{
  "best_metric": 0.06262260675430298,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.10077519379845,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12403100775193798,
      "grad_norm": 17.95539093017578,
      "learning_rate": 5e-05,
      "loss": 8.7922,
      "step": 1
    },
    {
      "epoch": 0.12403100775193798,
      "eval_loss": 10.018525123596191,
      "eval_runtime": 3.316,
      "eval_samples_per_second": 15.078,
      "eval_steps_per_second": 3.92,
      "step": 1
    },
    {
      "epoch": 0.24806201550387597,
      "grad_norm": 24.31969451904297,
      "learning_rate": 0.0001,
      "loss": 10.214,
      "step": 2
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 15.721542358398438,
      "learning_rate": 9.958086757163489e-05,
      "loss": 7.0541,
      "step": 3
    },
    {
      "epoch": 0.49612403100775193,
      "grad_norm": 18.70537567138672,
      "learning_rate": 9.833127793065098e-05,
      "loss": 3.6346,
      "step": 4
    },
    {
      "epoch": 0.6201550387596899,
      "grad_norm": 15.574380874633789,
      "learning_rate": 9.627450856774539e-05,
      "loss": 1.5274,
      "step": 5
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 19.581275939941406,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.952,
      "step": 6
    },
    {
      "epoch": 0.8682170542635659,
      "grad_norm": 7.610567092895508,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.6147,
      "step": 7
    },
    {
      "epoch": 0.9922480620155039,
      "grad_norm": 9.733624458312988,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.5275,
      "step": 8
    },
    {
      "epoch": 1.1162790697674418,
      "grad_norm": 11.229278564453125,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.8541,
      "step": 9
    },
    {
      "epoch": 1.2403100775193798,
      "grad_norm": 3.612816095352173,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.4081,
      "step": 10
    },
    {
      "epoch": 1.3643410852713178,
      "grad_norm": 3.192284107208252,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.3498,
      "step": 11
    },
    {
      "epoch": 1.4883720930232558,
      "grad_norm": 4.103220462799072,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.3952,
      "step": 12
    },
    {
      "epoch": 1.6124031007751938,
      "grad_norm": 1.8152902126312256,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.2829,
      "step": 13
    },
    {
      "epoch": 1.7364341085271318,
      "grad_norm": 3.1709251403808594,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.3134,
      "step": 14
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 1.8685613870620728,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.2375,
      "step": 15
    },
    {
      "epoch": 1.9844961240310077,
      "grad_norm": 3.034189224243164,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.2409,
      "step": 16
    },
    {
      "epoch": 2.108527131782946,
      "grad_norm": 4.653195858001709,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.3418,
      "step": 17
    },
    {
      "epoch": 2.2325581395348837,
      "grad_norm": 1.6827412843704224,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.1981,
      "step": 18
    },
    {
      "epoch": 2.356589147286822,
      "grad_norm": 1.9079591035842896,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.1454,
      "step": 19
    },
    {
      "epoch": 2.4806201550387597,
      "grad_norm": 1.6528128385543823,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.1295,
      "step": 20
    },
    {
      "epoch": 2.604651162790698,
      "grad_norm": 1.2485013008117676,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.1171,
      "step": 21
    },
    {
      "epoch": 2.7286821705426356,
      "grad_norm": 1.5870386362075806,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.0988,
      "step": 22
    },
    {
      "epoch": 2.8527131782945734,
      "grad_norm": 1.9483548402786255,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.111,
      "step": 23
    },
    {
      "epoch": 2.9767441860465116,
      "grad_norm": 2.1530604362487793,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.0986,
      "step": 24
    },
    {
      "epoch": 3.10077519379845,
      "grad_norm": 3.1103856563568115,
      "learning_rate": 1e-05,
      "loss": 0.1425,
      "step": 25
    },
    {
      "epoch": 3.10077519379845,
      "eval_loss": 0.06262260675430298,
      "eval_runtime": 3.3969,
      "eval_samples_per_second": 14.719,
      "eval_steps_per_second": 3.827,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "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": 3.315690861756416e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}