{
  "best_metric": 0.9273862242698669,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.02527379949452401,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008424599831508003,
      "eval_loss": 1.7102633714675903,
      "eval_runtime": 327.8358,
      "eval_samples_per_second": 1.525,
      "eval_steps_per_second": 0.763,
      "step": 1
    },
    {
      "epoch": 0.002527379949452401,
      "grad_norm": 4.6926374435424805,
      "learning_rate": 6e-05,
      "loss": 7.1659,
      "step": 3
    },
    {
      "epoch": 0.004212299915754001,
      "eval_loss": 1.4572758674621582,
      "eval_runtime": 329.8168,
      "eval_samples_per_second": 1.516,
      "eval_steps_per_second": 0.758,
      "step": 5
    },
    {
      "epoch": 0.005054759898904802,
      "grad_norm": 3.720707893371582,
      "learning_rate": 9.96057350657239e-05,
      "loss": 6.1748,
      "step": 6
    },
    {
      "epoch": 0.007582139848357203,
      "grad_norm": 13.290879249572754,
      "learning_rate": 9.381533400219318e-05,
      "loss": 5.0921,
      "step": 9
    },
    {
      "epoch": 0.008424599831508003,
      "eval_loss": 1.0737336874008179,
      "eval_runtime": 329.7783,
      "eval_samples_per_second": 1.516,
      "eval_steps_per_second": 0.758,
      "step": 10
    },
    {
      "epoch": 0.010109519797809604,
      "grad_norm": 5.166086673736572,
      "learning_rate": 8.18711994874345e-05,
      "loss": 4.1518,
      "step": 12
    },
    {
      "epoch": 0.012636899747262006,
      "grad_norm": 2.968581438064575,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.9438,
      "step": 15
    },
    {
      "epoch": 0.012636899747262006,
      "eval_loss": 0.9627827405929565,
      "eval_runtime": 329.8855,
      "eval_samples_per_second": 1.516,
      "eval_steps_per_second": 0.758,
      "step": 15
    },
    {
      "epoch": 0.015164279696714406,
      "grad_norm": 2.9499189853668213,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 3.5457,
      "step": 18
    },
    {
      "epoch": 0.016849199663016005,
      "eval_loss": 0.9386328458786011,
      "eval_runtime": 329.7122,
      "eval_samples_per_second": 1.516,
      "eval_steps_per_second": 0.758,
      "step": 20
    },
    {
      "epoch": 0.017691659646166806,
      "grad_norm": 2.26678466796875,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 3.862,
      "step": 21
    },
    {
      "epoch": 0.020219039595619208,
      "grad_norm": 2.4825687408447266,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 3.3123,
      "step": 24
    },
    {
      "epoch": 0.02106149957877001,
      "eval_loss": 0.9290638566017151,
      "eval_runtime": 329.8404,
      "eval_samples_per_second": 1.516,
      "eval_steps_per_second": 0.758,
      "step": 25
    },
    {
      "epoch": 0.02274641954507161,
      "grad_norm": 2.2778186798095703,
      "learning_rate": 3.511175705587433e-06,
      "loss": 3.9046,
      "step": 27
    },
    {
      "epoch": 0.02527379949452401,
      "grad_norm": 2.4795632362365723,
      "learning_rate": 0.0,
      "loss": 4.1006,
      "step": 30
    },
    {
      "epoch": 0.02527379949452401,
      "eval_loss": 0.9273862242698669,
      "eval_runtime": 329.814,
      "eval_samples_per_second": 1.516,
      "eval_steps_per_second": 0.758,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0586133192638464e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}