{
  "best_metric": 1.001101016998291,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.2089864158829676,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008359456635318705,
      "grad_norm": 0.528317391872406,
      "learning_rate": 5e-05,
      "loss": 1.0432,
      "step": 1
    },
    {
      "epoch": 0.008359456635318705,
      "eval_loss": 1.539870023727417,
      "eval_runtime": 1.8349,
      "eval_samples_per_second": 27.25,
      "eval_steps_per_second": 7.085,
      "step": 1
    },
    {
      "epoch": 0.01671891327063741,
      "grad_norm": 0.8531002998352051,
      "learning_rate": 0.0001,
      "loss": 1.4622,
      "step": 2
    },
    {
      "epoch": 0.025078369905956112,
      "grad_norm": 0.7735457420349121,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.4612,
      "step": 3
    },
    {
      "epoch": 0.03343782654127482,
      "grad_norm": 0.7207358479499817,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.4384,
      "step": 4
    },
    {
      "epoch": 0.04179728317659352,
      "grad_norm": 0.7249660491943359,
      "learning_rate": 9.913533761814537e-05,
      "loss": 1.3701,
      "step": 5
    },
    {
      "epoch": 0.050156739811912224,
      "grad_norm": 0.7058163285255432,
      "learning_rate": 9.846666218300807e-05,
      "loss": 1.3037,
      "step": 6
    },
    {
      "epoch": 0.05851619644723093,
      "grad_norm": 0.730956494808197,
      "learning_rate": 9.761185582727977e-05,
      "loss": 1.3047,
      "step": 7
    },
    {
      "epoch": 0.06687565308254964,
      "grad_norm": 0.663693904876709,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.2384,
      "step": 8
    },
    {
      "epoch": 0.07523510971786834,
      "grad_norm": 0.5950675010681152,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.2468,
      "step": 9
    },
    {
      "epoch": 0.08359456635318704,
      "grad_norm": 0.5878185033798218,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.201,
      "step": 10
    },
    {
      "epoch": 0.09195402298850575,
      "grad_norm": 0.7090585827827454,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.2783,
      "step": 11
    },
    {
      "epoch": 0.10031347962382445,
      "grad_norm": 0.6280428767204285,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.2595,
      "step": 12
    },
    {
      "epoch": 0.10867293625914315,
      "grad_norm": 0.6365631818771362,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.9264,
      "step": 13
    },
    {
      "epoch": 0.11703239289446186,
      "grad_norm": 0.5153186917304993,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.0121,
      "step": 14
    },
    {
      "epoch": 0.12539184952978055,
      "grad_norm": 0.44470345973968506,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.0041,
      "step": 15
    },
    {
      "epoch": 0.13375130616509928,
      "grad_norm": 0.4626646339893341,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.0477,
      "step": 16
    },
    {
      "epoch": 0.14211076280041798,
      "grad_norm": 0.46722468733787537,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.1018,
      "step": 17
    },
    {
      "epoch": 0.15047021943573669,
      "grad_norm": 0.46091338992118835,
      "learning_rate": 7.75e-05,
      "loss": 1.1099,
      "step": 18
    },
    {
      "epoch": 0.1588296760710554,
      "grad_norm": 0.3986632227897644,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.1126,
      "step": 19
    },
    {
      "epoch": 0.1671891327063741,
      "grad_norm": 0.38878515362739563,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.0734,
      "step": 20
    },
    {
      "epoch": 0.1755485893416928,
      "grad_norm": 0.4430249333381653,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.1306,
      "step": 21
    },
    {
      "epoch": 0.1839080459770115,
      "grad_norm": 0.49307769536972046,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.0652,
      "step": 22
    },
    {
      "epoch": 0.1922675026123302,
      "grad_norm": 0.4030891954898834,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.1236,
      "step": 23
    },
    {
      "epoch": 0.2006269592476489,
      "grad_norm": 0.43994420766830444,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.1189,
      "step": 24
    },
    {
      "epoch": 0.2089864158829676,
      "grad_norm": 0.4256235361099243,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.0948,
      "step": 25
    },
    {
      "epoch": 0.2089864158829676,
      "eval_loss": 1.001101016998291,
      "eval_runtime": 1.1638,
      "eval_samples_per_second": 42.962,
      "eval_steps_per_second": 11.17,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.114626154561536e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}