epoch": 0.06545082665757627,
      "grad_norm": 3.3522398471832275,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 4.535,
      "step": 24
    },
    {
      "epoch": 0.06817794443497528,
      "grad_norm": 7.1114373207092285,
      "learning_rate": 5.327015646150716e-05,
      "loss": 4.6403,
      "step": 25
    },
    {
      "epoch": 0.06817794443497528,
      "eval_loss": 4.349310874938965,
      "eval_runtime": 22.6616,
      "eval_samples_per_second": 108.995,
      "eval_steps_per_second": 13.635,
      "step": 25
    },
    {
      "epoch": 0.0709050622123743,
      "grad_norm": 5.366950988769531,
      "learning_rate": 5e-05,
      "loss": 4.1341,
      "step": 26
    },
    {
      "epoch": 0.07363217998977331,
      "grad_norm": 4.294180393218994,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 4.1222,
      "step": 27
    },
    {
      "epoch": 0.07635929776717232,
      "grad_norm": 4.62194299697876,
      "learning_rate": 4.347369038899744e-05,
      "loss": 4.1533,
      "step": 28
    },
    {
      "epoch": 0.07908641554457133,
      "grad_norm": 2.8264970779418945,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 4.0021,
      "step": 29
    },
    {
      "epoch": 0.08181353332197035,
      "grad_norm": 1.9990670680999756,
      "learning_rate": 3.705904774487396e-05,
      "loss": 4.0211,
      "step": 30
    },
    {
      "epoch": 0.08454065109936935,
      "grad_norm": 2.144385576248169,
      "learning_rate": 3.392802673484193e-05,
      "loss": 4.0862,
      "step": 31
    },
    {
      "epoch": 0.08726776887676836,
      "grad_norm": 2.083113670349121,
      "learning_rate": 3.086582838174551e-05,
      "loss": 4.1946,
      "step": 32
    },
    {
      "epoch": 0.08999488665416738,
      "grad_norm": 3.0313470363616943,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 4.2242,
      "step": 33
    },
    {
      "epoch": 0.09272200443156639,
      "grad_norm": 2.697965621948242,
      "learning_rate": 2.500000000000001e-05,
      "loss": 4.2101,
      "step": 34
    },
    {
      "epoch": 0.0954491222089654,
      "grad_norm": 3.0470216274261475,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 4.2259,
      "step": 35
    },
    {
      "epoch": 0.0981762399863644,
      "grad_norm": 3.7986397743225098,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 4.3803,
      "step": 36
    },
    {
      "epoch": 0.10090335776376343,
      "grad_norm": 5.8233866691589355,
      "learning_rate": 1.703270924499656e-05,
      "loss": 4.5658,
      "step": 37
    },
    {
      "epoch": 0.10363047554116243,
      "grad_norm": 4.283393383026123,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 4.004,
      "step": 38
    },
    {
      "epoch": 0.10635759331856144,
      "grad_norm": 2.6006555557250977,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 3.7634,
      "step": 39
    },
    {
      "epoch": 0.10908471109596046,
      "grad_norm": 1.7798596620559692,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 3.9449,
      "step": 40
    },
    {
      "epoch": 0.11181182887335947,
      "grad_norm": 1.8412628173828125,
      "learning_rate": 8.426519384872733e-06,
      "loss": 3.8364,
      "step": 41
    },
    {
      "epoch": 0.11453894665075848,
      "grad_norm": 1.7957643270492554,
      "learning_rate": 6.698729810778065e-06,
      "loss": 4.0027,
      "step": 42
    },
    {
      "epoch": 0.11726606442815748,
      "grad_norm": 1.6139096021652222,
      "learning_rate": 5.156362923365588e-06,
      "loss": 3.9258,
      "step": 43
    },
    {
      "epoch": 0.1199931822055565,
      "grad_norm": 1.685750961303711,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 4.0996,
      "step": 44
    },
    {
      "epoch": 0.12272029998295551,
      "grad_norm": 1.6270910501480103,
      "learning_rate": 2.653493525244721e-06,
      "loss": 3.9753,
      "step": 45
    },
    {
      "epoch": 0.12544741776035453,
      "grad_norm": 1.973434567451477,
      "learning_rate": 1.70370868554659e-06,
      "loss": 4.1226,
      "step": 46
    },
    {
      "epoch": 0.12817453553775354,
      "grad_norm": 2.979440689086914,
      "learning_rate": 9.607359798384785e-07,
      "loss": 4.1031,
      "step": 47
    },
    {
      "epoch": 0.13090165331515255,
      "grad_norm": 2.294022798538208,
      "learning_rate": 4.277569313094809e-07,
      "loss": 4.183,
      "step": 48
    },
    {
      "epoch": 0.13362877109255156,
      "grad_norm": 3.7254600524902344,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 4.4106,
      "step": 49
    },
    {
      "epoch": 0.13635588886995056,
      "grad_norm": 6.3755784034729,
      "learning_rate": 0.0,
      "loss": 4.6472,
      "step": 50
    },
    {
      "epoch": 0.13635588886995056,
      "eval_loss": 4.109295845031738,
      "eval_runtime": 22.6607,
      "eval_samples_per_second": 108.999,
      "eval_steps_per_second": 13.636,
      "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": 8.33416392081408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}