{
  "best_metric": 1.4860066175460815,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.12944983818770225,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004314994606256742,
      "eval_loss": 2.5526950359344482,
      "eval_runtime": 44.3024,
      "eval_samples_per_second": 4.402,
      "eval_steps_per_second": 1.106,
      "step": 1
    },
    {
      "epoch": 0.012944983818770227,
      "grad_norm": 0.4382025897502899,
      "learning_rate": 6e-05,
      "loss": 1.9198,
      "step": 3
    },
    {
      "epoch": 0.021574973031283712,
      "eval_loss": 2.516932487487793,
      "eval_runtime": 44.2768,
      "eval_samples_per_second": 4.404,
      "eval_steps_per_second": 1.107,
      "step": 5
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 0.5087972283363342,
      "learning_rate": 9.96057350657239e-05,
      "loss": 2.157,
      "step": 6
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": 0.8384918570518494,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.0916,
      "step": 9
    },
    {
      "epoch": 0.043149946062567425,
      "eval_loss": 2.1281909942626953,
      "eval_runtime": 44.4377,
      "eval_samples_per_second": 4.388,
      "eval_steps_per_second": 1.103,
      "step": 10
    },
    {
      "epoch": 0.05177993527508091,
      "grad_norm": 0.9176951050758362,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.8931,
      "step": 12
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 0.8622118830680847,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7376,
      "step": 15
    },
    {
      "epoch": 0.06472491909385113,
      "eval_loss": 1.7508946657180786,
      "eval_runtime": 44.6275,
      "eval_samples_per_second": 4.37,
      "eval_steps_per_second": 1.098,
      "step": 15
    },
    {
      "epoch": 0.07766990291262135,
      "grad_norm": 0.6933388113975525,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.5609,
      "step": 18
    },
    {
      "epoch": 0.08629989212513485,
      "eval_loss": 1.5642491579055786,
      "eval_runtime": 44.4716,
      "eval_samples_per_second": 4.385,
      "eval_steps_per_second": 1.102,
      "step": 20
    },
    {
      "epoch": 0.09061488673139159,
      "grad_norm": 0.7784251570701599,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 1.5033,
      "step": 21
    },
    {
      "epoch": 0.10355987055016182,
      "grad_norm": 0.9875249862670898,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 1.468,
      "step": 24
    },
    {
      "epoch": 0.10787486515641856,
      "eval_loss": 1.4989583492279053,
      "eval_runtime": 44.5228,
      "eval_samples_per_second": 4.38,
      "eval_steps_per_second": 1.101,
      "step": 25
    },
    {
      "epoch": 0.11650485436893204,
      "grad_norm": 0.7232942581176758,
      "learning_rate": 3.511175705587433e-06,
      "loss": 1.5199,
      "step": 27
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": 0.8101120591163635,
      "learning_rate": 0.0,
      "loss": 1.5326,
      "step": 30
    },
    {
      "epoch": 0.12944983818770225,
      "eval_loss": 1.4860066175460815,
      "eval_runtime": 44.5057,
      "eval_samples_per_second": 4.381,
      "eval_steps_per_second": 1.101,
      "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": 3.8086738182144e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}