{
  "best_metric": 0.00014307092351373285,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.11885306789481503,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002377061357896301,
      "grad_norm": 38.32674789428711,
      "learning_rate": 5e-05,
      "loss": 33.2987,
      "step": 1
    },
    {
      "epoch": 0.002377061357896301,
      "eval_loss": 2.0533382892608643,
      "eval_runtime": 67.9226,
      "eval_samples_per_second": 41.724,
      "eval_steps_per_second": 5.227,
      "step": 1
    },
    {
      "epoch": 0.004754122715792602,
      "grad_norm": 36.541969299316406,
      "learning_rate": 0.0001,
      "loss": 32.1562,
      "step": 2
    },
    {
      "epoch": 0.007131184073688902,
      "grad_norm": 36.157711029052734,
      "learning_rate": 9.989294616193017e-05,
      "loss": 31.3953,
      "step": 3
    },
    {
      "epoch": 0.009508245431585204,
      "grad_norm": 38.35823440551758,
      "learning_rate": 9.957224306869053e-05,
      "loss": 26.2098,
      "step": 4
    },
    {
      "epoch": 0.011885306789481503,
      "grad_norm": 36.233970642089844,
      "learning_rate": 9.903926402016153e-05,
      "loss": 19.0098,
      "step": 5
    },
    {
      "epoch": 0.014262368147377804,
      "grad_norm": 31.973276138305664,
      "learning_rate": 9.829629131445342e-05,
      "loss": 12.8589,
      "step": 6
    },
    {
      "epoch": 0.016639429505274105,
      "grad_norm": 21.48830795288086,
      "learning_rate": 9.73465064747553e-05,
      "loss": 7.4534,
      "step": 7
    },
    {
      "epoch": 0.019016490863170407,
      "grad_norm": 16.298980712890625,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.8427,
      "step": 8
    },
    {
      "epoch": 0.021393552221066706,
      "grad_norm": 15.034470558166504,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.7704,
      "step": 9
    },
    {
      "epoch": 0.023770613578963005,
      "grad_norm": 7.554548263549805,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.3207,
      "step": 10
    },
    {
      "epoch": 0.026147674936859308,
      "grad_norm": 4.658464431762695,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.583,
      "step": 11
    },
    {
      "epoch": 0.028524736294755607,
      "grad_norm": 2.1628975868225098,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.2339,
      "step": 12
    },
    {
      "epoch": 0.03090179765265191,
      "grad_norm": 1.2267247438430786,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.2359,
      "step": 13
    },
    {
      "epoch": 0.03327885901054821,
      "grad_norm": 1.0571072101593018,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0424,
      "step": 14
    },
    {
      "epoch": 0.03565592036844451,
      "grad_norm": 0.28590092062950134,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.0149,
      "step": 15
    },
    {
      "epoch": 0.038032981726340814,
      "grad_norm": 1.3651249408721924,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.0367,
      "step": 16
    },
    {
      "epoch": 0.04041004308423711,
      "grad_norm": 0.8734675049781799,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.0101,
      "step": 17
    },
    {
      "epoch": 0.04278710444213341,
      "grad_norm": 0.05193432420492172,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0018,
      "step": 18
    },
    {
      "epoch": 0.045164165800029715,
      "grad_norm": 0.04141559079289436,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.0014,
      "step": 19
    },
    {
      "epoch": 0.04754122715792601,
      "grad_norm": 0.02652605250477791,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0008,
      "step": 20
    },
    {
      "epoch": 0.049918288515822314,
      "grad_norm": 0.03439049422740936,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.0009,
      "step": 21
    },
    {
      "epoch": 0.052295349873718616,
      "grad_norm": 0.096359021961689,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0015,
      "step": 22
    },
    {
      "epoch": 0.05467241123161492,
      "grad_norm": 0.03302336111664772,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.0012,
      "step": 23
    },
    {
      "epoch": 0.057049472589511215,
      "grad_norm": 0.027081813663244247,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0007,
      "step": 24
    },
    {
      "epoch": 0.05942653394740752,
      "grad_norm": 0.06951026618480682,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.0016,
      "step": 25
    },
    {
      "epoch": 0.05942653394740752,
      "eval_loss": 0.0004589141171891242,
      "eval_runtime": 67.9274,
      "eval_samples_per_second": 41.721,
      "eval_steps_per_second": 5.226,
      "step": 25
    },
    {
      "epoch": 0.06180359530530382,
      "grad_norm": 0.5359752178192139,
      "learning_rate": 5e-05,
      "loss": 0.0032,
      "step": 26
    },
    {
      "epoch": 0.06418065666320012,
      "grad_norm": 0.013400775380432606,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.0005,
      "step": 27
    },
    {
      "epoch": 0.06655771802109642,
      "grad_norm": 0.19051715731620789,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0026,
      "step": 28
    },
    {
      "epoch": 0.06893477937899271,
      "grad_norm": 0.01478293351829052,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.0006,
      "step": 29
    },
    {
      "epoch": 0.07131184073688902,
      "grad_norm": 0.016781041398644447,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0007,
      "step": 30
    },
    {
      "epoch": 0.07368890209478532,
      "grad_norm": 0.8415308594703674,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.005,
      "step": 31
    },
    {
      "epoch": 0.07606596345268163,
      "grad_norm": 0.009778022766113281,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0004,
      "step": 32
    },
    {
      "epoch": 0.07844302481057792,
      "grad_norm": 0.013184771873056889,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.0004,
      "step": 33
    },
    {
      "epoch": 0.08082008616847422,
      "grad_norm": 0.011009763926267624,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0004,
      "step": 34
    },
    {
      "epoch": 0.08319714752637053,
      "grad_norm": 0.015330126509070396,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.0006,
      "step": 35
    },
    {
      "epoch": 0.08557420888426683,
      "grad_norm": 0.015668345615267754,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0005,
      "step": 36
    },
    {
      "epoch": 0.08795127024216312,
      "grad_norm": 0.0042808507569134235,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.0003,
      "step": 37
    },
    {
      "epoch": 0.09032833160005943,
      "grad_norm": 0.07753123342990875,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0009,
      "step": 38
    },
    {
      "epoch": 0.09270539295795573,
      "grad_norm": 0.010145001113414764,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.0006,
      "step": 39
    },
    {
      "epoch": 0.09508245431585202,
      "grad_norm": 16.53394889831543,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0323,
      "step": 40
    },
    {
      "epoch": 0.09745951567374833,
      "grad_norm": 0.01686001382768154,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.0005,
      "step": 41
    },
    {
      "epoch": 0.09983657703164463,
      "grad_norm": 0.028522521257400513,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0007,
      "step": 42
    },
    {
      "epoch": 0.10221363838954094,
      "grad_norm": 0.03315084055066109,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.0005,
      "step": 43
    },
    {
      "epoch": 0.10459069974743723,
      "grad_norm": 0.019801389425992966,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0006,
      "step": 44
    },
    {
      "epoch": 0.10696776110533353,
      "grad_norm": 0.06491321325302124,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.0006,
      "step": 45
    },
    {
      "epoch": 0.10934482246322984,
      "grad_norm": 0.006896046455949545,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0003,
      "step": 46
    },
    {
      "epoch": 0.11172188382112613,
      "grad_norm": 1.4069654941558838,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.017,
      "step": 47
    },
    {
      "epoch": 0.11409894517902243,
      "grad_norm": 0.004831578582525253,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0004,
      "step": 48
    },
    {
      "epoch": 0.11647600653691874,
      "grad_norm": 0.0032711592502892017,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.0003,
      "step": 49
    },
    {
      "epoch": 0.11885306789481503,
      "grad_norm": 0.004975167568773031,
      "learning_rate": 0.0,
      "loss": 0.0003,
      "step": 50
    },
    {
      "epoch": 0.11885306789481503,
      "eval_loss": 0.00014307092351373285,
      "eval_runtime": 67.8913,
      "eval_samples_per_second": 41.743,
      "eval_steps_per_second": 5.229,
      "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": 5.259156315439104e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}