{
  "best_metric": 2.7564406394958496,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.01929880990672242,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000643293663557414,
      "eval_loss": 4.462230682373047,
      "eval_runtime": 37.1541,
      "eval_samples_per_second": 17.629,
      "eval_steps_per_second": 8.828,
      "step": 1
    },
    {
      "epoch": 0.0019298809906722419,
      "grad_norm": 54.602684020996094,
      "learning_rate": 6e-05,
      "loss": 18.2192,
      "step": 3
    },
    {
      "epoch": 0.0032164683177870698,
      "eval_loss": 3.654305934906006,
      "eval_runtime": 36.457,
      "eval_samples_per_second": 17.966,
      "eval_steps_per_second": 8.997,
      "step": 5
    },
    {
      "epoch": 0.0038597619813444837,
      "grad_norm": 27.949995040893555,
      "learning_rate": 0.00012,
      "loss": 15.5849,
      "step": 6
    },
    {
      "epoch": 0.005789642972016726,
      "grad_norm": 28.1956844329834,
      "learning_rate": 0.00018,
      "loss": 14.0487,
      "step": 9
    },
    {
      "epoch": 0.0064329366355741395,
      "eval_loss": 3.191856861114502,
      "eval_runtime": 36.434,
      "eval_samples_per_second": 17.978,
      "eval_steps_per_second": 9.003,
      "step": 10
    },
    {
      "epoch": 0.0077195239626889674,
      "grad_norm": 22.417402267456055,
      "learning_rate": 0.00019510565162951537,
      "loss": 12.8354,
      "step": 12
    },
    {
      "epoch": 0.00964940495336121,
      "grad_norm": 18.914457321166992,
      "learning_rate": 0.00017071067811865476,
      "loss": 12.246,
      "step": 15
    },
    {
      "epoch": 0.00964940495336121,
      "eval_loss": 2.9757304191589355,
      "eval_runtime": 36.5751,
      "eval_samples_per_second": 17.908,
      "eval_steps_per_second": 8.968,
      "step": 15
    },
    {
      "epoch": 0.011579285944033452,
      "grad_norm": 20.381372451782227,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.5845,
      "step": 18
    },
    {
      "epoch": 0.012865873271148279,
      "eval_loss": 2.85648775100708,
      "eval_runtime": 36.4422,
      "eval_samples_per_second": 17.974,
      "eval_steps_per_second": 9.001,
      "step": 20
    },
    {
      "epoch": 0.013509166934705693,
      "grad_norm": 15.971494674682617,
      "learning_rate": 8.435655349597689e-05,
      "loss": 11.7824,
      "step": 21
    },
    {
      "epoch": 0.015439047925377935,
      "grad_norm": 17.2126407623291,
      "learning_rate": 4.12214747707527e-05,
      "loss": 11.6427,
      "step": 24
    },
    {
      "epoch": 0.01608234158893535,
      "eval_loss": 2.779222011566162,
      "eval_runtime": 36.6356,
      "eval_samples_per_second": 17.879,
      "eval_steps_per_second": 8.953,
      "step": 25
    },
    {
      "epoch": 0.017368928916050175,
      "grad_norm": 16.1795654296875,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 11.416,
      "step": 27
    },
    {
      "epoch": 0.01929880990672242,
      "grad_norm": 17.771339416503906,
      "learning_rate": 0.0,
      "loss": 11.0296,
      "step": 30
    },
    {
      "epoch": 0.01929880990672242,
      "eval_loss": 2.7564406394958496,
      "eval_runtime": 36.4515,
      "eval_samples_per_second": 17.969,
      "eval_steps_per_second": 8.998,
      "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": 1.054695455981568e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}