{
  "best_metric": 1.3719592094421387,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.01422475106685633,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005689900426742532,
      "grad_norm": 1.732013463973999,
      "learning_rate": 2e-05,
      "loss": 6.0004,
      "step": 1
    },
    {
      "epoch": 0.0005689900426742532,
      "eval_loss": 1.5131011009216309,
      "eval_runtime": 116.905,
      "eval_samples_per_second": 6.33,
      "eval_steps_per_second": 3.165,
      "step": 1
    },
    {
      "epoch": 0.0011379800853485065,
      "grad_norm": 1.7130495309829712,
      "learning_rate": 4e-05,
      "loss": 6.6271,
      "step": 2
    },
    {
      "epoch": 0.0017069701280227596,
      "grad_norm": 2.198338508605957,
      "learning_rate": 6e-05,
      "loss": 7.4807,
      "step": 3
    },
    {
      "epoch": 0.002275960170697013,
      "grad_norm": 2.2081143856048584,
      "learning_rate": 8e-05,
      "loss": 8.7104,
      "step": 4
    },
    {
      "epoch": 0.002844950213371266,
      "grad_norm": 1.5882880687713623,
      "learning_rate": 0.0001,
      "loss": 6.7147,
      "step": 5
    },
    {
      "epoch": 0.002844950213371266,
      "eval_loss": 1.5044010877609253,
      "eval_runtime": 115.6383,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 3.2,
      "step": 5
    },
    {
      "epoch": 0.0034139402560455193,
      "grad_norm": 1.4717925786972046,
      "learning_rate": 0.00012,
      "loss": 4.0462,
      "step": 6
    },
    {
      "epoch": 0.003982930298719772,
      "grad_norm": 2.0216853618621826,
      "learning_rate": 0.00014,
      "loss": 5.9091,
      "step": 7
    },
    {
      "epoch": 0.004551920341394026,
      "grad_norm": 1.7940618991851807,
      "learning_rate": 0.00016,
      "loss": 4.312,
      "step": 8
    },
    {
      "epoch": 0.005120910384068279,
      "grad_norm": 2.1044986248016357,
      "learning_rate": 0.00018,
      "loss": 5.6228,
      "step": 9
    },
    {
      "epoch": 0.005689900426742532,
      "grad_norm": 3.0336008071899414,
      "learning_rate": 0.0002,
      "loss": 5.4563,
      "step": 10
    },
    {
      "epoch": 0.005689900426742532,
      "eval_loss": 1.4492992162704468,
      "eval_runtime": 126.3834,
      "eval_samples_per_second": 5.855,
      "eval_steps_per_second": 2.928,
      "step": 10
    },
    {
      "epoch": 0.006258890469416785,
      "grad_norm": 2.8724112510681152,
      "learning_rate": 0.00019781476007338058,
      "loss": 5.1733,
      "step": 11
    },
    {
      "epoch": 0.0068278805120910386,
      "grad_norm": 2.897056818008423,
      "learning_rate": 0.0001913545457642601,
      "loss": 4.9277,
      "step": 12
    },
    {
      "epoch": 0.007396870554765292,
      "grad_norm": 1.9220606088638306,
      "learning_rate": 0.00018090169943749476,
      "loss": 3.0438,
      "step": 13
    },
    {
      "epoch": 0.007965860597439544,
      "grad_norm": 4.364326000213623,
      "learning_rate": 0.00016691306063588583,
      "loss": 5.4731,
      "step": 14
    },
    {
      "epoch": 0.008534850640113799,
      "grad_norm": 3.4079654216766357,
      "learning_rate": 0.00015000000000000001,
      "loss": 6.2501,
      "step": 15
    },
    {
      "epoch": 0.008534850640113799,
      "eval_loss": 1.4071946144104004,
      "eval_runtime": 113.6558,
      "eval_samples_per_second": 6.511,
      "eval_steps_per_second": 3.255,
      "step": 15
    },
    {
      "epoch": 0.009103840682788052,
      "grad_norm": 3.1693203449249268,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.6554,
      "step": 16
    },
    {
      "epoch": 0.009672830725462305,
      "grad_norm": 3.4745993614196777,
      "learning_rate": 0.00011045284632676536,
      "loss": 6.187,
      "step": 17
    },
    {
      "epoch": 0.010241820768136558,
      "grad_norm": 4.106719017028809,
      "learning_rate": 8.954715367323468e-05,
      "loss": 7.185,
      "step": 18
    },
    {
      "epoch": 0.010810810810810811,
      "grad_norm": 4.38962459564209,
      "learning_rate": 6.909830056250527e-05,
      "loss": 7.0849,
      "step": 19
    },
    {
      "epoch": 0.011379800853485065,
      "grad_norm": 3.2297611236572266,
      "learning_rate": 5.000000000000002e-05,
      "loss": 7.1814,
      "step": 20
    },
    {
      "epoch": 0.011379800853485065,
      "eval_loss": 1.3764064311981201,
      "eval_runtime": 116.0269,
      "eval_samples_per_second": 6.378,
      "eval_steps_per_second": 3.189,
      "step": 20
    },
    {
      "epoch": 0.011948790896159318,
      "grad_norm": 2.581949234008789,
      "learning_rate": 3.308693936411421e-05,
      "loss": 5.8999,
      "step": 21
    },
    {
      "epoch": 0.01251778093883357,
      "grad_norm": 2.7319865226745605,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 5.0108,
      "step": 22
    },
    {
      "epoch": 0.013086770981507824,
      "grad_norm": 1.8899096250534058,
      "learning_rate": 8.645454235739903e-06,
      "loss": 3.3853,
      "step": 23
    },
    {
      "epoch": 0.013655761024182077,
      "grad_norm": 3.539898633956909,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 8.5112,
      "step": 24
    },
    {
      "epoch": 0.01422475106685633,
      "grad_norm": 3.2797906398773193,
      "learning_rate": 0.0,
      "loss": 5.732,
      "step": 25
    },
    {
      "epoch": 0.01422475106685633,
      "eval_loss": 1.3719592094421387,
      "eval_runtime": 117.6658,
      "eval_samples_per_second": 6.289,
      "eval_steps_per_second": 3.144,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 5415537676910592.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}