{
  "best_metric": 0.8691785335540771,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.025546209900433648,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.109241980086729e-05,
      "eval_loss": 2.2433838844299316,
      "eval_runtime": 3261.1045,
      "eval_samples_per_second": 10.108,
      "eval_steps_per_second": 2.527,
      "step": 1
    },
    {
      "epoch": 0.0025546209900433646,
      "grad_norm": 0.7787982821464539,
      "learning_rate": 0.000106,
      "loss": 1.5045,
      "step": 50
    },
    {
      "epoch": 0.005109241980086729,
      "grad_norm": 0.7246711850166321,
      "learning_rate": 0.000212,
      "loss": 1.1,
      "step": 100
    },
    {
      "epoch": 0.007663862970130094,
      "grad_norm": 0.5906647443771362,
      "learning_rate": 0.0002039312304461964,
      "loss": 1.0226,
      "step": 150
    },
    {
      "epoch": 0.010218483960173459,
      "grad_norm": 0.5370720028877258,
      "learning_rate": 0.00018095331880577404,
      "loss": 0.9885,
      "step": 200
    },
    {
      "epoch": 0.012773104950216824,
      "grad_norm": 0.8217043876647949,
      "learning_rate": 0.00014656444383069953,
      "loss": 0.9601,
      "step": 250
    },
    {
      "epoch": 0.015327725940260188,
      "grad_norm": 0.6211170554161072,
      "learning_rate": 0.000106,
      "loss": 0.9373,
      "step": 300
    },
    {
      "epoch": 0.017882346930303553,
      "grad_norm": 0.5487996935844421,
      "learning_rate": 6.543555616930049e-05,
      "loss": 0.9048,
      "step": 350
    },
    {
      "epoch": 0.020436967920346917,
      "grad_norm": 0.6398413777351379,
      "learning_rate": 3.104668119422597e-05,
      "loss": 0.9171,
      "step": 400
    },
    {
      "epoch": 0.02299158891039028,
      "grad_norm": 0.5369225740432739,
      "learning_rate": 8.068769553803605e-06,
      "loss": 0.8788,
      "step": 450
    },
    {
      "epoch": 0.025546209900433648,
      "grad_norm": 0.5273388028144836,
      "learning_rate": 0.0,
      "loss": 0.8856,
      "step": 500
    },
    {
      "epoch": 0.025546209900433648,
      "eval_loss": 0.8691785335540771,
      "eval_runtime": 3261.5417,
      "eval_samples_per_second": 10.107,
      "eval_steps_per_second": 2.527,
      "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": 6.654206431639634e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}