{
  "best_metric": 1.3286937475204468,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0015698176395175427,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.232725465058476e-05,
      "eval_loss": 2.1072628498077393,
      "eval_runtime": 3076.7009,
      "eval_samples_per_second": 5.231,
      "eval_steps_per_second": 1.308,
      "step": 1
    },
    {
      "epoch": 0.00015698176395175428,
      "grad_norm": 0.2532333731651306,
      "learning_rate": 0.00012,
      "loss": 1.0963,
      "step": 3
    },
    {
      "epoch": 0.0002616362732529238,
      "eval_loss": 1.9177733659744263,
      "eval_runtime": 3095.3028,
      "eval_samples_per_second": 5.199,
      "eval_steps_per_second": 1.3,
      "step": 5
    },
    {
      "epoch": 0.00031396352790350856,
      "grad_norm": 0.3635496199131012,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.109,
      "step": 6
    },
    {
      "epoch": 0.0004709452918552628,
      "grad_norm": 0.37732282280921936,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.0465,
      "step": 9
    },
    {
      "epoch": 0.0005232725465058476,
      "eval_loss": 1.5030826330184937,
      "eval_runtime": 3092.9168,
      "eval_samples_per_second": 5.203,
      "eval_steps_per_second": 1.301,
      "step": 10
    },
    {
      "epoch": 0.0006279270558070171,
      "grad_norm": 0.3684312105178833,
      "learning_rate": 0.000163742398974869,
      "loss": 1.044,
      "step": 12
    },
    {
      "epoch": 0.0007849088197587713,
      "grad_norm": 0.3923090994358063,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.997,
      "step": 15
    },
    {
      "epoch": 0.0007849088197587713,
      "eval_loss": 1.3932478427886963,
      "eval_runtime": 3094.3973,
      "eval_samples_per_second": 5.201,
      "eval_steps_per_second": 1.3,
      "step": 15
    },
    {
      "epoch": 0.0009418905837105256,
      "grad_norm": 0.34257999062538147,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.0033,
      "step": 18
    },
    {
      "epoch": 0.0010465450930116952,
      "eval_loss": 1.3482195138931274,
      "eval_runtime": 3086.4995,
      "eval_samples_per_second": 5.214,
      "eval_steps_per_second": 1.304,
      "step": 20
    },
    {
      "epoch": 0.00109887234766228,
      "grad_norm": 0.29628661274909973,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.0515,
      "step": 21
    },
    {
      "epoch": 0.0012558541116140342,
      "grad_norm": 0.3616541028022766,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.0526,
      "step": 24
    },
    {
      "epoch": 0.001308181366264619,
      "eval_loss": 1.3322861194610596,
      "eval_runtime": 3085.4269,
      "eval_samples_per_second": 5.216,
      "eval_steps_per_second": 1.304,
      "step": 25
    },
    {
      "epoch": 0.0014128358755657884,
      "grad_norm": 0.3618899881839752,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.1563,
      "step": 27
    },
    {
      "epoch": 0.0015698176395175427,
      "grad_norm": 0.37173062562942505,
      "learning_rate": 0.0,
      "loss": 1.139,
      "step": 30
    },
    {
      "epoch": 0.0015698176395175427,
      "eval_loss": 1.3286937475204468,
      "eval_runtime": 3087.5087,
      "eval_samples_per_second": 5.212,
      "eval_steps_per_second": 1.303,
      "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": 3.84041276669952e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}