{
  "best_metric": 1.4820817708969116,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.212630236019562,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00042526047203912394,
      "eval_loss": 1.9815311431884766,
      "eval_runtime": 16.6153,
      "eval_samples_per_second": 59.584,
      "eval_steps_per_second": 14.926,
      "step": 1
    },
    {
      "epoch": 0.0212630236019562,
      "grad_norm": 3.432788610458374,
      "learning_rate": 0.000218,
      "loss": 3.6234,
      "step": 50
    },
    {
      "epoch": 0.0212630236019562,
      "eval_loss": 1.6699233055114746,
      "eval_runtime": 16.6431,
      "eval_samples_per_second": 59.484,
      "eval_steps_per_second": 14.901,
      "step": 50
    },
    {
      "epoch": 0.0425260472039124,
      "grad_norm": 5.106495380401611,
      "learning_rate": 0.00021142649566566402,
      "loss": 3.2122,
      "step": 100
    },
    {
      "epoch": 0.0425260472039124,
      "eval_loss": 1.5982940196990967,
      "eval_runtime": 16.6121,
      "eval_samples_per_second": 59.595,
      "eval_steps_per_second": 14.929,
      "step": 100
    },
    {
      "epoch": 0.0637890708058686,
      "grad_norm": 2.0981123447418213,
      "learning_rate": 0.0001924988442999686,
      "loss": 3.1573,
      "step": 150
    },
    {
      "epoch": 0.0637890708058686,
      "eval_loss": 1.5603516101837158,
      "eval_runtime": 16.5941,
      "eval_samples_per_second": 59.66,
      "eval_steps_per_second": 14.945,
      "step": 150
    },
    {
      "epoch": 0.0850520944078248,
      "grad_norm": 4.763351917266846,
      "learning_rate": 0.00016350000000000002,
      "loss": 3.1364,
      "step": 200
    },
    {
      "epoch": 0.0850520944078248,
      "eval_loss": 1.5375880002975464,
      "eval_runtime": 16.667,
      "eval_samples_per_second": 59.399,
      "eval_steps_per_second": 14.88,
      "step": 200
    },
    {
      "epoch": 0.106315118009781,
      "grad_norm": 5.718186855316162,
      "learning_rate": 0.00012792765136569544,
      "loss": 3.0396,
      "step": 250
    },
    {
      "epoch": 0.106315118009781,
      "eval_loss": 1.5229949951171875,
      "eval_runtime": 16.5927,
      "eval_samples_per_second": 59.665,
      "eval_steps_per_second": 14.946,
      "step": 250
    },
    {
      "epoch": 0.1275781416117372,
      "grad_norm": 4.68707799911499,
      "learning_rate": 9.00723486343046e-05,
      "loss": 3.001,
      "step": 300
    },
    {
      "epoch": 0.1275781416117372,
      "eval_loss": 1.505061149597168,
      "eval_runtime": 16.5996,
      "eval_samples_per_second": 59.64,
      "eval_steps_per_second": 14.94,
      "step": 300
    },
    {
      "epoch": 0.1488411652136934,
      "grad_norm": 4.057254791259766,
      "learning_rate": 5.450000000000003e-05,
      "loss": 2.9998,
      "step": 350
    },
    {
      "epoch": 0.1488411652136934,
      "eval_loss": 1.4966707229614258,
      "eval_runtime": 16.6457,
      "eval_samples_per_second": 59.475,
      "eval_steps_per_second": 14.899,
      "step": 350
    },
    {
      "epoch": 0.1701041888156496,
      "grad_norm": 3.0910041332244873,
      "learning_rate": 2.550115570003141e-05,
      "loss": 2.9899,
      "step": 400
    },
    {
      "epoch": 0.1701041888156496,
      "eval_loss": 1.486367106437683,
      "eval_runtime": 16.6009,
      "eval_samples_per_second": 59.635,
      "eval_steps_per_second": 14.939,
      "step": 400
    },
    {
      "epoch": 0.1913672124176058,
      "grad_norm": 1.9594502449035645,
      "learning_rate": 6.573504334335994e-06,
      "loss": 2.965,
      "step": 450
    },
    {
      "epoch": 0.1913672124176058,
      "eval_loss": 1.4858981370925903,
      "eval_runtime": 16.6,
      "eval_samples_per_second": 59.639,
      "eval_steps_per_second": 14.94,
      "step": 450
    },
    {
      "epoch": 0.212630236019562,
      "grad_norm": 3.2577598094940186,
      "learning_rate": 0.0,
      "loss": 2.9982,
      "step": 500
    },
    {
      "epoch": 0.212630236019562,
      "eval_loss": 1.4820817708969116,
      "eval_runtime": 16.6053,
      "eval_samples_per_second": 59.62,
      "eval_steps_per_second": 14.935,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "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": 6613636428595200.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}