{
  "best_metric": 0.9853674173355103,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0176678445229682,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005889281507656066,
      "eval_loss": 1.3518844842910767,
      "eval_runtime": 498.2998,
      "eval_samples_per_second": 2.87,
      "eval_steps_per_second": 0.718,
      "step": 1
    },
    {
      "epoch": 0.0017667844522968198,
      "grad_norm": 0.6670573949813843,
      "learning_rate": 0.00012,
      "loss": 5.3578,
      "step": 3
    },
    {
      "epoch": 0.002944640753828033,
      "eval_loss": 1.2665971517562866,
      "eval_runtime": 501.4957,
      "eval_samples_per_second": 2.851,
      "eval_steps_per_second": 0.714,
      "step": 5
    },
    {
      "epoch": 0.0035335689045936395,
      "grad_norm": 0.8898412585258484,
      "learning_rate": 0.0001992114701314478,
      "loss": 5.1071,
      "step": 6
    },
    {
      "epoch": 0.00530035335689046,
      "grad_norm": 1.0011253356933594,
      "learning_rate": 0.00018763066800438636,
      "loss": 4.7639,
      "step": 9
    },
    {
      "epoch": 0.005889281507656066,
      "eval_loss": 1.063054084777832,
      "eval_runtime": 502.2943,
      "eval_samples_per_second": 2.847,
      "eval_steps_per_second": 0.713,
      "step": 10
    },
    {
      "epoch": 0.007067137809187279,
      "grad_norm": 0.6839013695716858,
      "learning_rate": 0.000163742398974869,
      "loss": 4.2181,
      "step": 12
    },
    {
      "epoch": 0.0088339222614841,
      "grad_norm": 0.757274866104126,
      "learning_rate": 0.00013090169943749476,
      "loss": 4.2507,
      "step": 15
    },
    {
      "epoch": 0.0088339222614841,
      "eval_loss": 1.0176669359207153,
      "eval_runtime": 500.0195,
      "eval_samples_per_second": 2.86,
      "eval_steps_per_second": 0.716,
      "step": 15
    },
    {
      "epoch": 0.01060070671378092,
      "grad_norm": 0.7244177460670471,
      "learning_rate": 9.372094804706867e-05,
      "loss": 3.94,
      "step": 18
    },
    {
      "epoch": 0.011778563015312132,
      "eval_loss": 0.9963037371635437,
      "eval_runtime": 499.8463,
      "eval_samples_per_second": 2.861,
      "eval_steps_per_second": 0.716,
      "step": 20
    },
    {
      "epoch": 0.012367491166077738,
      "grad_norm": 0.7493723034858704,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 3.8839,
      "step": 21
    },
    {
      "epoch": 0.014134275618374558,
      "grad_norm": 0.6799465417861938,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 4.0398,
      "step": 24
    },
    {
      "epoch": 0.014723203769140165,
      "eval_loss": 0.9870917797088623,
      "eval_runtime": 499.6308,
      "eval_samples_per_second": 2.862,
      "eval_steps_per_second": 0.717,
      "step": 25
    },
    {
      "epoch": 0.015901060070671377,
      "grad_norm": 0.7286937236785889,
      "learning_rate": 7.022351411174866e-06,
      "loss": 3.7649,
      "step": 27
    },
    {
      "epoch": 0.0176678445229682,
      "grad_norm": 0.6232637166976929,
      "learning_rate": 0.0,
      "loss": 4.2536,
      "step": 30
    },
    {
      "epoch": 0.0176678445229682,
      "eval_loss": 0.9853674173355103,
      "eval_runtime": 500.7857,
      "eval_samples_per_second": 2.856,
      "eval_steps_per_second": 0.715,
      "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": 7.6173476364288e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}