{
  "best_metric": 1.720038652420044,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.024017467248908,
  "eval_steps": 25,
  "global_step": 43,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06986899563318777,
      "grad_norm": 7.252934455871582,
      "learning_rate": 5e-05,
      "loss": 4.6181,
      "step": 1
    },
    {
      "epoch": 0.06986899563318777,
      "eval_loss": 9.674843788146973,
      "eval_runtime": 3.2767,
      "eval_samples_per_second": 15.259,
      "eval_steps_per_second": 3.967,
      "step": 1
    },
    {
      "epoch": 0.13973799126637554,
      "grad_norm": 15.196834564208984,
      "learning_rate": 0.0001,
      "loss": 7.5007,
      "step": 2
    },
    {
      "epoch": 0.2096069868995633,
      "grad_norm": 22.981645584106445,
      "learning_rate": 9.986796105326832e-05,
      "loss": 10.3302,
      "step": 3
    },
    {
      "epoch": 0.2794759825327511,
      "grad_norm": 8.001959800720215,
      "learning_rate": 9.947261907011569e-05,
      "loss": 4.0802,
      "step": 4
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 11.598747253417969,
      "learning_rate": 9.881629407450006e-05,
      "loss": 4.1733,
      "step": 5
    },
    {
      "epoch": 0.4192139737991266,
      "grad_norm": 25.42584991455078,
      "learning_rate": 9.790283764247188e-05,
      "loss": 5.0721,
      "step": 6
    },
    {
      "epoch": 0.4890829694323144,
      "grad_norm": 49.51744079589844,
      "learning_rate": 9.673761029959427e-05,
      "loss": 6.0229,
      "step": 7
    },
    {
      "epoch": 0.5589519650655022,
      "grad_norm": 8.035906791687012,
      "learning_rate": 9.53274500632475e-05,
      "loss": 2.3775,
      "step": 8
    },
    {
      "epoch": 0.62882096069869,
      "grad_norm": 3.325791358947754,
      "learning_rate": 9.368063231442406e-05,
      "loss": 2.2398,
      "step": 9
    },
    {
      "epoch": 0.6986899563318777,
      "grad_norm": 2.332188367843628,
      "learning_rate": 9.18068212345023e-05,
      "loss": 2.222,
      "step": 10
    },
    {
      "epoch": 0.7685589519650655,
      "grad_norm": 6.436346054077148,
      "learning_rate": 8.971701309198744e-05,
      "loss": 2.037,
      "step": 11
    },
    {
      "epoch": 0.8384279475982532,
      "grad_norm": 4.404402732849121,
      "learning_rate": 8.742347171203542e-05,
      "loss": 2.0669,
      "step": 12
    },
    {
      "epoch": 0.9082969432314411,
      "grad_norm": 6.946753025054932,
      "learning_rate": 8.493965650745043e-05,
      "loss": 2.1317,
      "step": 13
    },
    {
      "epoch": 0.9781659388646288,
      "grad_norm": 10.7241849899292,
      "learning_rate": 8.228014349349872e-05,
      "loss": 2.2125,
      "step": 14
    },
    {
      "epoch": 1.054585152838428,
      "grad_norm": 4.120997428894043,
      "learning_rate": 7.946053975005496e-05,
      "loss": 3.4602,
      "step": 15
    },
    {
      "epoch": 1.1244541484716157,
      "grad_norm": 2.569685459136963,
      "learning_rate": 7.649739183305184e-05,
      "loss": 1.8468,
      "step": 16
    },
    {
      "epoch": 1.1943231441048034,
      "grad_norm": 2.034120798110962,
      "learning_rate": 7.34080886727103e-05,
      "loss": 1.8211,
      "step": 17
    },
    {
      "epoch": 1.2641921397379914,
      "grad_norm": 2.2087416648864746,
      "learning_rate": 7.021075952838262e-05,
      "loss": 1.6219,
      "step": 18
    },
    {
      "epoch": 1.334061135371179,
      "grad_norm": 2.031977891921997,
      "learning_rate": 6.692416759884978e-05,
      "loss": 1.9057,
      "step": 19
    },
    {
      "epoch": 1.4039301310043668,
      "grad_norm": 1.8749696016311646,
      "learning_rate": 6.356759991241008e-05,
      "loss": 1.7426,
      "step": 20
    },
    {
      "epoch": 1.4737991266375545,
      "grad_norm": 2.725235939025879,
      "learning_rate": 6.016075414292803e-05,
      "loss": 1.9118,
      "step": 21
    },
    {
      "epoch": 1.5436681222707422,
      "grad_norm": 1.8467425107955933,
      "learning_rate": 5.6723623016051596e-05,
      "loss": 1.6104,
      "step": 22
    },
    {
      "epoch": 1.6135371179039302,
      "grad_norm": 1.3791073560714722,
      "learning_rate": 5.3276376983948415e-05,
      "loss": 1.6028,
      "step": 23
    },
    {
      "epoch": 1.6834061135371179,
      "grad_norm": 2.391037940979004,
      "learning_rate": 4.9839245857071994e-05,
      "loss": 1.6691,
      "step": 24
    },
    {
      "epoch": 1.7532751091703056,
      "grad_norm": 1.2627737522125244,
      "learning_rate": 4.643240008758992e-05,
      "loss": 1.4168,
      "step": 25
    },
    {
      "epoch": 1.7532751091703056,
      "eval_loss": 1.720038652420044,
      "eval_runtime": 3.1999,
      "eval_samples_per_second": 15.625,
      "eval_steps_per_second": 4.063,
      "step": 25
    },
    {
      "epoch": 1.8231441048034935,
      "grad_norm": 1.7683324813842773,
      "learning_rate": 4.307583240115024e-05,
      "loss": 1.8031,
      "step": 26
    },
    {
      "epoch": 1.8930131004366813,
      "grad_norm": 1.5601824522018433,
      "learning_rate": 3.9789240471617385e-05,
      "loss": 1.6297,
      "step": 27
    },
    {
      "epoch": 1.962882096069869,
      "grad_norm": 2.1221816539764404,
      "learning_rate": 3.659191132728971e-05,
      "loss": 1.7874,
      "step": 28
    },
    {
      "epoch": 2.039301310043668,
      "grad_norm": 2.4992384910583496,
      "learning_rate": 3.350260816694816e-05,
      "loss": 2.8092,
      "step": 29
    },
    {
      "epoch": 2.109170305676856,
      "grad_norm": 1.075144648551941,
      "learning_rate": 3.0539460249945056e-05,
      "loss": 1.371,
      "step": 30
    },
    {
      "epoch": 2.1790393013100435,
      "grad_norm": 1.4480336904525757,
      "learning_rate": 2.7719856506501306e-05,
      "loss": 1.4821,
      "step": 31
    },
    {
      "epoch": 2.2489082969432315,
      "grad_norm": 0.9556394815444946,
      "learning_rate": 2.5060343492549566e-05,
      "loss": 0.9686,
      "step": 32
    },
    {
      "epoch": 2.3187772925764194,
      "grad_norm": 1.2648524045944214,
      "learning_rate": 2.257652828796459e-05,
      "loss": 2.0128,
      "step": 33
    },
    {
      "epoch": 2.388646288209607,
      "grad_norm": 1.1361418962478638,
      "learning_rate": 2.0282986908012567e-05,
      "loss": 1.3708,
      "step": 34
    },
    {
      "epoch": 2.458515283842795,
      "grad_norm": 2.031010627746582,
      "learning_rate": 1.819317876549771e-05,
      "loss": 1.5572,
      "step": 35
    },
    {
      "epoch": 2.5283842794759828,
      "grad_norm": 1.5639622211456299,
      "learning_rate": 1.631936768557596e-05,
      "loss": 1.4997,
      "step": 36
    },
    {
      "epoch": 2.5982532751091703,
      "grad_norm": 0.8983284831047058,
      "learning_rate": 1.4672549936752506e-05,
      "loss": 1.3531,
      "step": 37
    },
    {
      "epoch": 2.668122270742358,
      "grad_norm": 1.3355714082717896,
      "learning_rate": 1.3262389700405744e-05,
      "loss": 1.3925,
      "step": 38
    },
    {
      "epoch": 2.7379912663755457,
      "grad_norm": 1.021559476852417,
      "learning_rate": 1.2097162357528127e-05,
      "loss": 0.8967,
      "step": 39
    },
    {
      "epoch": 2.8078602620087336,
      "grad_norm": 1.4824175834655762,
      "learning_rate": 1.1183705925499948e-05,
      "loss": 1.9967,
      "step": 40
    },
    {
      "epoch": 2.8777292576419216,
      "grad_norm": 1.0364881753921509,
      "learning_rate": 1.0527380929884324e-05,
      "loss": 1.4141,
      "step": 41
    },
    {
      "epoch": 2.947598253275109,
      "grad_norm": 1.6417279243469238,
      "learning_rate": 1.013203894673168e-05,
      "loss": 1.4857,
      "step": 42
    },
    {
      "epoch": 3.024017467248908,
      "grad_norm": 2.14969801902771,
      "learning_rate": 1e-05,
      "loss": 2.6031,
      "step": 43
    }
  ],
  "logging_steps": 1,
  "max_steps": 43,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 5.3100522362424525e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}