{
  "best_metric": 2.1618664264678955,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.03753518923991242,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012511729746637473,
      "eval_loss": 3.794546127319336,
      "eval_runtime": 18.5098,
      "eval_samples_per_second": 18.207,
      "eval_steps_per_second": 9.13,
      "step": 1
    },
    {
      "epoch": 0.003753518923991242,
      "grad_norm": 1.2596303224563599,
      "learning_rate": 6e-05,
      "loss": 3.7409,
      "step": 3
    },
    {
      "epoch": 0.006255864873318737,
      "eval_loss": 3.7131717205047607,
      "eval_runtime": 17.7214,
      "eval_samples_per_second": 19.017,
      "eval_steps_per_second": 9.536,
      "step": 5
    },
    {
      "epoch": 0.007507037847982484,
      "grad_norm": 1.0141929388046265,
      "learning_rate": 0.00012,
      "loss": 3.6177,
      "step": 6
    },
    {
      "epoch": 0.011260556771973726,
      "grad_norm": 1.4149610996246338,
      "learning_rate": 0.00018,
      "loss": 3.315,
      "step": 9
    },
    {
      "epoch": 0.012511729746637473,
      "eval_loss": 3.066793203353882,
      "eval_runtime": 17.7282,
      "eval_samples_per_second": 19.009,
      "eval_steps_per_second": 9.533,
      "step": 10
    },
    {
      "epoch": 0.015014075695964968,
      "grad_norm": 1.6633483171463013,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.9406,
      "step": 12
    },
    {
      "epoch": 0.01876759461995621,
      "grad_norm": 1.8299262523651123,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.6414,
      "step": 15
    },
    {
      "epoch": 0.01876759461995621,
      "eval_loss": 2.5201518535614014,
      "eval_runtime": 17.8514,
      "eval_samples_per_second": 18.878,
      "eval_steps_per_second": 9.467,
      "step": 15
    },
    {
      "epoch": 0.022521113543947452,
      "grad_norm": 1.523863434791565,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.4272,
      "step": 18
    },
    {
      "epoch": 0.025023459493274947,
      "eval_loss": 2.2870724201202393,
      "eval_runtime": 17.7315,
      "eval_samples_per_second": 19.006,
      "eval_steps_per_second": 9.531,
      "step": 20
    },
    {
      "epoch": 0.026274632467938694,
      "grad_norm": 1.7266687154769897,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.2876,
      "step": 21
    },
    {
      "epoch": 0.030028151391929936,
      "grad_norm": 2.26924467086792,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.247,
      "step": 24
    },
    {
      "epoch": 0.03127932436659368,
      "eval_loss": 2.1842119693756104,
      "eval_runtime": 17.8552,
      "eval_samples_per_second": 18.874,
      "eval_steps_per_second": 9.465,
      "step": 25
    },
    {
      "epoch": 0.03378167031592118,
      "grad_norm": 1.735610008239746,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.289,
      "step": 27
    },
    {
      "epoch": 0.03753518923991242,
      "grad_norm": 2.1275014877319336,
      "learning_rate": 0.0,
      "loss": 2.3015,
      "step": 30
    },
    {
      "epoch": 0.03753518923991242,
      "eval_loss": 2.1618664264678955,
      "eval_runtime": 17.7533,
      "eval_samples_per_second": 18.982,
      "eval_steps_per_second": 9.519,
      "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": 1.048558039990272e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}