{
  "best_metric": 1.8321987390518188,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.0432432432432432,
  "eval_steps": 25,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08648648648648649,
      "grad_norm": 13.138847351074219,
      "learning_rate": 5e-05,
      "loss": 32.0769,
      "step": 1
    },
    {
      "epoch": 0.08648648648648649,
      "eval_loss": 1.941705584526062,
      "eval_runtime": 4.771,
      "eval_samples_per_second": 16.349,
      "eval_steps_per_second": 2.096,
      "step": 1
    },
    {
      "epoch": 0.17297297297297298,
      "grad_norm": 13.951818466186523,
      "learning_rate": 0.0001,
      "loss": 31.5154,
      "step": 2
    },
    {
      "epoch": 0.2594594594594595,
      "grad_norm": 8.283455848693848,
      "learning_rate": 9.977359612865423e-05,
      "loss": 32.4068,
      "step": 3
    },
    {
      "epoch": 0.34594594594594597,
      "grad_norm": 15.601115226745605,
      "learning_rate": 9.909643486313533e-05,
      "loss": 31.3009,
      "step": 4
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 11.00848388671875,
      "learning_rate": 9.797464868072488e-05,
      "loss": 30.5228,
      "step": 5
    },
    {
      "epoch": 0.518918918918919,
      "grad_norm": 5.229431629180908,
      "learning_rate": 9.641839665080363e-05,
      "loss": 30.6521,
      "step": 6
    },
    {
      "epoch": 0.6054054054054054,
      "grad_norm": 4.670675754547119,
      "learning_rate": 9.444177243274618e-05,
      "loss": 30.4653,
      "step": 7
    },
    {
      "epoch": 0.6918918918918919,
      "grad_norm": 4.181548118591309,
      "learning_rate": 9.206267664155907e-05,
      "loss": 29.8145,
      "step": 8
    },
    {
      "epoch": 0.7783783783783784,
      "grad_norm": 3.289199113845825,
      "learning_rate": 8.930265473713938e-05,
      "loss": 30.8407,
      "step": 9
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 3.4983394145965576,
      "learning_rate": 8.618670190525352e-05,
      "loss": 30.9321,
      "step": 10
    },
    {
      "epoch": 0.9513513513513514,
      "grad_norm": 4.764837265014648,
      "learning_rate": 8.274303669726426e-05,
      "loss": 30.8902,
      "step": 11
    },
    {
      "epoch": 1.0432432432432432,
      "grad_norm": 2.7808339595794678,
      "learning_rate": 7.900284547855991e-05,
      "loss": 29.4438,
      "step": 12
    },
    {
      "epoch": 1.1297297297297297,
      "grad_norm": 2.721719264984131,
      "learning_rate": 7.500000000000001e-05,
      "loss": 29.93,
      "step": 13
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 3.323044776916504,
      "learning_rate": 7.077075065009433e-05,
      "loss": 28.8181,
      "step": 14
    },
    {
      "epoch": 1.3027027027027027,
      "grad_norm": 2.9210305213928223,
      "learning_rate": 6.635339816587109e-05,
      "loss": 30.0156,
      "step": 15
    },
    {
      "epoch": 1.3891891891891892,
      "grad_norm": 2.4984383583068848,
      "learning_rate": 6.178794677547137e-05,
      "loss": 29.8112,
      "step": 16
    },
    {
      "epoch": 1.4756756756756757,
      "grad_norm": 3.663684129714966,
      "learning_rate": 5.7115741913664264e-05,
      "loss": 28.6436,
      "step": 17
    },
    {
      "epoch": 1.5621621621621622,
      "grad_norm": 2.6698148250579834,
      "learning_rate": 5.2379095791187124e-05,
      "loss": 30.2336,
      "step": 18
    },
    {
      "epoch": 1.6486486486486487,
      "grad_norm": 2.9213438034057617,
      "learning_rate": 4.762090420881289e-05,
      "loss": 29.4472,
      "step": 19
    },
    {
      "epoch": 1.7351351351351352,
      "grad_norm": 3.6099703311920166,
      "learning_rate": 4.288425808633575e-05,
      "loss": 29.1332,
      "step": 20
    },
    {
      "epoch": 1.8216216216216217,
      "grad_norm": 2.4624807834625244,
      "learning_rate": 3.821205322452863e-05,
      "loss": 30.2577,
      "step": 21
    },
    {
      "epoch": 1.9081081081081082,
      "grad_norm": 2.677868127822876,
      "learning_rate": 3.364660183412892e-05,
      "loss": 29.3551,
      "step": 22
    },
    {
      "epoch": 1.9945945945945946,
      "grad_norm": 3.205655574798584,
      "learning_rate": 2.9229249349905684e-05,
      "loss": 29.9678,
      "step": 23
    },
    {
      "epoch": 2.0864864864864865,
      "grad_norm": 2.382532835006714,
      "learning_rate": 2.500000000000001e-05,
      "loss": 29.9985,
      "step": 24
    },
    {
      "epoch": 2.172972972972973,
      "grad_norm": 2.4374914169311523,
      "learning_rate": 2.09971545214401e-05,
      "loss": 29.3895,
      "step": 25
    },
    {
      "epoch": 2.172972972972973,
      "eval_loss": 1.8321987390518188,
      "eval_runtime": 5.0477,
      "eval_samples_per_second": 15.453,
      "eval_steps_per_second": 1.981,
      "step": 25
    },
    {
      "epoch": 2.2594594594594595,
      "grad_norm": 3.1819040775299072,
      "learning_rate": 1.725696330273575e-05,
      "loss": 28.4675,
      "step": 26
    },
    {
      "epoch": 2.345945945945946,
      "grad_norm": 2.3536086082458496,
      "learning_rate": 1.3813298094746491e-05,
      "loss": 29.8276,
      "step": 27
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 2.923321008682251,
      "learning_rate": 1.0697345262860636e-05,
      "loss": 28.0126,
      "step": 28
    },
    {
      "epoch": 2.518918918918919,
      "grad_norm": 3.1668083667755127,
      "learning_rate": 7.937323358440935e-06,
      "loss": 29.3021,
      "step": 29
    },
    {
      "epoch": 2.6054054054054054,
      "grad_norm": 2.4113199710845947,
      "learning_rate": 5.558227567253832e-06,
      "loss": 29.5839,
      "step": 30
    },
    {
      "epoch": 2.691891891891892,
      "grad_norm": 3.0063042640686035,
      "learning_rate": 3.581603349196372e-06,
      "loss": 29.1112,
      "step": 31
    },
    {
      "epoch": 2.7783783783783784,
      "grad_norm": 2.736527919769287,
      "learning_rate": 2.0253513192751373e-06,
      "loss": 28.905,
      "step": 32
    },
    {
      "epoch": 2.864864864864865,
      "grad_norm": 2.431605577468872,
      "learning_rate": 9.035651368646648e-07,
      "loss": 28.684,
      "step": 33
    },
    {
      "epoch": 2.9513513513513514,
      "grad_norm": 3.4076993465423584,
      "learning_rate": 2.2640387134577058e-07,
      "loss": 28.1141,
      "step": 34
    },
    {
      "epoch": 3.0432432432432432,
      "grad_norm": 2.473551034927368,
      "learning_rate": 0.0,
      "loss": 29.3945,
      "step": 35
    }
  ],
  "logging_steps": 1,
  "max_steps": 35,
  "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": 5.774718047847711e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}