{
  "best_metric": 0.7749077677726746,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.016953941791466517,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005651313930488839,
      "eval_loss": 1.4163936376571655,
      "eval_runtime": 690.8771,
      "eval_samples_per_second": 2.157,
      "eval_steps_per_second": 0.54,
      "step": 1
    },
    {
      "epoch": 0.0016953941791466515,
      "grad_norm": 0.2287186235189438,
      "learning_rate": 0.00012,
      "loss": 1.3454,
      "step": 3
    },
    {
      "epoch": 0.0028256569652444193,
      "eval_loss": 1.3175787925720215,
      "eval_runtime": 696.2628,
      "eval_samples_per_second": 2.14,
      "eval_steps_per_second": 0.536,
      "step": 5
    },
    {
      "epoch": 0.003390788358293303,
      "grad_norm": 0.43228718638420105,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.3042,
      "step": 6
    },
    {
      "epoch": 0.005086182537439954,
      "grad_norm": 0.21914565563201904,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.0941,
      "step": 9
    },
    {
      "epoch": 0.005651313930488839,
      "eval_loss": 1.0314421653747559,
      "eval_runtime": 699.9854,
      "eval_samples_per_second": 2.129,
      "eval_steps_per_second": 0.533,
      "step": 10
    },
    {
      "epoch": 0.006781576716586606,
      "grad_norm": 0.2585771381855011,
      "learning_rate": 0.000163742398974869,
      "loss": 0.9694,
      "step": 12
    },
    {
      "epoch": 0.008476970895733259,
      "grad_norm": 0.1790218949317932,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.9023,
      "step": 15
    },
    {
      "epoch": 0.008476970895733259,
      "eval_loss": 0.8702918291091919,
      "eval_runtime": 700.0949,
      "eval_samples_per_second": 2.128,
      "eval_steps_per_second": 0.533,
      "step": 15
    },
    {
      "epoch": 0.010172365074879909,
      "grad_norm": 0.14580154418945312,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.8086,
      "step": 18
    },
    {
      "epoch": 0.011302627860977677,
      "eval_loss": 0.8038806915283203,
      "eval_runtime": 697.027,
      "eval_samples_per_second": 2.138,
      "eval_steps_per_second": 0.535,
      "step": 20
    },
    {
      "epoch": 0.01186775925402656,
      "grad_norm": 0.1351657211780548,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.782,
      "step": 21
    },
    {
      "epoch": 0.013563153433173212,
      "grad_norm": 0.12833859026432037,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.7737,
      "step": 24
    },
    {
      "epoch": 0.014128284826222097,
      "eval_loss": 0.7793111205101013,
      "eval_runtime": 698.6184,
      "eval_samples_per_second": 2.133,
      "eval_steps_per_second": 0.534,
      "step": 25
    },
    {
      "epoch": 0.015258547612319864,
      "grad_norm": 0.13125252723693848,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.7798,
      "step": 27
    },
    {
      "epoch": 0.016953941791466517,
      "grad_norm": 0.13646282255649567,
      "learning_rate": 0.0,
      "loss": 0.7686,
      "step": 30
    },
    {
      "epoch": 0.016953941791466517,
      "eval_loss": 0.7749077677726746,
      "eval_runtime": 696.2618,
      "eval_samples_per_second": 2.14,
      "eval_steps_per_second": 0.536,
      "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": 7.59889303437312e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}