{
  "best_metric": 1.5677101612091064,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.1718213058419244,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000859106529209622,
      "eval_loss": 2.5483837127685547,
      "eval_runtime": 23.9097,
      "eval_samples_per_second": 20.494,
      "eval_steps_per_second": 5.144,
      "step": 1
    },
    {
      "epoch": 0.00859106529209622,
      "grad_norm": 5.005776882171631,
      "learning_rate": 5.05e-06,
      "loss": 2.3503,
      "step": 10
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 1.9826234579086304,
      "learning_rate": 1.01e-05,
      "loss": 2.2512,
      "step": 20
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 0.8136302828788757,
      "learning_rate": 9.538888888888889e-06,
      "loss": 1.7905,
      "step": 30
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 0.8505245447158813,
      "learning_rate": 8.977777777777778e-06,
      "loss": 1.6465,
      "step": 40
    },
    {
      "epoch": 0.0429553264604811,
      "grad_norm": 1.3877776861190796,
      "learning_rate": 8.416666666666667e-06,
      "loss": 1.7359,
      "step": 50
    },
    {
      "epoch": 0.0429553264604811,
      "eval_loss": 1.639662504196167,
      "eval_runtime": 24.0211,
      "eval_samples_per_second": 20.399,
      "eval_steps_per_second": 5.121,
      "step": 50
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 0.652748167514801,
      "learning_rate": 7.855555555555556e-06,
      "loss": 1.5711,
      "step": 60
    },
    {
      "epoch": 0.06013745704467354,
      "grad_norm": 0.6387035846710205,
      "learning_rate": 7.294444444444444e-06,
      "loss": 1.6766,
      "step": 70
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 0.6020448803901672,
      "learning_rate": 6.733333333333333e-06,
      "loss": 1.5793,
      "step": 80
    },
    {
      "epoch": 0.07731958762886598,
      "grad_norm": 0.7771233320236206,
      "learning_rate": 6.172222222222223e-06,
      "loss": 1.5681,
      "step": 90
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 1.099347472190857,
      "learning_rate": 5.611111111111111e-06,
      "loss": 1.6476,
      "step": 100
    },
    {
      "epoch": 0.0859106529209622,
      "eval_loss": 1.587920069694519,
      "eval_runtime": 24.0797,
      "eval_samples_per_second": 20.349,
      "eval_steps_per_second": 5.108,
      "step": 100
    },
    {
      "epoch": 0.09450171821305842,
      "grad_norm": 0.6418641209602356,
      "learning_rate": 5.05e-06,
      "loss": 1.5007,
      "step": 110
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.5860769748687744,
      "learning_rate": 4.488888888888889e-06,
      "loss": 1.5939,
      "step": 120
    },
    {
      "epoch": 0.11168384879725086,
      "grad_norm": 0.5860627889633179,
      "learning_rate": 3.927777777777778e-06,
      "loss": 1.5596,
      "step": 130
    },
    {
      "epoch": 0.12027491408934708,
      "grad_norm": 0.6728429198265076,
      "learning_rate": 3.3666666666666665e-06,
      "loss": 1.5375,
      "step": 140
    },
    {
      "epoch": 0.12886597938144329,
      "grad_norm": 1.1351910829544067,
      "learning_rate": 2.8055555555555555e-06,
      "loss": 1.5916,
      "step": 150
    },
    {
      "epoch": 0.12886597938144329,
      "eval_loss": 1.571736454963684,
      "eval_runtime": 24.0175,
      "eval_samples_per_second": 20.402,
      "eval_steps_per_second": 5.121,
      "step": 150
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 0.5671700239181519,
      "learning_rate": 2.2444444444444445e-06,
      "loss": 1.4621,
      "step": 160
    },
    {
      "epoch": 0.14604810996563575,
      "grad_norm": 0.6307945847511292,
      "learning_rate": 1.6833333333333332e-06,
      "loss": 1.5589,
      "step": 170
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 0.6016616225242615,
      "learning_rate": 1.1222222222222222e-06,
      "loss": 1.5354,
      "step": 180
    },
    {
      "epoch": 0.16323024054982818,
      "grad_norm": 0.6347000598907471,
      "learning_rate": 5.611111111111111e-07,
      "loss": 1.5171,
      "step": 190
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 1.540158987045288,
      "learning_rate": 0.0,
      "loss": 1.5985,
      "step": 200
    },
    {
      "epoch": 0.1718213058419244,
      "eval_loss": 1.5677101612091064,
      "eval_runtime": 24.0604,
      "eval_samples_per_second": 20.365,
      "eval_steps_per_second": 5.112,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 5.9886658387968e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}