{
  "best_metric": 10.369670867919922,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0631911532385466,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00210637177461822,
      "eval_loss": 10.380047798156738,
      "eval_runtime": 1.543,
      "eval_samples_per_second": 259.238,
      "eval_steps_per_second": 64.809,
      "step": 1
    },
    {
      "epoch": 0.00631911532385466,
      "grad_norm": 0.05801166594028473,
      "learning_rate": 0.00012,
      "loss": 10.3752,
      "step": 3
    },
    {
      "epoch": 0.010531858873091101,
      "eval_loss": 10.378893852233887,
      "eval_runtime": 1.5456,
      "eval_samples_per_second": 258.801,
      "eval_steps_per_second": 64.7,
      "step": 5
    },
    {
      "epoch": 0.01263823064770932,
      "grad_norm": 0.07109837979078293,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.3782,
      "step": 6
    },
    {
      "epoch": 0.018957345971563982,
      "grad_norm": 0.09247684478759766,
      "learning_rate": 0.00018763066800438636,
      "loss": 10.3741,
      "step": 9
    },
    {
      "epoch": 0.021063717746182202,
      "eval_loss": 10.375741958618164,
      "eval_runtime": 1.5001,
      "eval_samples_per_second": 266.645,
      "eval_steps_per_second": 66.661,
      "step": 10
    },
    {
      "epoch": 0.02527646129541864,
      "grad_norm": 0.09941345453262329,
      "learning_rate": 0.000163742398974869,
      "loss": 10.3769,
      "step": 12
    },
    {
      "epoch": 0.0315955766192733,
      "grad_norm": 0.10976149886846542,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.3736,
      "step": 15
    },
    {
      "epoch": 0.0315955766192733,
      "eval_loss": 10.372819900512695,
      "eval_runtime": 1.5881,
      "eval_samples_per_second": 251.87,
      "eval_steps_per_second": 62.968,
      "step": 15
    },
    {
      "epoch": 0.037914691943127965,
      "grad_norm": 0.11037761718034744,
      "learning_rate": 9.372094804706867e-05,
      "loss": 10.376,
      "step": 18
    },
    {
      "epoch": 0.042127435492364404,
      "eval_loss": 10.370805740356445,
      "eval_runtime": 1.5368,
      "eval_samples_per_second": 260.274,
      "eval_steps_per_second": 65.069,
      "step": 20
    },
    {
      "epoch": 0.044233807266982623,
      "grad_norm": 0.1159617155790329,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 10.3719,
      "step": 21
    },
    {
      "epoch": 0.05055292259083728,
      "grad_norm": 0.1259760856628418,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 10.3727,
      "step": 24
    },
    {
      "epoch": 0.0526592943654555,
      "eval_loss": 10.36983871459961,
      "eval_runtime": 1.57,
      "eval_samples_per_second": 254.779,
      "eval_steps_per_second": 63.695,
      "step": 25
    },
    {
      "epoch": 0.05687203791469194,
      "grad_norm": 0.15423348546028137,
      "learning_rate": 7.022351411174866e-06,
      "loss": 10.3674,
      "step": 27
    },
    {
      "epoch": 0.0631911532385466,
      "grad_norm": 0.15420296788215637,
      "learning_rate": 0.0,
      "loss": 10.3697,
      "step": 30
    },
    {
      "epoch": 0.0631911532385466,
      "eval_loss": 10.369670867919922,
      "eval_runtime": 1.5332,
      "eval_samples_per_second": 260.899,
      "eval_steps_per_second": 65.225,
      "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": 1569073397760.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}