{
  "best_metric": 0.008380405604839325,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.36363636363636365,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007272727272727273,
      "grad_norm": 5.9078497886657715,
      "learning_rate": 5e-06,
      "loss": 2.1548,
      "step": 1
    },
    {
      "epoch": 0.007272727272727273,
      "eval_loss": 0.6558012962341309,
      "eval_runtime": 14.7162,
      "eval_samples_per_second": 15.765,
      "eval_steps_per_second": 1.971,
      "step": 1
    },
    {
      "epoch": 0.014545454545454545,
      "grad_norm": 7.902283191680908,
      "learning_rate": 1e-05,
      "loss": 2.5623,
      "step": 2
    },
    {
      "epoch": 0.02181818181818182,
      "grad_norm": 7.969634056091309,
      "learning_rate": 1.5e-05,
      "loss": 2.7019,
      "step": 3
    },
    {
      "epoch": 0.02909090909090909,
      "grad_norm": 6.62489128112793,
      "learning_rate": 2e-05,
      "loss": 2.3783,
      "step": 4
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 7.612579822540283,
      "learning_rate": 2.5e-05,
      "loss": 2.3724,
      "step": 5
    },
    {
      "epoch": 0.04363636363636364,
      "grad_norm": 8.370535850524902,
      "learning_rate": 3e-05,
      "loss": 2.1463,
      "step": 6
    },
    {
      "epoch": 0.05090909090909091,
      "grad_norm": 6.560786247253418,
      "learning_rate": 3.5e-05,
      "loss": 1.8776,
      "step": 7
    },
    {
      "epoch": 0.05818181818181818,
      "grad_norm": 5.89080286026001,
      "learning_rate": 4e-05,
      "loss": 1.5091,
      "step": 8
    },
    {
      "epoch": 0.06545454545454546,
      "grad_norm": 3.6321754455566406,
      "learning_rate": 4.5e-05,
      "loss": 1.115,
      "step": 9
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 4.617589950561523,
      "learning_rate": 5e-05,
      "loss": 1.0275,
      "step": 10
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.9518864154815674,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.785,
      "step": 11
    },
    {
      "epoch": 0.08727272727272728,
      "grad_norm": 3.878249406814575,
      "learning_rate": 6e-05,
      "loss": 0.5741,
      "step": 12
    },
    {
      "epoch": 0.09454545454545454,
      "grad_norm": 5.305299758911133,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.5009,
      "step": 13
    },
    {
      "epoch": 0.10181818181818182,
      "grad_norm": 2.926271438598633,
      "learning_rate": 7e-05,
      "loss": 0.298,
      "step": 14
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 2.7366039752960205,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2178,
      "step": 15
    },
    {
      "epoch": 0.11636363636363636,
      "grad_norm": 2.242034673690796,
      "learning_rate": 8e-05,
      "loss": 0.1494,
      "step": 16
    },
    {
      "epoch": 0.12363636363636364,
      "grad_norm": 2.2095048427581787,
      "learning_rate": 8.5e-05,
      "loss": 0.1056,
      "step": 17
    },
    {
      "epoch": 0.13090909090909092,
      "grad_norm": 2.1519293785095215,
      "learning_rate": 9e-05,
      "loss": 0.0771,
      "step": 18
    },
    {
      "epoch": 0.13818181818181818,
      "grad_norm": 2.775590181350708,
      "learning_rate": 9.5e-05,
      "loss": 0.0448,
      "step": 19
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 2.8195669651031494,
      "learning_rate": 0.0001,
      "loss": 0.1262,
      "step": 20
    },
    {
      "epoch": 0.15272727272727274,
      "grad_norm": 3.0878517627716064,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.1248,
      "step": 21
    },
    {
      "epoch": 0.16,
      "grad_norm": 3.8688416481018066,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1375,
      "step": 22
    },
    {
      "epoch": 0.16727272727272727,
      "grad_norm": 6.216594696044922,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1336,
      "step": 23
    },
    {
      "epoch": 0.17454545454545456,
      "grad_norm": 3.8340837955474854,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0731,
      "step": 24
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.728262186050415,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1183,
      "step": 25
    },
    {
      "epoch": 0.18181818181818182,
      "eval_loss": 0.014856944791972637,
      "eval_runtime": 14.9599,
      "eval_samples_per_second": 15.508,
      "eval_steps_per_second": 1.939,
      "step": 25
    },
    {
      "epoch": 0.1890909090909091,
      "grad_norm": 3.340867042541504,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0748,
      "step": 26
    },
    {
      "epoch": 0.19636363636363635,
      "grad_norm": 4.756340980529785,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0569,
      "step": 27
    },
    {
      "epoch": 0.20363636363636364,
      "grad_norm": 2.0056493282318115,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0392,
      "step": 28
    },
    {
      "epoch": 0.2109090909090909,
      "grad_norm": 1.7935372591018677,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0728,
      "step": 29
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 3.992663860321045,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0897,
      "step": 30
    },
    {
      "epoch": 0.22545454545454546,
      "grad_norm": 2.0212645530700684,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0439,
      "step": 31
    },
    {
      "epoch": 0.23272727272727273,
      "grad_norm": 1.1357940435409546,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0609,
      "step": 32
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.6464401483535767,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0382,
      "step": 33
    },
    {
      "epoch": 0.24727272727272728,
      "grad_norm": 1.2237344980239868,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0718,
      "step": 34
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 2.4357638359069824,
      "learning_rate": 5e-05,
      "loss": 0.0566,
      "step": 35
    },
    {
      "epoch": 0.26181818181818184,
      "grad_norm": 1.897200584411621,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.1047,
      "step": 36
    },
    {
      "epoch": 0.2690909090909091,
      "grad_norm": 1.4117827415466309,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0423,
      "step": 37
    },
    {
      "epoch": 0.27636363636363637,
      "grad_norm": 1.0462509393692017,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.04,
      "step": 38
    },
    {
      "epoch": 0.28363636363636363,
      "grad_norm": 1.4082738161087036,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0524,
      "step": 39
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 1.5846432447433472,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0752,
      "step": 40
    },
    {
      "epoch": 0.29818181818181816,
      "grad_norm": 2.12044095993042,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0367,
      "step": 41
    },
    {
      "epoch": 0.3054545454545455,
      "grad_norm": 0.6483519077301025,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0364,
      "step": 42
    },
    {
      "epoch": 0.31272727272727274,
      "grad_norm": 0.7130972146987915,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0174,
      "step": 43
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.9654887318611145,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0556,
      "step": 44
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 2.261229991912842,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0579,
      "step": 45
    },
    {
      "epoch": 0.33454545454545453,
      "grad_norm": 1.1127955913543701,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0171,
      "step": 46
    },
    {
      "epoch": 0.3418181818181818,
      "grad_norm": 0.7904780507087708,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0358,
      "step": 47
    },
    {
      "epoch": 0.3490909090909091,
      "grad_norm": 1.2277880907058716,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0484,
      "step": 48
    },
    {
      "epoch": 0.3563636363636364,
      "grad_norm": 0.925501823425293,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.013,
      "step": 49
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.3169645071029663,
      "learning_rate": 0.0,
      "loss": 0.0447,
      "step": 50
    },
    {
      "epoch": 0.36363636363636365,
      "eval_loss": 0.008380405604839325,
      "eval_runtime": 14.9451,
      "eval_samples_per_second": 15.523,
      "eval_steps_per_second": 1.94,
      "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": 6.65247887130624e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}