{
  "best_metric": 0.8129812479019165,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0011708916339792752,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.6835665359171006e-05,
      "grad_norm": 0.7221629619598389,
      "learning_rate": 2e-05,
      "loss": 0.876,
      "step": 1
    },
    {
      "epoch": 4.6835665359171006e-05,
      "eval_loss": 1.0366460084915161,
      "eval_runtime": 2844.3805,
      "eval_samples_per_second": 3.161,
      "eval_steps_per_second": 1.58,
      "step": 1
    },
    {
      "epoch": 9.367133071834201e-05,
      "grad_norm": 0.8914138078689575,
      "learning_rate": 4e-05,
      "loss": 0.9882,
      "step": 2
    },
    {
      "epoch": 0.00014050699607751302,
      "grad_norm": 0.9784770607948303,
      "learning_rate": 6e-05,
      "loss": 1.2942,
      "step": 3
    },
    {
      "epoch": 0.00018734266143668403,
      "grad_norm": 0.7786074280738831,
      "learning_rate": 8e-05,
      "loss": 0.9422,
      "step": 4
    },
    {
      "epoch": 0.00023417832679585503,
      "grad_norm": 0.6185960173606873,
      "learning_rate": 0.0001,
      "loss": 0.8609,
      "step": 5
    },
    {
      "epoch": 0.00023417832679585503,
      "eval_loss": 0.9876631498336792,
      "eval_runtime": 2857.2233,
      "eval_samples_per_second": 3.146,
      "eval_steps_per_second": 1.573,
      "step": 5
    },
    {
      "epoch": 0.00028101399215502604,
      "grad_norm": 0.6685774326324463,
      "learning_rate": 0.00012,
      "loss": 0.8235,
      "step": 6
    },
    {
      "epoch": 0.00032784965751419707,
      "grad_norm": 0.6721071004867554,
      "learning_rate": 0.00014,
      "loss": 0.989,
      "step": 7
    },
    {
      "epoch": 0.00037468532287336805,
      "grad_norm": 0.8013759255409241,
      "learning_rate": 0.00016,
      "loss": 0.8728,
      "step": 8
    },
    {
      "epoch": 0.0004215209882325391,
      "grad_norm": 0.6883695721626282,
      "learning_rate": 0.00018,
      "loss": 0.774,
      "step": 9
    },
    {
      "epoch": 0.00046835665359171006,
      "grad_norm": 0.5397657155990601,
      "learning_rate": 0.0002,
      "loss": 0.7173,
      "step": 10
    },
    {
      "epoch": 0.00046835665359171006,
      "eval_loss": 0.8521348237991333,
      "eval_runtime": 2828.8096,
      "eval_samples_per_second": 3.178,
      "eval_steps_per_second": 1.589,
      "step": 10
    },
    {
      "epoch": 0.000515192318950881,
      "grad_norm": 0.6538496017456055,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.8828,
      "step": 11
    },
    {
      "epoch": 0.0005620279843100521,
      "grad_norm": 0.7199555039405823,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.6093,
      "step": 12
    },
    {
      "epoch": 0.0006088636496692231,
      "grad_norm": 0.8212117552757263,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.842,
      "step": 13
    },
    {
      "epoch": 0.0006556993150283941,
      "grad_norm": 0.6258594989776611,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.7928,
      "step": 14
    },
    {
      "epoch": 0.0007025349803875652,
      "grad_norm": 0.8337199687957764,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8851,
      "step": 15
    },
    {
      "epoch": 0.0007025349803875652,
      "eval_loss": 0.8297687768936157,
      "eval_runtime": 2839.0047,
      "eval_samples_per_second": 3.167,
      "eval_steps_per_second": 1.583,
      "step": 15
    },
    {
      "epoch": 0.0007493706457467361,
      "grad_norm": 0.5545913577079773,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.7313,
      "step": 16
    },
    {
      "epoch": 0.0007962063111059071,
      "grad_norm": 0.6206797361373901,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.8542,
      "step": 17
    },
    {
      "epoch": 0.0008430419764650782,
      "grad_norm": 0.6755259037017822,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.8265,
      "step": 18
    },
    {
      "epoch": 0.0008898776418242492,
      "grad_norm": 0.46088144183158875,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6002,
      "step": 19
    },
    {
      "epoch": 0.0009367133071834201,
      "grad_norm": 0.6171578764915466,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.9655,
      "step": 20
    },
    {
      "epoch": 0.0009367133071834201,
      "eval_loss": 0.815974235534668,
      "eval_runtime": 2833.2714,
      "eval_samples_per_second": 3.173,
      "eval_steps_per_second": 1.587,
      "step": 20
    },
    {
      "epoch": 0.0009835489725425913,
      "grad_norm": 0.47180765867233276,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.7465,
      "step": 21
    },
    {
      "epoch": 0.001030384637901762,
      "grad_norm": 0.4130145311355591,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.5707,
      "step": 22
    },
    {
      "epoch": 0.0010772203032609331,
      "grad_norm": 0.730938732624054,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.8911,
      "step": 23
    },
    {
      "epoch": 0.0011240559686201042,
      "grad_norm": 0.5450481176376343,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.7751,
      "step": 24
    },
    {
      "epoch": 0.0011708916339792752,
      "grad_norm": 0.48658469319343567,
      "learning_rate": 0.0,
      "loss": 0.8835,
      "step": 25
    },
    {
      "epoch": 0.0011708916339792752,
      "eval_loss": 0.8129812479019165,
      "eval_runtime": 2839.9874,
      "eval_samples_per_second": 3.166,
      "eval_steps_per_second": 1.583,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 5918605594066944.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}