{
  "best_metric": 1.3010038137435913,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.7465472191116088,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014930944382232176,
      "eval_loss": 5.227748394012451,
      "eval_runtime": 275.3633,
      "eval_samples_per_second": 4.1,
      "eval_steps_per_second": 1.028,
      "step": 1
    },
    {
      "epoch": 0.07465472191116088,
      "grad_norm": 3.244680404663086,
      "learning_rate": 0.0001015,
      "loss": 2.3821,
      "step": 50
    },
    {
      "epoch": 0.14930944382232175,
      "grad_norm": 3.4606010913848877,
      "learning_rate": 0.000203,
      "loss": 1.7001,
      "step": 100
    },
    {
      "epoch": 0.22396416573348266,
      "grad_norm": 2.69309401512146,
      "learning_rate": 0.0001952737725498956,
      "loss": 1.5613,
      "step": 150
    },
    {
      "epoch": 0.2986188876446435,
      "grad_norm": 2.8384764194488525,
      "learning_rate": 0.00017327133829043458,
      "loss": 1.5169,
      "step": 200
    },
    {
      "epoch": 0.3732736095558044,
      "grad_norm": 4.116892337799072,
      "learning_rate": 0.00014034236838505662,
      "loss": 1.481,
      "step": 250
    },
    {
      "epoch": 0.4479283314669653,
      "grad_norm": 2.7776787281036377,
      "learning_rate": 0.0001015,
      "loss": 1.4521,
      "step": 300
    },
    {
      "epoch": 0.5225830533781262,
      "grad_norm": 3.30334734916687,
      "learning_rate": 6.265763161494339e-05,
      "loss": 1.3618,
      "step": 350
    },
    {
      "epoch": 0.597237775289287,
      "grad_norm": 2.48299241065979,
      "learning_rate": 2.972866170956543e-05,
      "loss": 1.3536,
      "step": 400
    },
    {
      "epoch": 0.671892497200448,
      "grad_norm": 2.8466036319732666,
      "learning_rate": 7.726227450104397e-06,
      "loss": 1.3104,
      "step": 450
    },
    {
      "epoch": 0.7465472191116088,
      "grad_norm": 2.7488033771514893,
      "learning_rate": 0.0,
      "loss": 1.3434,
      "step": 500
    },
    {
      "epoch": 0.7465472191116088,
      "eval_loss": 1.3010038137435913,
      "eval_runtime": 276.0394,
      "eval_samples_per_second": 4.09,
      "eval_steps_per_second": 1.025,
      "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": 1.3600598424079565e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}