{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.0383838383838384,
  "eval_steps": 25,
  "global_step": 47,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06464646464646465,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.06464646464646465,
      "eval_loss": NaN,
      "eval_runtime": 3.0904,
      "eval_samples_per_second": 16.179,
      "eval_steps_per_second": 4.207,
      "step": 1
    },
    {
      "epoch": 0.1292929292929293,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.19393939393939394,
      "grad_norm": NaN,
      "learning_rate": 9.989038226169209e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.2585858585858586,
      "grad_norm": NaN,
      "learning_rate": 9.956206309337068e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": NaN,
      "learning_rate": 9.901664203302126e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": NaN,
      "learning_rate": 9.825677631722435e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.45252525252525255,
      "grad_norm": NaN,
      "learning_rate": 9.728616793536588e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.5171717171717172,
      "grad_norm": NaN,
      "learning_rate": 9.610954559391703e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": NaN,
      "learning_rate": 9.473264167865173e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": NaN,
      "learning_rate": 9.316216432703917e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": NaN,
      "learning_rate": 8.947199994035401e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.8404040404040404,
      "grad_norm": NaN,
      "learning_rate": 8.73702910152393e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.9050505050505051,
      "grad_norm": NaN,
      "learning_rate": 8.511087728614862e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": NaN,
      "learning_rate": 8.270476638965462e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.0343434343434343,
      "grad_norm": NaN,
      "learning_rate": 8.016368065618361e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.098989898989899,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.1636363636363636,
      "grad_norm": NaN,
      "learning_rate": 7.472670160550849e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.2282828282828282,
      "grad_norm": NaN,
      "learning_rate": 7.185729670371605e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.2929292929292928,
      "grad_norm": NaN,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.3575757575757577,
      "grad_norm": NaN,
      "learning_rate": 6.588648530198504e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": NaN,
      "learning_rate": 6.281416799501188e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.486868686868687,
      "grad_norm": NaN,
      "learning_rate": 5.970378084704441e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.5515151515151515,
      "grad_norm": NaN,
      "learning_rate": 5.657047735161256e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.6161616161616161,
      "grad_norm": NaN,
      "learning_rate": 5.342952264838747e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.6161616161616161,
      "eval_loss": NaN,
      "eval_runtime": 3.0755,
      "eval_samples_per_second": 16.258,
      "eval_steps_per_second": 4.227,
      "step": 25
    },
    {
      "epoch": 1.680808080808081,
      "grad_norm": NaN,
      "learning_rate": 5.0296219152955604e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 1.7454545454545456,
      "grad_norm": NaN,
      "learning_rate": 4.718583200498814e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 1.8101010101010102,
      "grad_norm": NaN,
      "learning_rate": 4.411351469801496e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 1.8747474747474748,
      "grad_norm": NaN,
      "learning_rate": 4.109423525312738e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": NaN,
      "learning_rate": 3.814270329628396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 2.004040404040404,
      "grad_norm": NaN,
      "learning_rate": 3.5273298394491515e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 2.0686868686868687,
      "grad_norm": NaN,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": NaN,
      "learning_rate": 2.98363193438164e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 2.197979797979798,
      "grad_norm": NaN,
      "learning_rate": 2.729523361034538e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 2.2626262626262625,
      "grad_norm": NaN,
      "learning_rate": 2.4889122713851394e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 2.327272727272727,
      "grad_norm": NaN,
      "learning_rate": 2.2629708984760708e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 2.391919191919192,
      "grad_norm": NaN,
      "learning_rate": 2.0528000059645997e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 2.4565656565656564,
      "grad_norm": NaN,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 2.5212121212121215,
      "grad_norm": NaN,
      "learning_rate": 1.6837835672960835e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 2.5858585858585856,
      "grad_norm": NaN,
      "learning_rate": 1.526735832134829e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 2.6505050505050507,
      "grad_norm": NaN,
      "learning_rate": 1.389045440608296e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 2.7151515151515153,
      "grad_norm": NaN,
      "learning_rate": 1.2713832064634126e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 2.77979797979798,
      "grad_norm": NaN,
      "learning_rate": 1.174322368277565e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 2.8444444444444446,
      "grad_norm": NaN,
      "learning_rate": 1.0983357966978745e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": NaN,
      "learning_rate": 1.0437936906629336e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 2.973737373737374,
      "grad_norm": NaN,
      "learning_rate": 1.0109617738307912e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 3.0383838383838384,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 47
    }
  ],
  "logging_steps": 1,
  "max_steps": 47,
  "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": 2.796085766604718e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}