{
  "best_metric": 1.802408218383789,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.27952480782669464,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005590496156533892,
      "grad_norm": 3.375347375869751,
      "learning_rate": 5e-05,
      "loss": 3.4843,
      "step": 1
    },
    {
      "epoch": 0.005590496156533892,
      "eval_loss": 3.5440049171447754,
      "eval_runtime": 79.7068,
      "eval_samples_per_second": 15.118,
      "eval_steps_per_second": 1.894,
      "step": 1
    },
    {
      "epoch": 0.011180992313067784,
      "grad_norm": 3.6230032444000244,
      "learning_rate": 0.0001,
      "loss": 3.4947,
      "step": 2
    },
    {
      "epoch": 0.016771488469601678,
      "grad_norm": 3.5874381065368652,
      "learning_rate": 9.989294616193017e-05,
      "loss": 3.3285,
      "step": 3
    },
    {
      "epoch": 0.02236198462613557,
      "grad_norm": 3.016197443008423,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.7118,
      "step": 4
    },
    {
      "epoch": 0.027952480782669462,
      "grad_norm": 1.4132294654846191,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.2225,
      "step": 5
    },
    {
      "epoch": 0.033542976939203356,
      "grad_norm": 0.9763197898864746,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.0212,
      "step": 6
    },
    {
      "epoch": 0.039133473095737246,
      "grad_norm": 0.6066507697105408,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.974,
      "step": 7
    },
    {
      "epoch": 0.04472396925227114,
      "grad_norm": 1.3473191261291504,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.9496,
      "step": 8
    },
    {
      "epoch": 0.050314465408805034,
      "grad_norm": 0.8651624917984009,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.9296,
      "step": 9
    },
    {
      "epoch": 0.055904961565338925,
      "grad_norm": 1.3660520315170288,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.9349,
      "step": 10
    },
    {
      "epoch": 0.061495457721872815,
      "grad_norm": 0.7258374691009521,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.9106,
      "step": 11
    },
    {
      "epoch": 0.06708595387840671,
      "grad_norm": 0.8489522337913513,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.9355,
      "step": 12
    },
    {
      "epoch": 0.0726764500349406,
      "grad_norm": 0.3361421525478363,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.8979,
      "step": 13
    },
    {
      "epoch": 0.07826694619147449,
      "grad_norm": 1.4656604528427124,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9886,
      "step": 14
    },
    {
      "epoch": 0.08385744234800839,
      "grad_norm": 1.0648608207702637,
      "learning_rate": 8.296729075500344e-05,
      "loss": 1.9429,
      "step": 15
    },
    {
      "epoch": 0.08944793850454227,
      "grad_norm": 0.9452705979347229,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.9267,
      "step": 16
    },
    {
      "epoch": 0.09503843466107617,
      "grad_norm": 0.555007815361023,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.8837,
      "step": 17
    },
    {
      "epoch": 0.10062893081761007,
      "grad_norm": 0.937122642993927,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.9098,
      "step": 18
    },
    {
      "epoch": 0.10621942697414395,
      "grad_norm": 0.6235987544059753,
      "learning_rate": 7.211443451095007e-05,
      "loss": 1.8882,
      "step": 19
    },
    {
      "epoch": 0.11180992313067785,
      "grad_norm": 0.8975427150726318,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8652,
      "step": 20
    },
    {
      "epoch": 0.11740041928721175,
      "grad_norm": 0.40991145372390747,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.8333,
      "step": 21
    },
    {
      "epoch": 0.12299091544374563,
      "grad_norm": 0.3930458426475525,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8781,
      "step": 22
    },
    {
      "epoch": 0.12858141160027953,
      "grad_norm": 0.6450754404067993,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.8845,
      "step": 23
    },
    {
      "epoch": 0.13417190775681342,
      "grad_norm": 0.3807777762413025,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.8999,
      "step": 24
    },
    {
      "epoch": 0.13976240391334732,
      "grad_norm": 0.5022652745246887,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.8782,
      "step": 25
    },
    {
      "epoch": 0.13976240391334732,
      "eval_loss": 1.8583567142486572,
      "eval_runtime": 79.619,
      "eval_samples_per_second": 15.135,
      "eval_steps_per_second": 1.897,
      "step": 25
    },
    {
      "epoch": 0.1453529000698812,
      "grad_norm": 1.0631482601165771,
      "learning_rate": 5e-05,
      "loss": 1.8831,
      "step": 26
    },
    {
      "epoch": 0.1509433962264151,
      "grad_norm": 0.5609247088432312,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.8731,
      "step": 27
    },
    {
      "epoch": 0.15653389238294899,
      "grad_norm": 0.39559921622276306,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.8558,
      "step": 28
    },
    {
      "epoch": 0.16212438853948288,
      "grad_norm": 0.47969213128089905,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.8337,
      "step": 29
    },
    {
      "epoch": 0.16771488469601678,
      "grad_norm": 0.4855305850505829,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.8349,
      "step": 30
    },
    {
      "epoch": 0.17330538085255065,
      "grad_norm": 0.2550031542778015,
      "learning_rate": 3.392802673484193e-05,
      "loss": 1.8541,
      "step": 31
    },
    {
      "epoch": 0.17889587700908455,
      "grad_norm": 0.3771445155143738,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.7896,
      "step": 32
    },
    {
      "epoch": 0.18448637316561844,
      "grad_norm": 0.29389744997024536,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.8033,
      "step": 33
    },
    {
      "epoch": 0.19007686932215234,
      "grad_norm": 0.49211373925209045,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.8085,
      "step": 34
    },
    {
      "epoch": 0.19566736547868624,
      "grad_norm": 0.9361554384231567,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.7993,
      "step": 35
    },
    {
      "epoch": 0.20125786163522014,
      "grad_norm": 0.2670358717441559,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.8468,
      "step": 36
    },
    {
      "epoch": 0.206848357791754,
      "grad_norm": 0.39633437991142273,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.8736,
      "step": 37
    },
    {
      "epoch": 0.2124388539482879,
      "grad_norm": 0.8676222562789917,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.8282,
      "step": 38
    },
    {
      "epoch": 0.2180293501048218,
      "grad_norm": 0.6907089352607727,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.8042,
      "step": 39
    },
    {
      "epoch": 0.2236198462613557,
      "grad_norm": 0.39775529503822327,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.8102,
      "step": 40
    },
    {
      "epoch": 0.2292103424178896,
      "grad_norm": 0.6039819717407227,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.8196,
      "step": 41
    },
    {
      "epoch": 0.2348008385744235,
      "grad_norm": 0.6109508872032166,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.8307,
      "step": 42
    },
    {
      "epoch": 0.24039133473095736,
      "grad_norm": 0.34840458631515503,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.8035,
      "step": 43
    },
    {
      "epoch": 0.24598183088749126,
      "grad_norm": 0.37127500772476196,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.7735,
      "step": 44
    },
    {
      "epoch": 0.25157232704402516,
      "grad_norm": 0.4650353789329529,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.7549,
      "step": 45
    },
    {
      "epoch": 0.25716282320055905,
      "grad_norm": 0.6289724707603455,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.7748,
      "step": 46
    },
    {
      "epoch": 0.26275331935709295,
      "grad_norm": 0.3786230981349945,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.8439,
      "step": 47
    },
    {
      "epoch": 0.26834381551362685,
      "grad_norm": 0.6821170449256897,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.7976,
      "step": 48
    },
    {
      "epoch": 0.27393431167016075,
      "grad_norm": 0.3082614541053772,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.8181,
      "step": 49
    },
    {
      "epoch": 0.27952480782669464,
      "grad_norm": 0.44825708866119385,
      "learning_rate": 0.0,
      "loss": 1.8796,
      "step": 50
    },
    {
      "epoch": 0.27952480782669464,
      "eval_loss": 1.802408218383789,
      "eval_runtime": 79.7187,
      "eval_samples_per_second": 15.116,
      "eval_steps_per_second": 1.894,
      "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
}