{
  "best_metric": 6.923157215118408,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.05102040816326531,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017006802721088435,
      "eval_loss": 6.93667459487915,
      "eval_runtime": 2.6649,
      "eval_samples_per_second": 185.748,
      "eval_steps_per_second": 46.531,
      "step": 1
    },
    {
      "epoch": 0.00510204081632653,
      "grad_norm": 0.09512083232402802,
      "learning_rate": 0.00012,
      "loss": 6.9367,
      "step": 3
    },
    {
      "epoch": 0.008503401360544218,
      "eval_loss": 6.93510103225708,
      "eval_runtime": 1.3791,
      "eval_samples_per_second": 358.921,
      "eval_steps_per_second": 89.911,
      "step": 5
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": 0.09417915344238281,
      "learning_rate": 0.0001992114701314478,
      "loss": 6.9373,
      "step": 6
    },
    {
      "epoch": 0.015306122448979591,
      "grad_norm": 0.10015915334224701,
      "learning_rate": 0.00018763066800438636,
      "loss": 6.9343,
      "step": 9
    },
    {
      "epoch": 0.017006802721088437,
      "eval_loss": 6.9310455322265625,
      "eval_runtime": 1.377,
      "eval_samples_per_second": 359.482,
      "eval_steps_per_second": 90.052,
      "step": 10
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 0.10518069565296173,
      "learning_rate": 0.000163742398974869,
      "loss": 6.9317,
      "step": 12
    },
    {
      "epoch": 0.025510204081632654,
      "grad_norm": 0.1085585281252861,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.9294,
      "step": 15
    },
    {
      "epoch": 0.025510204081632654,
      "eval_loss": 6.927322864532471,
      "eval_runtime": 1.407,
      "eval_samples_per_second": 351.806,
      "eval_steps_per_second": 88.129,
      "step": 15
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 0.1129802018404007,
      "learning_rate": 9.372094804706867e-05,
      "loss": 6.9265,
      "step": 18
    },
    {
      "epoch": 0.034013605442176874,
      "eval_loss": 6.9246506690979,
      "eval_runtime": 1.3869,
      "eval_samples_per_second": 356.908,
      "eval_steps_per_second": 89.407,
      "step": 20
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 0.10753895342350006,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 6.9267,
      "step": 21
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 0.11653916537761688,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 6.9259,
      "step": 24
    },
    {
      "epoch": 0.04251700680272109,
      "eval_loss": 6.923396587371826,
      "eval_runtime": 1.396,
      "eval_samples_per_second": 354.578,
      "eval_steps_per_second": 88.824,
      "step": 25
    },
    {
      "epoch": 0.04591836734693878,
      "grad_norm": 0.11115945130586624,
      "learning_rate": 7.022351411174866e-06,
      "loss": 6.9258,
      "step": 27
    },
    {
      "epoch": 0.05102040816326531,
      "grad_norm": 0.11353718489408493,
      "learning_rate": 0.0,
      "loss": 6.9242,
      "step": 30
    },
    {
      "epoch": 0.05102040816326531,
      "eval_loss": 6.923157215118408,
      "eval_runtime": 1.4012,
      "eval_samples_per_second": 353.257,
      "eval_steps_per_second": 88.493,
      "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": 332956188672.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}