{
  "best_metric": 0.0014202457387000322,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.08087016295337836,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001617403259067567,
      "eval_loss": 0.6103610992431641,
      "eval_runtime": 1006.8545,
      "eval_samples_per_second": 10.343,
      "eval_steps_per_second": 2.586,
      "step": 1
    },
    {
      "epoch": 0.008087016295337835,
      "grad_norm": 2.6788830757141113,
      "learning_rate": 0.000106,
      "loss": 1.0078,
      "step": 50
    },
    {
      "epoch": 0.01617403259067567,
      "grad_norm": 4.463006019592285,
      "learning_rate": 0.000212,
      "loss": 0.0925,
      "step": 100
    },
    {
      "epoch": 0.024261048886013506,
      "grad_norm": 4.31649923324585,
      "learning_rate": 0.0002039312304461964,
      "loss": 0.0873,
      "step": 150
    },
    {
      "epoch": 0.03234806518135134,
      "grad_norm": 3.63008189201355,
      "learning_rate": 0.00018095331880577404,
      "loss": 0.0645,
      "step": 200
    },
    {
      "epoch": 0.04043508147668918,
      "grad_norm": 1.7857822179794312,
      "learning_rate": 0.00014656444383069953,
      "loss": 0.0525,
      "step": 250
    },
    {
      "epoch": 0.04852209777202701,
      "grad_norm": 0.8407556414604187,
      "learning_rate": 0.000106,
      "loss": 0.0327,
      "step": 300
    },
    {
      "epoch": 0.056609114067364845,
      "grad_norm": 2.8419251441955566,
      "learning_rate": 6.543555616930049e-05,
      "loss": 0.0255,
      "step": 350
    },
    {
      "epoch": 0.06469613036270268,
      "grad_norm": 0.30184730887413025,
      "learning_rate": 3.104668119422597e-05,
      "loss": 0.0236,
      "step": 400
    },
    {
      "epoch": 0.07278314665804052,
      "grad_norm": 0.2783595323562622,
      "learning_rate": 8.068769553803605e-06,
      "loss": 0.0102,
      "step": 450
    },
    {
      "epoch": 0.08087016295337836,
      "grad_norm": 0.034443601965904236,
      "learning_rate": 0.0,
      "loss": 0.0078,
      "step": 500
    },
    {
      "epoch": 0.08087016295337836,
      "eval_loss": 0.0014202457387000322,
      "eval_runtime": 1007.1347,
      "eval_samples_per_second": 10.34,
      "eval_steps_per_second": 2.586,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 6.655805110741893e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}