{
  "best_metric": 0.5274834036827087,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0033685156074556477,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011228385358185493,
      "eval_loss": 0.884139358997345,
      "eval_runtime": 905.847,
      "eval_samples_per_second": 4.14,
      "eval_steps_per_second": 2.07,
      "step": 1
    },
    {
      "epoch": 0.00033685156074556477,
      "grad_norm": 0.6061684489250183,
      "learning_rate": 0.00012,
      "loss": 0.5719,
      "step": 3
    },
    {
      "epoch": 0.0005614192679092747,
      "eval_loss": 0.7328800559043884,
      "eval_runtime": 924.8761,
      "eval_samples_per_second": 4.055,
      "eval_steps_per_second": 2.027,
      "step": 5
    },
    {
      "epoch": 0.0006737031214911295,
      "grad_norm": 0.39864975214004517,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.6211,
      "step": 6
    },
    {
      "epoch": 0.0010105546822366943,
      "grad_norm": 0.5194618105888367,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.5772,
      "step": 9
    },
    {
      "epoch": 0.0011228385358185494,
      "eval_loss": 0.5936566591262817,
      "eval_runtime": 922.5813,
      "eval_samples_per_second": 4.065,
      "eval_steps_per_second": 2.032,
      "step": 10
    },
    {
      "epoch": 0.001347406242982259,
      "grad_norm": 0.3496973514556885,
      "learning_rate": 0.000163742398974869,
      "loss": 0.5662,
      "step": 12
    },
    {
      "epoch": 0.0016842578037278239,
      "grad_norm": 0.4843774735927582,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.582,
      "step": 15
    },
    {
      "epoch": 0.0016842578037278239,
      "eval_loss": 0.5531880259513855,
      "eval_runtime": 921.6965,
      "eval_samples_per_second": 4.069,
      "eval_steps_per_second": 2.034,
      "step": 15
    },
    {
      "epoch": 0.0020211093644733886,
      "grad_norm": 0.34231698513031006,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.4974,
      "step": 18
    },
    {
      "epoch": 0.0022456770716370988,
      "eval_loss": 0.5368123054504395,
      "eval_runtime": 920.5174,
      "eval_samples_per_second": 4.074,
      "eval_steps_per_second": 2.037,
      "step": 20
    },
    {
      "epoch": 0.0023579609252189536,
      "grad_norm": 0.34568342566490173,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.5287,
      "step": 21
    },
    {
      "epoch": 0.002694812485964518,
      "grad_norm": 0.32576116919517517,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.5571,
      "step": 24
    },
    {
      "epoch": 0.002807096339546373,
      "eval_loss": 0.5289449095726013,
      "eval_runtime": 922.3702,
      "eval_samples_per_second": 4.066,
      "eval_steps_per_second": 2.033,
      "step": 25
    },
    {
      "epoch": 0.003031664046710083,
      "grad_norm": 0.7168234586715698,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.5479,
      "step": 27
    },
    {
      "epoch": 0.0033685156074556477,
      "grad_norm": 0.3806007504463196,
      "learning_rate": 0.0,
      "loss": 0.5298,
      "step": 30
    },
    {
      "epoch": 0.0033685156074556477,
      "eval_loss": 0.5274834036827087,
      "eval_runtime": 921.6759,
      "eval_samples_per_second": 4.069,
      "eval_steps_per_second": 2.034,
      "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": 1.3560798743887872e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}