{
  "best_metric": 11.931824684143066,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.012759170653907496,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 11.931965827941895,
      "eval_runtime": 13.4611,
      "eval_samples_per_second": 73.545,
      "eval_steps_per_second": 36.773,
      "step": 1
    },
    {
      "epoch": 0.0012759170653907496,
      "grad_norm": 0.014513014815747738,
      "learning_rate": 1.5e-05,
      "loss": 11.932,
      "step": 3
    },
    {
      "epoch": 0.002126528442317916,
      "eval_loss": 11.931958198547363,
      "eval_runtime": 14.6689,
      "eval_samples_per_second": 67.49,
      "eval_steps_per_second": 33.745,
      "step": 5
    },
    {
      "epoch": 0.002551834130781499,
      "grad_norm": 0.014365456998348236,
      "learning_rate": 3e-05,
      "loss": 11.931,
      "step": 6
    },
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 0.01398945041000843,
      "learning_rate": 4.5e-05,
      "loss": 11.9308,
      "step": 9
    },
    {
      "epoch": 0.004253056884635832,
      "eval_loss": 11.931923866271973,
      "eval_runtime": 14.5223,
      "eval_samples_per_second": 68.171,
      "eval_steps_per_second": 34.085,
      "step": 10
    },
    {
      "epoch": 0.005103668261562998,
      "grad_norm": 0.010259094648063183,
      "learning_rate": 4.877641290737884e-05,
      "loss": 11.9327,
      "step": 12
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 0.011632326059043407,
      "learning_rate": 4.267766952966369e-05,
      "loss": 11.9342,
      "step": 15
    },
    {
      "epoch": 0.006379585326953748,
      "eval_loss": 11.931878089904785,
      "eval_runtime": 14.0328,
      "eval_samples_per_second": 70.549,
      "eval_steps_per_second": 35.275,
      "step": 15
    },
    {
      "epoch": 0.007655502392344498,
      "grad_norm": 0.015634937211871147,
      "learning_rate": 3.272542485937369e-05,
      "loss": 11.9305,
      "step": 18
    },
    {
      "epoch": 0.008506113769271665,
      "eval_loss": 11.931843757629395,
      "eval_runtime": 14.489,
      "eval_samples_per_second": 68.328,
      "eval_steps_per_second": 34.164,
      "step": 20
    },
    {
      "epoch": 0.008931419457735247,
      "grad_norm": 0.012297064065933228,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 11.9309,
      "step": 21
    },
    {
      "epoch": 0.010207336523125997,
      "grad_norm": 0.016836898401379585,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 11.9325,
      "step": 24
    },
    {
      "epoch": 0.01063264221158958,
      "eval_loss": 11.931828498840332,
      "eval_runtime": 14.0894,
      "eval_samples_per_second": 70.266,
      "eval_steps_per_second": 35.133,
      "step": 25
    },
    {
      "epoch": 0.011483253588516746,
      "grad_norm": 0.011750569567084312,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 11.9329,
      "step": 27
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 0.015399892814457417,
      "learning_rate": 0.0,
      "loss": 11.9333,
      "step": 30
    },
    {
      "epoch": 0.012759170653907496,
      "eval_loss": 11.931824684143066,
      "eval_runtime": 14.4226,
      "eval_samples_per_second": 68.642,
      "eval_steps_per_second": 34.321,
      "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": 11335729152.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}