{
  "best_metric": 2.5499963760375977,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0005255919479313577,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7519731597711922e-05,
      "eval_loss": 3.9743845462799072,
      "eval_runtime": 1381.4735,
      "eval_samples_per_second": 17.397,
      "eval_steps_per_second": 8.699,
      "step": 1
    },
    {
      "epoch": 5.2559194793135767e-05,
      "grad_norm": 1.904785394668579,
      "learning_rate": 0.00012,
      "loss": 3.8515,
      "step": 3
    },
    {
      "epoch": 8.759865798855962e-05,
      "eval_loss": 3.40993595123291,
      "eval_runtime": 1379.2014,
      "eval_samples_per_second": 17.426,
      "eval_steps_per_second": 8.713,
      "step": 5
    },
    {
      "epoch": 0.00010511838958627153,
      "grad_norm": 2.348266839981079,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.6623,
      "step": 6
    },
    {
      "epoch": 0.0001576775843794073,
      "grad_norm": 3.9737961292266846,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.7532,
      "step": 9
    },
    {
      "epoch": 0.00017519731597711924,
      "eval_loss": 2.764575719833374,
      "eval_runtime": 1380.799,
      "eval_samples_per_second": 17.406,
      "eval_steps_per_second": 8.703,
      "step": 10
    },
    {
      "epoch": 0.00021023677917254307,
      "grad_norm": 3.4274017810821533,
      "learning_rate": 0.000163742398974869,
      "loss": 2.8338,
      "step": 12
    },
    {
      "epoch": 0.00026279597396567885,
      "grad_norm": 2.62567138671875,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.7121,
      "step": 15
    },
    {
      "epoch": 0.00026279597396567885,
      "eval_loss": 2.642612934112549,
      "eval_runtime": 1381.9033,
      "eval_samples_per_second": 17.392,
      "eval_steps_per_second": 8.696,
      "step": 15
    },
    {
      "epoch": 0.0003153551687588146,
      "grad_norm": 2.2296853065490723,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.6752,
      "step": 18
    },
    {
      "epoch": 0.00035039463195423847,
      "eval_loss": 2.568502187728882,
      "eval_runtime": 1380.1266,
      "eval_samples_per_second": 17.414,
      "eval_steps_per_second": 8.707,
      "step": 20
    },
    {
      "epoch": 0.0003679143635519504,
      "grad_norm": 2.19140362739563,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.7154,
      "step": 21
    },
    {
      "epoch": 0.00042047355834508613,
      "grad_norm": 2.177623987197876,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.3971,
      "step": 24
    },
    {
      "epoch": 0.0004379932899427981,
      "eval_loss": 2.5534322261810303,
      "eval_runtime": 1380.0307,
      "eval_samples_per_second": 17.416,
      "eval_steps_per_second": 8.708,
      "step": 25
    },
    {
      "epoch": 0.00047303275313822195,
      "grad_norm": 1.7770730257034302,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.617,
      "step": 27
    },
    {
      "epoch": 0.0005255919479313577,
      "grad_norm": 1.8957409858703613,
      "learning_rate": 0.0,
      "loss": 2.5408,
      "step": 30
    },
    {
      "epoch": 0.0005255919479313577,
      "eval_loss": 2.5499963760375977,
      "eval_runtime": 1380.394,
      "eval_samples_per_second": 17.411,
      "eval_steps_per_second": 8.705,
      "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": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}