{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.12521521364845828,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025043042729691657,
      "grad_norm": NaN,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0025043042729691657,
      "eval_loss": NaN,
      "eval_runtime": 1.5072,
      "eval_samples_per_second": 33.175,
      "eval_steps_per_second": 8.625,
      "step": 1
    },
    {
      "epoch": 0.005008608545938331,
      "grad_norm": NaN,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.007512912818907497,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.010017217091876663,
      "grad_norm": NaN,
      "learning_rate": 9.99571699711836e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.01252152136484583,
      "grad_norm": NaN,
      "learning_rate": 9.982876141412856e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.015025825637814995,
      "grad_norm": NaN,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.017530129910784162,
      "grad_norm": NaN,
      "learning_rate": 9.931634888554937e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.020034434183753325,
      "grad_norm": NaN,
      "learning_rate": 9.893332032039701e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.022538738456722492,
      "grad_norm": NaN,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.02504304272969166,
      "grad_norm": NaN,
      "learning_rate": 9.791726278367022e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.027547347002660823,
      "grad_norm": NaN,
      "learning_rate": 9.728616793536588e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.03005165127562999,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.03255595554859916,
      "grad_norm": NaN,
      "learning_rate": 9.578385041664925e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.035060259821568324,
      "grad_norm": NaN,
      "learning_rate": 9.491548749301997e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.037564564094537484,
      "grad_norm": NaN,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.04006886836750665,
      "grad_norm": NaN,
      "learning_rate": 9.295261506157986e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.04257317264047582,
      "grad_norm": NaN,
      "learning_rate": 9.186184199300464e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.045077476913444985,
      "grad_norm": NaN,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.04758178118641415,
      "grad_norm": NaN,
      "learning_rate": 8.947199994035401e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.05008608545938332,
      "grad_norm": NaN,
      "learning_rate": 8.817748015645558e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.05259038973235248,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.055094694005321646,
      "grad_norm": NaN,
      "learning_rate": 8.540155934270471e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.05759899827829081,
      "grad_norm": NaN,
      "learning_rate": 8.392544243589427e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.06010330255125998,
      "grad_norm": NaN,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.06260760682422914,
      "grad_norm": NaN,
      "learning_rate": 8.081093963579707e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.06260760682422914,
      "eval_loss": NaN,
      "eval_runtime": 1.4453,
      "eval_samples_per_second": 34.596,
      "eval_steps_per_second": 8.995,
      "step": 25
    },
    {
      "epoch": 0.06511191109719831,
      "grad_norm": NaN,
      "learning_rate": 7.917848237560709e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.06761621537016747,
      "grad_norm": NaN,
      "learning_rate": 7.75e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.07012051964313665,
      "grad_norm": NaN,
      "learning_rate": 7.577868759557654e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.07262482391610581,
      "grad_norm": NaN,
      "learning_rate": 7.401782177833148e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.07512912818907497,
      "grad_norm": NaN,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.07763343246204414,
      "grad_norm": NaN,
      "learning_rate": 7.03909064496551e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.0801377367350133,
      "grad_norm": NaN,
      "learning_rate": 6.853176097769229e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.08264204100798248,
      "grad_norm": NaN,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.08514634528095164,
      "grad_norm": NaN,
      "learning_rate": 6.473978262721463e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0876506495539208,
      "grad_norm": NaN,
      "learning_rate": 6.281416799501188e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.09015495382688997,
      "grad_norm": NaN,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.09265925809985913,
      "grad_norm": NaN,
      "learning_rate": 5.8922008423644624e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0951635623728283,
      "grad_norm": NaN,
      "learning_rate": 5.696287243144013e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.09766786664579746,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.10017217091876664,
      "grad_norm": NaN,
      "learning_rate": 5.303712756855988e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.1026764751917358,
      "grad_norm": NaN,
      "learning_rate": 5.107799157635538e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.10518077946470496,
      "grad_norm": NaN,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.10768508373767413,
      "grad_norm": NaN,
      "learning_rate": 4.718583200498814e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.11018938801064329,
      "grad_norm": NaN,
      "learning_rate": 4.526021737278538e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.11269369228361246,
      "grad_norm": NaN,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.11519799655658162,
      "grad_norm": NaN,
      "learning_rate": 4.146823902230772e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.11770230082955078,
      "grad_norm": NaN,
      "learning_rate": 3.960909355034491e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.12020660510251996,
      "grad_norm": NaN,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.12271090937548912,
      "grad_norm": NaN,
      "learning_rate": 3.598217822166854e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.12521521364845828,
      "grad_norm": NaN,
      "learning_rate": 3.422131240442349e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.12521521364845828,
      "eval_loss": NaN,
      "eval_runtime": 1.5015,
      "eval_samples_per_second": 33.3,
      "eval_steps_per_second": 8.658,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.83042868150272e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}