{
  "best_metric": 0.4884698987007141,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.7905138339920948,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03162055335968379,
      "grad_norm": 11.872172355651855,
      "learning_rate": 5e-05,
      "loss": 12.4387,
      "step": 1
    },
    {
      "epoch": 0.03162055335968379,
      "eval_loss": 13.357632637023926,
      "eval_runtime": 14.4094,
      "eval_samples_per_second": 14.782,
      "eval_steps_per_second": 1.874,
      "step": 1
    },
    {
      "epoch": 0.06324110671936758,
      "grad_norm": 11.944364547729492,
      "learning_rate": 0.0001,
      "loss": 12.507,
      "step": 2
    },
    {
      "epoch": 0.09486166007905138,
      "grad_norm": 12.8162202835083,
      "learning_rate": 9.989294616193017e-05,
      "loss": 12.1593,
      "step": 3
    },
    {
      "epoch": 0.12648221343873517,
      "grad_norm": 16.479677200317383,
      "learning_rate": 9.957224306869053e-05,
      "loss": 9.4681,
      "step": 4
    },
    {
      "epoch": 0.15810276679841898,
      "grad_norm": 18.85612678527832,
      "learning_rate": 9.903926402016153e-05,
      "loss": 5.9714,
      "step": 5
    },
    {
      "epoch": 0.18972332015810275,
      "grad_norm": 13.984392166137695,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.9941,
      "step": 6
    },
    {
      "epoch": 0.22134387351778656,
      "grad_norm": 12.14105224609375,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.6446,
      "step": 7
    },
    {
      "epoch": 0.25296442687747034,
      "grad_norm": 9.039938926696777,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.864,
      "step": 8
    },
    {
      "epoch": 0.2845849802371542,
      "grad_norm": 27.8907413482666,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.5257,
      "step": 9
    },
    {
      "epoch": 0.31620553359683795,
      "grad_norm": 19.8009033203125,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9778,
      "step": 10
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 7.286177158355713,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.6243,
      "step": 11
    },
    {
      "epoch": 0.3794466403162055,
      "grad_norm": 6.214678764343262,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5454,
      "step": 12
    },
    {
      "epoch": 0.41106719367588934,
      "grad_norm": 6.982287883758545,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.5268,
      "step": 13
    },
    {
      "epoch": 0.4426877470355731,
      "grad_norm": 3.287309169769287,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.446,
      "step": 14
    },
    {
      "epoch": 0.4743083003952569,
      "grad_norm": 3.5173118114471436,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.3369,
      "step": 15
    },
    {
      "epoch": 0.5059288537549407,
      "grad_norm": 4.333190441131592,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.4597,
      "step": 16
    },
    {
      "epoch": 0.5375494071146245,
      "grad_norm": 3.6946616172790527,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.4796,
      "step": 17
    },
    {
      "epoch": 0.5691699604743083,
      "grad_norm": 8.35791301727295,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5804,
      "step": 18
    },
    {
      "epoch": 0.6007905138339921,
      "grad_norm": 7.611564636230469,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.5395,
      "step": 19
    },
    {
      "epoch": 0.6324110671936759,
      "grad_norm": 3.933959484100342,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.4075,
      "step": 20
    },
    {
      "epoch": 0.6640316205533597,
      "grad_norm": 4.536863327026367,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.4579,
      "step": 21
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 3.593409538269043,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.3821,
      "step": 22
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.9236183166503906,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.3274,
      "step": 23
    },
    {
      "epoch": 0.758893280632411,
      "grad_norm": 2.631983518600464,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.4191,
      "step": 24
    },
    {
      "epoch": 0.7905138339920948,
      "grad_norm": 3.7012534141540527,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.4676,
      "step": 25
    },
    {
      "epoch": 0.7905138339920948,
      "eval_loss": 0.4884698987007141,
      "eval_runtime": 14.4016,
      "eval_samples_per_second": 14.79,
      "eval_steps_per_second": 1.875,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.984041808658432e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}