{
  "best_metric": 1.318974494934082,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.15789473684210525,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005263157894736842,
      "eval_loss": 1.6880848407745361,
      "eval_runtime": 9.1708,
      "eval_samples_per_second": 17.447,
      "eval_steps_per_second": 4.362,
      "step": 1
    },
    {
      "epoch": 0.015789473684210527,
      "grad_norm": 2.127700090408325,
      "learning_rate": 0.00012,
      "loss": 6.2728,
      "step": 3
    },
    {
      "epoch": 0.02631578947368421,
      "eval_loss": 1.5987045764923096,
      "eval_runtime": 9.1471,
      "eval_samples_per_second": 17.492,
      "eval_steps_per_second": 4.373,
      "step": 5
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 2.6955976486206055,
      "learning_rate": 0.0001992114701314478,
      "loss": 6.3863,
      "step": 6
    },
    {
      "epoch": 0.04736842105263158,
      "grad_norm": 2.396484613418579,
      "learning_rate": 0.00018763066800438636,
      "loss": 6.0131,
      "step": 9
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 1.4852279424667358,
      "eval_runtime": 9.2099,
      "eval_samples_per_second": 17.373,
      "eval_steps_per_second": 4.343,
      "step": 10
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 1.9726710319519043,
      "learning_rate": 0.000163742398974869,
      "loss": 5.6899,
      "step": 12
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 2.23517107963562,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.4887,
      "step": 15
    },
    {
      "epoch": 0.07894736842105263,
      "eval_loss": 1.3928982019424438,
      "eval_runtime": 9.2351,
      "eval_samples_per_second": 17.325,
      "eval_steps_per_second": 4.331,
      "step": 15
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 2.371098279953003,
      "learning_rate": 9.372094804706867e-05,
      "loss": 5.4168,
      "step": 18
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 1.3468906879425049,
      "eval_runtime": 9.2425,
      "eval_samples_per_second": 17.311,
      "eval_steps_per_second": 4.328,
      "step": 20
    },
    {
      "epoch": 0.11052631578947368,
      "grad_norm": 2.1808433532714844,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 5.5852,
      "step": 21
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 2.32429575920105,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 5.2769,
      "step": 24
    },
    {
      "epoch": 0.13157894736842105,
      "eval_loss": 1.321532964706421,
      "eval_runtime": 9.2743,
      "eval_samples_per_second": 17.252,
      "eval_steps_per_second": 4.313,
      "step": 25
    },
    {
      "epoch": 0.14210526315789473,
      "grad_norm": 2.4233052730560303,
      "learning_rate": 7.022351411174866e-06,
      "loss": 5.3304,
      "step": 27
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 2.362999677658081,
      "learning_rate": 0.0,
      "loss": 5.1204,
      "step": 30
    },
    {
      "epoch": 0.15789473684210525,
      "eval_loss": 1.318974494934082,
      "eval_runtime": 9.2727,
      "eval_samples_per_second": 17.255,
      "eval_steps_per_second": 4.314,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 3601422687928320.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}