{
  "best_metric": 1.4500839710235596,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.10704727921498662,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003568242640499554,
      "eval_loss": 2.772989273071289,
      "eval_runtime": 23.53,
      "eval_samples_per_second": 10.03,
      "eval_steps_per_second": 2.507,
      "step": 1
    },
    {
      "epoch": 0.010704727921498661,
      "grad_norm": 6.560239315032959,
      "learning_rate": 0.00012,
      "loss": 7.597,
      "step": 3
    },
    {
      "epoch": 0.01784121320249777,
      "eval_loss": 2.4825103282928467,
      "eval_runtime": 23.9141,
      "eval_samples_per_second": 9.869,
      "eval_steps_per_second": 2.467,
      "step": 5
    },
    {
      "epoch": 0.021409455842997322,
      "grad_norm": 5.811731338500977,
      "learning_rate": 0.0001992114701314478,
      "loss": 6.7685,
      "step": 6
    },
    {
      "epoch": 0.032114183764495985,
      "grad_norm": 8.593225479125977,
      "learning_rate": 0.00018763066800438636,
      "loss": 5.9497,
      "step": 9
    },
    {
      "epoch": 0.03568242640499554,
      "eval_loss": 1.8928427696228027,
      "eval_runtime": 24.1424,
      "eval_samples_per_second": 9.775,
      "eval_steps_per_second": 2.444,
      "step": 10
    },
    {
      "epoch": 0.042818911685994644,
      "grad_norm": 11.166938781738281,
      "learning_rate": 0.000163742398974869,
      "loss": 5.2163,
      "step": 12
    },
    {
      "epoch": 0.05352363960749331,
      "grad_norm": 11.668803215026855,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.4989,
      "step": 15
    },
    {
      "epoch": 0.05352363960749331,
      "eval_loss": 1.7072616815567017,
      "eval_runtime": 24.2567,
      "eval_samples_per_second": 9.729,
      "eval_steps_per_second": 2.432,
      "step": 15
    },
    {
      "epoch": 0.06422836752899197,
      "grad_norm": 13.31494140625,
      "learning_rate": 9.372094804706867e-05,
      "loss": 5.7607,
      "step": 18
    },
    {
      "epoch": 0.07136485280999108,
      "eval_loss": 1.5477936267852783,
      "eval_runtime": 24.2406,
      "eval_samples_per_second": 9.736,
      "eval_steps_per_second": 2.434,
      "step": 20
    },
    {
      "epoch": 0.07493309545049064,
      "grad_norm": 11.966535568237305,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 6.785,
      "step": 21
    },
    {
      "epoch": 0.08563782337198929,
      "grad_norm": 9.986099243164062,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 5.7129,
      "step": 24
    },
    {
      "epoch": 0.08920606601248884,
      "eval_loss": 1.4632445573806763,
      "eval_runtime": 24.1718,
      "eval_samples_per_second": 9.763,
      "eval_steps_per_second": 2.441,
      "step": 25
    },
    {
      "epoch": 0.09634255129348795,
      "grad_norm": 16.059425354003906,
      "learning_rate": 7.022351411174866e-06,
      "loss": 8.0728,
      "step": 27
    },
    {
      "epoch": 0.10704727921498662,
      "grad_norm": 14.310097694396973,
      "learning_rate": 0.0,
      "loss": 7.0192,
      "step": 30
    },
    {
      "epoch": 0.10704727921498662,
      "eval_loss": 1.4500839710235596,
      "eval_runtime": 24.1501,
      "eval_samples_per_second": 9.772,
      "eval_steps_per_second": 2.443,
      "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": 1.960374605709312e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}