{
  "best_metric": 0.4249492883682251,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.04515182300485382,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018060729201941528,
      "grad_norm": 1.1679450273513794,
      "learning_rate": 5e-05,
      "loss": 0.6004,
      "step": 1
    },
    {
      "epoch": 0.0018060729201941528,
      "eval_loss": 0.8847251534461975,
      "eval_runtime": 90.5294,
      "eval_samples_per_second": 41.202,
      "eval_steps_per_second": 5.159,
      "step": 1
    },
    {
      "epoch": 0.0036121458403883056,
      "grad_norm": 1.3293408155441284,
      "learning_rate": 0.0001,
      "loss": 0.7309,
      "step": 2
    },
    {
      "epoch": 0.005418218760582459,
      "grad_norm": 1.1348483562469482,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.7001,
      "step": 3
    },
    {
      "epoch": 0.007224291680776611,
      "grad_norm": 0.891630232334137,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.654,
      "step": 4
    },
    {
      "epoch": 0.009030364600970764,
      "grad_norm": 0.6690797805786133,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.5954,
      "step": 5
    },
    {
      "epoch": 0.010836437521164918,
      "grad_norm": 0.7938116788864136,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.4948,
      "step": 6
    },
    {
      "epoch": 0.01264251044135907,
      "grad_norm": 0.51275235414505,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.549,
      "step": 7
    },
    {
      "epoch": 0.014448583361553222,
      "grad_norm": 0.5153568983078003,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5082,
      "step": 8
    },
    {
      "epoch": 0.016254656281747375,
      "grad_norm": 0.4821842610836029,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.5415,
      "step": 9
    },
    {
      "epoch": 0.018060729201941527,
      "grad_norm": 0.47277501225471497,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5302,
      "step": 10
    },
    {
      "epoch": 0.019866802122135683,
      "grad_norm": 0.46804219484329224,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.559,
      "step": 11
    },
    {
      "epoch": 0.021672875042329835,
      "grad_norm": 0.5385531187057495,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5089,
      "step": 12
    },
    {
      "epoch": 0.023478947962523988,
      "grad_norm": 0.31599441170692444,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.3866,
      "step": 13
    },
    {
      "epoch": 0.02528502088271814,
      "grad_norm": 0.31341472268104553,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.4071,
      "step": 14
    },
    {
      "epoch": 0.027091093802912292,
      "grad_norm": 0.3027861714363098,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.4013,
      "step": 15
    },
    {
      "epoch": 0.028897166723106445,
      "grad_norm": 0.32209834456443787,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.4672,
      "step": 16
    },
    {
      "epoch": 0.030703239643300597,
      "grad_norm": 0.35165438055992126,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.4605,
      "step": 17
    },
    {
      "epoch": 0.03250931256349475,
      "grad_norm": 0.3231716454029083,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.431,
      "step": 18
    },
    {
      "epoch": 0.034315385483688905,
      "grad_norm": 0.28098562359809875,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.4488,
      "step": 19
    },
    {
      "epoch": 0.036121458403883054,
      "grad_norm": 0.29532745480537415,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.4626,
      "step": 20
    },
    {
      "epoch": 0.03792753132407721,
      "grad_norm": 0.3408537805080414,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.487,
      "step": 21
    },
    {
      "epoch": 0.039733604244271366,
      "grad_norm": 0.33273807168006897,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.444,
      "step": 22
    },
    {
      "epoch": 0.041539677164465515,
      "grad_norm": 0.34283336997032166,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.4601,
      "step": 23
    },
    {
      "epoch": 0.04334575008465967,
      "grad_norm": 0.3913612365722656,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.5043,
      "step": 24
    },
    {
      "epoch": 0.04515182300485382,
      "grad_norm": 0.4402361810207367,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.4355,
      "step": 25
    },
    {
      "epoch": 0.04515182300485382,
      "eval_loss": 0.4249492883682251,
      "eval_runtime": 90.4536,
      "eval_samples_per_second": 41.237,
      "eval_steps_per_second": 5.163,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.952285976808653e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}