{
  "best_metric": 0.15465113520622253,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.16028209648982208,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00032056419297964416,
      "eval_loss": 0.6954826712608337,
      "eval_runtime": 534.29,
      "eval_samples_per_second": 9.834,
      "eval_steps_per_second": 2.459,
      "step": 1
    },
    {
      "epoch": 0.01602820964898221,
      "grad_norm": 0.21765097975730896,
      "learning_rate": 0.0001075,
      "loss": 0.3418,
      "step": 50
    },
    {
      "epoch": 0.03205641929796442,
      "grad_norm": 0.20030294358730316,
      "learning_rate": 0.000215,
      "loss": 0.2316,
      "step": 100
    },
    {
      "epoch": 0.04808462894694662,
      "grad_norm": 0.16089896857738495,
      "learning_rate": 0.0002068170497449633,
      "loss": 0.2135,
      "step": 150
    },
    {
      "epoch": 0.06411283859592884,
      "grad_norm": 0.21217867732048035,
      "learning_rate": 0.00018351397897755384,
      "loss": 0.1948,
      "step": 200
    },
    {
      "epoch": 0.08014104824491104,
      "grad_norm": 0.17849212884902954,
      "learning_rate": 0.00014863846897924716,
      "loss": 0.1863,
      "step": 250
    },
    {
      "epoch": 0.09616925789389325,
      "grad_norm": 0.16983668506145477,
      "learning_rate": 0.0001075,
      "loss": 0.1731,
      "step": 300
    },
    {
      "epoch": 0.11219746754287546,
      "grad_norm": 0.19890177249908447,
      "learning_rate": 6.636153102075285e-05,
      "loss": 0.1692,
      "step": 350
    },
    {
      "epoch": 0.12822567719185768,
      "grad_norm": 0.17077498137950897,
      "learning_rate": 3.148602102244615e-05,
      "loss": 0.1616,
      "step": 400
    },
    {
      "epoch": 0.14425388684083987,
      "grad_norm": 0.15306362509727478,
      "learning_rate": 8.182950255036675e-06,
      "loss": 0.1583,
      "step": 450
    },
    {
      "epoch": 0.16028209648982208,
      "grad_norm": 0.16775737702846527,
      "learning_rate": 0.0,
      "loss": 0.1519,
      "step": 500
    },
    {
      "epoch": 0.16028209648982208,
      "eval_loss": 0.15465113520622253,
      "eval_runtime": 535.2023,
      "eval_samples_per_second": 9.817,
      "eval_steps_per_second": 2.455,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 6.725721272069652e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}