{
  "best_metric": 10.323739051818848,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.5128205128205128,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020512820512820513,
      "grad_norm": 0.27070486545562744,
      "learning_rate": 5e-05,
      "loss": 10.3777,
      "step": 1
    },
    {
      "epoch": 0.020512820512820513,
      "eval_loss": 10.361001014709473,
      "eval_runtime": 0.1067,
      "eval_samples_per_second": 468.596,
      "eval_steps_per_second": 121.835,
      "step": 1
    },
    {
      "epoch": 0.041025641025641026,
      "grad_norm": 0.2512279748916626,
      "learning_rate": 0.0001,
      "loss": 10.3865,
      "step": 2
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 0.26547926664352417,
      "learning_rate": 9.990365154573717e-05,
      "loss": 10.3909,
      "step": 3
    },
    {
      "epoch": 0.08205128205128205,
      "grad_norm": 0.26054540276527405,
      "learning_rate": 9.961501876182148e-05,
      "loss": 10.377,
      "step": 4
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.26316037774086,
      "learning_rate": 9.913533761814537e-05,
      "loss": 10.3617,
      "step": 5
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": 0.26677894592285156,
      "learning_rate": 9.846666218300807e-05,
      "loss": 10.3726,
      "step": 6
    },
    {
      "epoch": 0.14358974358974358,
      "grad_norm": 0.25949233770370483,
      "learning_rate": 9.761185582727977e-05,
      "loss": 10.3627,
      "step": 7
    },
    {
      "epoch": 0.1641025641025641,
      "grad_norm": 0.2796414792537689,
      "learning_rate": 9.657457896300791e-05,
      "loss": 10.3536,
      "step": 8
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.2990741431713104,
      "learning_rate": 9.535927336897098e-05,
      "loss": 10.3424,
      "step": 9
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.29780325293540955,
      "learning_rate": 9.397114317029975e-05,
      "loss": 10.3536,
      "step": 10
    },
    {
      "epoch": 0.22564102564102564,
      "grad_norm": 0.3147619962692261,
      "learning_rate": 9.241613255361455e-05,
      "loss": 10.3439,
      "step": 11
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": 0.3716137111186981,
      "learning_rate": 9.070090031310558e-05,
      "loss": 10.3582,
      "step": 12
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.28069737553596497,
      "learning_rate": 8.883279133655399e-05,
      "loss": 10.3686,
      "step": 13
    },
    {
      "epoch": 0.28717948717948716,
      "grad_norm": 0.2844381034374237,
      "learning_rate": 8.681980515339464e-05,
      "loss": 10.3814,
      "step": 14
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.2878939211368561,
      "learning_rate": 8.467056167950311e-05,
      "loss": 10.3661,
      "step": 15
    },
    {
      "epoch": 0.3282051282051282,
      "grad_norm": 0.31458649039268494,
      "learning_rate": 8.239426430539243e-05,
      "loss": 10.3666,
      "step": 16
    },
    {
      "epoch": 0.3487179487179487,
      "grad_norm": 0.3024202585220337,
      "learning_rate": 8.000066048588211e-05,
      "loss": 10.354,
      "step": 17
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3125394284725189,
      "learning_rate": 7.75e-05,
      "loss": 10.3361,
      "step": 18
    },
    {
      "epoch": 0.38974358974358975,
      "grad_norm": 0.33549174666404724,
      "learning_rate": 7.490299105985507e-05,
      "loss": 10.3418,
      "step": 19
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.3704705536365509,
      "learning_rate": 7.222075445642904e-05,
      "loss": 10.3256,
      "step": 20
    },
    {
      "epoch": 0.4307692307692308,
      "grad_norm": 0.3914016783237457,
      "learning_rate": 6.946477593864228e-05,
      "loss": 10.3287,
      "step": 21
    },
    {
      "epoch": 0.4512820512820513,
      "grad_norm": 0.4021913707256317,
      "learning_rate": 6.664685702961344e-05,
      "loss": 10.3277,
      "step": 22
    },
    {
      "epoch": 0.4717948717948718,
      "grad_norm": 0.4114139974117279,
      "learning_rate": 6.377906449072578e-05,
      "loss": 10.316,
      "step": 23
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": 0.46048444509506226,
      "learning_rate": 6.087367864990233e-05,
      "loss": 10.3339,
      "step": 24
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.371286541223526,
      "learning_rate": 5.794314081535644e-05,
      "loss": 10.3481,
      "step": 25
    },
    {
      "epoch": 0.5128205128205128,
      "eval_loss": 10.323739051818848,
      "eval_runtime": 0.0956,
      "eval_samples_per_second": 523.14,
      "eval_steps_per_second": 136.016,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 21384029798400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}