{
  "best_metric": 1.0043848752975464,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.08523332623055614,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001704666524611123,
      "eval_loss": 1.2497302293777466,
      "eval_runtime": 279.7857,
      "eval_samples_per_second": 8.828,
      "eval_steps_per_second": 2.209,
      "step": 1
    },
    {
      "epoch": 0.008523332623055616,
      "grad_norm": 0.695481538772583,
      "learning_rate": 2.5e-05,
      "loss": 5.2014,
      "step": 50
    },
    {
      "epoch": 0.01704666524611123,
      "grad_norm": 1.0811598300933838,
      "learning_rate": 5e-05,
      "loss": 4.6356,
      "step": 100
    },
    {
      "epoch": 0.025569997869166843,
      "grad_norm": 1.2635670900344849,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 4.1182,
      "step": 150
    },
    {
      "epoch": 0.03409333049222246,
      "grad_norm": 1.1559983491897583,
      "learning_rate": 4.267766952966369e-05,
      "loss": 4.049,
      "step": 200
    },
    {
      "epoch": 0.04261666311527807,
      "grad_norm": 1.2524633407592773,
      "learning_rate": 3.456708580912725e-05,
      "loss": 4.0722,
      "step": 250
    },
    {
      "epoch": 0.051139995738333686,
      "grad_norm": 1.2786623239517212,
      "learning_rate": 2.5e-05,
      "loss": 4.0676,
      "step": 300
    },
    {
      "epoch": 0.0596633283613893,
      "grad_norm": 1.3947089910507202,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 3.9511,
      "step": 350
    },
    {
      "epoch": 0.06818666098444492,
      "grad_norm": 1.28542160987854,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 4.049,
      "step": 400
    },
    {
      "epoch": 0.07670999360750053,
      "grad_norm": 1.590616226196289,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 4.0164,
      "step": 450
    },
    {
      "epoch": 0.08523332623055614,
      "grad_norm": 1.2694787979125977,
      "learning_rate": 0.0,
      "loss": 4.2086,
      "step": 500
    },
    {
      "epoch": 0.08523332623055614,
      "eval_loss": 1.0043848752975464,
      "eval_runtime": 279.5941,
      "eval_samples_per_second": 8.834,
      "eval_steps_per_second": 2.21,
      "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": 3.84149444666327e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}