{
  "best_metric": 1.529019832611084,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.14925373134328357,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004975124378109453,
      "eval_loss": 2.055938959121704,
      "eval_runtime": 5.2261,
      "eval_samples_per_second": 16.265,
      "eval_steps_per_second": 8.228,
      "step": 1
    },
    {
      "epoch": 0.014925373134328358,
      "grad_norm": 1.077970027923584,
      "learning_rate": 0.00012,
      "loss": 1.9103,
      "step": 3
    },
    {
      "epoch": 0.024875621890547265,
      "eval_loss": 1.9677706956863403,
      "eval_runtime": 4.6653,
      "eval_samples_per_second": 18.219,
      "eval_steps_per_second": 9.217,
      "step": 5
    },
    {
      "epoch": 0.029850746268656716,
      "grad_norm": 1.1067320108413696,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.8832,
      "step": 6
    },
    {
      "epoch": 0.04477611940298507,
      "grad_norm": 1.087184190750122,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.7443,
      "step": 9
    },
    {
      "epoch": 0.04975124378109453,
      "eval_loss": 1.7259494066238403,
      "eval_runtime": 4.6611,
      "eval_samples_per_second": 18.236,
      "eval_steps_per_second": 9.225,
      "step": 10
    },
    {
      "epoch": 0.05970149253731343,
      "grad_norm": 0.9545024633407593,
      "learning_rate": 0.000163742398974869,
      "loss": 1.6985,
      "step": 12
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 0.8490769267082214,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.6776,
      "step": 15
    },
    {
      "epoch": 0.07462686567164178,
      "eval_loss": 1.6065677404403687,
      "eval_runtime": 4.6817,
      "eval_samples_per_second": 18.156,
      "eval_steps_per_second": 9.185,
      "step": 15
    },
    {
      "epoch": 0.08955223880597014,
      "grad_norm": 0.9583144187927246,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.5263,
      "step": 18
    },
    {
      "epoch": 0.09950248756218906,
      "eval_loss": 1.5499287843704224,
      "eval_runtime": 4.6662,
      "eval_samples_per_second": 18.216,
      "eval_steps_per_second": 9.215,
      "step": 20
    },
    {
      "epoch": 0.1044776119402985,
      "grad_norm": 1.0285145044326782,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.4911,
      "step": 21
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 0.8856176733970642,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.5143,
      "step": 24
    },
    {
      "epoch": 0.12437810945273632,
      "eval_loss": 1.5311452150344849,
      "eval_runtime": 4.6651,
      "eval_samples_per_second": 18.22,
      "eval_steps_per_second": 9.217,
      "step": 25
    },
    {
      "epoch": 0.13432835820895522,
      "grad_norm": 0.7971075773239136,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.542,
      "step": 27
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 0.8718319535255432,
      "learning_rate": 0.0,
      "loss": 1.4543,
      "step": 30
    },
    {
      "epoch": 0.14925373134328357,
      "eval_loss": 1.529019832611084,
      "eval_runtime": 4.6718,
      "eval_samples_per_second": 18.194,
      "eval_steps_per_second": 9.204,
      "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": 9801873028546560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}