{
  "best_metric": 1.6394846439361572,
  "best_model_checkpoint": "miner_id_24/checkpoint-2100",
  "epoch": 3.5276825085742285,
  "eval_steps": 300,
  "global_step": 2700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013065490772497142,
      "eval_loss": 3.499333381652832,
      "eval_runtime": 47.0271,
      "eval_samples_per_second": 54.819,
      "eval_steps_per_second": 6.868,
      "step": 1
    },
    {
      "epoch": 0.39196472317491426,
      "grad_norm": 4.633114814758301,
      "learning_rate": 0.00039532411114201737,
      "loss": 1.9459,
      "step": 300
    },
    {
      "epoch": 0.39196472317491426,
      "eval_loss": 2.0433712005615234,
      "eval_runtime": 47.5709,
      "eval_samples_per_second": 54.193,
      "eval_steps_per_second": 6.79,
      "step": 300
    },
    {
      "epoch": 0.7839294463498285,
      "grad_norm": 3.9566309452056885,
      "learning_rate": 0.00037137143523351785,
      "loss": 1.7489,
      "step": 600
    },
    {
      "epoch": 0.7839294463498285,
      "eval_loss": 1.894108533859253,
      "eval_runtime": 47.5795,
      "eval_samples_per_second": 54.183,
      "eval_steps_per_second": 6.789,
      "step": 600
    },
    {
      "epoch": 1.1758941695247427,
      "grad_norm": 1.6150318384170532,
      "learning_rate": 0.00032947725695636553,
      "loss": 1.6123,
      "step": 900
    },
    {
      "epoch": 1.1758941695247427,
      "eval_loss": 1.7152339220046997,
      "eval_runtime": 47.4517,
      "eval_samples_per_second": 54.329,
      "eval_steps_per_second": 6.807,
      "step": 900
    },
    {
      "epoch": 1.567858892699657,
      "grad_norm": 1.470030665397644,
      "learning_rate": 0.0002740276310679829,
      "loss": 1.5098,
      "step": 1200
    },
    {
      "epoch": 1.567858892699657,
      "eval_loss": 1.6758149862289429,
      "eval_runtime": 47.7321,
      "eval_samples_per_second": 54.01,
      "eval_steps_per_second": 6.767,
      "step": 1200
    },
    {
      "epoch": 1.9598236158745714,
      "grad_norm": 1.277234673500061,
      "learning_rate": 0.00021082778171708353,
      "loss": 1.4944,
      "step": 1500
    },
    {
      "epoch": 1.9598236158745714,
      "eval_loss": 1.639987826347351,
      "eval_runtime": 47.5572,
      "eval_samples_per_second": 54.208,
      "eval_steps_per_second": 6.792,
      "step": 1500
    },
    {
      "epoch": 2.3517883390494854,
      "grad_norm": 0.6984204649925232,
      "learning_rate": 0.00014649433229415587,
      "loss": 1.2823,
      "step": 1800
    },
    {
      "epoch": 2.3517883390494854,
      "eval_loss": 1.6630264520645142,
      "eval_runtime": 47.5836,
      "eval_samples_per_second": 54.178,
      "eval_steps_per_second": 6.788,
      "step": 1800
    },
    {
      "epoch": 2.7437530622243997,
      "grad_norm": 0.7043100595474243,
      "learning_rate": 8.776258692752355e-05,
      "loss": 1.2428,
      "step": 2100
    },
    {
      "epoch": 2.7437530622243997,
      "eval_loss": 1.6394846439361572,
      "eval_runtime": 47.4121,
      "eval_samples_per_second": 54.374,
      "eval_steps_per_second": 6.813,
      "step": 2100
    },
    {
      "epoch": 3.135717785399314,
      "grad_norm": 0.5809474587440491,
      "learning_rate": 4.078138685887125e-05,
      "loss": 1.1651,
      "step": 2400
    },
    {
      "epoch": 3.135717785399314,
      "eval_loss": 1.7228788137435913,
      "eval_runtime": 47.5011,
      "eval_samples_per_second": 54.272,
      "eval_steps_per_second": 6.8,
      "step": 2400
    },
    {
      "epoch": 3.5276825085742285,
      "grad_norm": 0.49852386116981506,
      "learning_rate": 1.0469365763439531e-05,
      "loss": 1.0362,
      "step": 2700
    },
    {
      "epoch": 3.5276825085742285,
      "eval_loss": 1.6997878551483154,
      "eval_runtime": 47.5528,
      "eval_samples_per_second": 54.213,
      "eval_steps_per_second": 6.792,
      "step": 2700
    }
  ],
  "logging_steps": 300,
  "max_steps": 3000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 300,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1127910524203827e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}