{
  "best_metric": 0.6096845865249634,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.008477569763334511,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028258565877781704,
      "eval_loss": 1.004011631011963,
      "eval_runtime": 367.8146,
      "eval_samples_per_second": 4.051,
      "eval_steps_per_second": 2.025,
      "step": 1
    },
    {
      "epoch": 0.0008477569763334511,
      "grad_norm": 6.227362155914307,
      "learning_rate": 6e-05,
      "loss": 4.132,
      "step": 3
    },
    {
      "epoch": 0.001412928293889085,
      "eval_loss": 0.8604836463928223,
      "eval_runtime": 370.2175,
      "eval_samples_per_second": 4.025,
      "eval_steps_per_second": 2.012,
      "step": 5
    },
    {
      "epoch": 0.0016955139526669022,
      "grad_norm": 3.4391531944274902,
      "learning_rate": 0.00012,
      "loss": 3.564,
      "step": 6
    },
    {
      "epoch": 0.002543270929000353,
      "grad_norm": 3.636760950088501,
      "learning_rate": 0.00018,
      "loss": 3.0685,
      "step": 9
    },
    {
      "epoch": 0.00282585658777817,
      "eval_loss": 0.6580381393432617,
      "eval_runtime": 370.2065,
      "eval_samples_per_second": 4.025,
      "eval_steps_per_second": 2.012,
      "step": 10
    },
    {
      "epoch": 0.0033910279053338045,
      "grad_norm": 2.6489813327789307,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.5299,
      "step": 12
    },
    {
      "epoch": 0.0042387848816672555,
      "grad_norm": 1.7734023332595825,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.4377,
      "step": 15
    },
    {
      "epoch": 0.0042387848816672555,
      "eval_loss": 0.6288617849349976,
      "eval_runtime": 369.5481,
      "eval_samples_per_second": 4.032,
      "eval_steps_per_second": 2.016,
      "step": 15
    },
    {
      "epoch": 0.005086541858000706,
      "grad_norm": 1.6750638484954834,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.5392,
      "step": 18
    },
    {
      "epoch": 0.00565171317555634,
      "eval_loss": 0.6153923273086548,
      "eval_runtime": 369.2744,
      "eval_samples_per_second": 4.035,
      "eval_steps_per_second": 2.017,
      "step": 20
    },
    {
      "epoch": 0.0059342988343341575,
      "grad_norm": 1.9146122932434082,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.4474,
      "step": 21
    },
    {
      "epoch": 0.006782055810667609,
      "grad_norm": 1.4940017461776733,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.5059,
      "step": 24
    },
    {
      "epoch": 0.007064641469445425,
      "eval_loss": 0.6112915277481079,
      "eval_runtime": 369.4846,
      "eval_samples_per_second": 4.033,
      "eval_steps_per_second": 2.016,
      "step": 25
    },
    {
      "epoch": 0.0076298127870010595,
      "grad_norm": 1.4474186897277832,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.4497,
      "step": 27
    },
    {
      "epoch": 0.008477569763334511,
      "grad_norm": 1.4451892375946045,
      "learning_rate": 0.0,
      "loss": 2.4351,
      "step": 30
    },
    {
      "epoch": 0.008477569763334511,
      "eval_loss": 0.6096845865249634,
      "eval_runtime": 369.4916,
      "eval_samples_per_second": 4.033,
      "eval_steps_per_second": 2.016,
      "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": 2.109390911963136e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}