{
  "best_metric": 1.2926114797592163,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.018550007729169888,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006183335909723295,
      "eval_loss": 2.0126826763153076,
      "eval_runtime": 39.779,
      "eval_samples_per_second": 17.12,
      "eval_steps_per_second": 8.572,
      "step": 1
    },
    {
      "epoch": 0.0018550007729169888,
      "grad_norm": 1.9585036039352417,
      "learning_rate": 0.00012,
      "loss": 1.8567,
      "step": 3
    },
    {
      "epoch": 0.003091667954861648,
      "eval_loss": 1.8565876483917236,
      "eval_runtime": 39.295,
      "eval_samples_per_second": 17.33,
      "eval_steps_per_second": 8.678,
      "step": 5
    },
    {
      "epoch": 0.0037100015458339775,
      "grad_norm": 2.4216468334198,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.7559,
      "step": 6
    },
    {
      "epoch": 0.005565002318750966,
      "grad_norm": 1.4596807956695557,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.3623,
      "step": 9
    },
    {
      "epoch": 0.006183335909723296,
      "eval_loss": 1.5231108665466309,
      "eval_runtime": 39.287,
      "eval_samples_per_second": 17.334,
      "eval_steps_per_second": 8.68,
      "step": 10
    },
    {
      "epoch": 0.007420003091667955,
      "grad_norm": 1.6717714071273804,
      "learning_rate": 0.000163742398974869,
      "loss": 1.458,
      "step": 12
    },
    {
      "epoch": 0.009275003864584944,
      "grad_norm": 1.5961047410964966,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5404,
      "step": 15
    },
    {
      "epoch": 0.009275003864584944,
      "eval_loss": 1.3745887279510498,
      "eval_runtime": 39.337,
      "eval_samples_per_second": 17.312,
      "eval_steps_per_second": 8.669,
      "step": 15
    },
    {
      "epoch": 0.011130004637501932,
      "grad_norm": 1.4940749406814575,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.2339,
      "step": 18
    },
    {
      "epoch": 0.012366671819446591,
      "eval_loss": 1.321155309677124,
      "eval_runtime": 39.3011,
      "eval_samples_per_second": 17.328,
      "eval_steps_per_second": 8.677,
      "step": 20
    },
    {
      "epoch": 0.01298500541041892,
      "grad_norm": 1.2504786252975464,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.2214,
      "step": 21
    },
    {
      "epoch": 0.01484000618333591,
      "grad_norm": 1.550596833229065,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.3383,
      "step": 24
    },
    {
      "epoch": 0.015458339774308239,
      "eval_loss": 1.29700767993927,
      "eval_runtime": 39.2856,
      "eval_samples_per_second": 17.335,
      "eval_steps_per_second": 8.68,
      "step": 25
    },
    {
      "epoch": 0.016695006956252898,
      "grad_norm": 1.3250375986099243,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.2531,
      "step": 27
    },
    {
      "epoch": 0.018550007729169888,
      "grad_norm": 1.3671680688858032,
      "learning_rate": 0.0,
      "loss": 1.1492,
      "step": 30
    },
    {
      "epoch": 0.018550007729169888,
      "eval_loss": 1.2926114797592163,
      "eval_runtime": 39.3205,
      "eval_samples_per_second": 17.319,
      "eval_steps_per_second": 8.672,
      "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": 1.1221045163851776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}