{
  "best_metric": 2.666287899017334,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.000382616458884673,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2753881962822434e-05,
      "eval_loss": 3.4868648052215576,
      "eval_runtime": 4278.1726,
      "eval_samples_per_second": 7.717,
      "eval_steps_per_second": 3.858,
      "step": 1
    },
    {
      "epoch": 3.82616458884673e-05,
      "grad_norm": 1.6738007068634033,
      "learning_rate": 6e-05,
      "loss": 3.5199,
      "step": 3
    },
    {
      "epoch": 6.376940981411218e-05,
      "eval_loss": 3.4390904903411865,
      "eval_runtime": 4295.5009,
      "eval_samples_per_second": 7.686,
      "eval_steps_per_second": 3.843,
      "step": 5
    },
    {
      "epoch": 7.65232917769346e-05,
      "grad_norm": 1.7387325763702393,
      "learning_rate": 0.00012,
      "loss": 3.3451,
      "step": 6
    },
    {
      "epoch": 0.00011478493766540191,
      "grad_norm": 1.915514588356018,
      "learning_rate": 0.00018,
      "loss": 3.2395,
      "step": 9
    },
    {
      "epoch": 0.00012753881962822435,
      "eval_loss": 3.032045841217041,
      "eval_runtime": 4295.6165,
      "eval_samples_per_second": 7.686,
      "eval_steps_per_second": 3.843,
      "step": 10
    },
    {
      "epoch": 0.0001530465835538692,
      "grad_norm": 2.1459999084472656,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.9681,
      "step": 12
    },
    {
      "epoch": 0.0001913082294423365,
      "grad_norm": 1.5466257333755493,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.8409,
      "step": 15
    },
    {
      "epoch": 0.0001913082294423365,
      "eval_loss": 2.7555739879608154,
      "eval_runtime": 4291.7816,
      "eval_samples_per_second": 7.692,
      "eval_steps_per_second": 3.846,
      "step": 15
    },
    {
      "epoch": 0.00022956987533080382,
      "grad_norm": 1.3524450063705444,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.7526,
      "step": 18
    },
    {
      "epoch": 0.0002550776392564487,
      "eval_loss": 2.691340923309326,
      "eval_runtime": 4290.55,
      "eval_samples_per_second": 7.695,
      "eval_steps_per_second": 3.847,
      "step": 20
    },
    {
      "epoch": 0.0002678315212192711,
      "grad_norm": 1.37107253074646,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.7938,
      "step": 21
    },
    {
      "epoch": 0.0003060931671077384,
      "grad_norm": 1.5554951429367065,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.7326,
      "step": 24
    },
    {
      "epoch": 0.00031884704907056085,
      "eval_loss": 2.6710398197174072,
      "eval_runtime": 4289.0441,
      "eval_samples_per_second": 7.697,
      "eval_steps_per_second": 3.849,
      "step": 25
    },
    {
      "epoch": 0.00034435481299620573,
      "grad_norm": 1.6495437622070312,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.7699,
      "step": 27
    },
    {
      "epoch": 0.000382616458884673,
      "grad_norm": 1.6575912237167358,
      "learning_rate": 0.0,
      "loss": 2.7252,
      "step": 30
    },
    {
      "epoch": 0.000382616458884673,
      "eval_loss": 2.666287899017334,
      "eval_runtime": 4290.9939,
      "eval_samples_per_second": 7.694,
      "eval_steps_per_second": 3.847,
      "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": 1.112850252693504e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}