{
  "best_metric": 1.547580361366272,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.02321981424148607,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007739938080495357,
      "eval_loss": 1.9034968614578247,
      "eval_runtime": 37.049,
      "eval_samples_per_second": 14.71,
      "eval_steps_per_second": 7.369,
      "step": 1
    },
    {
      "epoch": 0.0023219814241486067,
      "grad_norm": 0.8577848672866821,
      "learning_rate": 0.00012,
      "loss": 1.7452,
      "step": 3
    },
    {
      "epoch": 0.003869969040247678,
      "eval_loss": 1.8057101964950562,
      "eval_runtime": 35.978,
      "eval_samples_per_second": 15.148,
      "eval_steps_per_second": 7.588,
      "step": 5
    },
    {
      "epoch": 0.0046439628482972135,
      "grad_norm": 1.0533894300460815,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.6628,
      "step": 6
    },
    {
      "epoch": 0.00696594427244582,
      "grad_norm": 0.6069959998130798,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.2944,
      "step": 9
    },
    {
      "epoch": 0.007739938080495356,
      "eval_loss": 1.6238172054290771,
      "eval_runtime": 36.0377,
      "eval_samples_per_second": 15.123,
      "eval_steps_per_second": 7.575,
      "step": 10
    },
    {
      "epoch": 0.009287925696594427,
      "grad_norm": 0.7501858472824097,
      "learning_rate": 0.000163742398974869,
      "loss": 1.2634,
      "step": 12
    },
    {
      "epoch": 0.011609907120743035,
      "grad_norm": 0.6477680206298828,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.4681,
      "step": 15
    },
    {
      "epoch": 0.011609907120743035,
      "eval_loss": 1.5720973014831543,
      "eval_runtime": 36.032,
      "eval_samples_per_second": 15.125,
      "eval_steps_per_second": 7.577,
      "step": 15
    },
    {
      "epoch": 0.01393188854489164,
      "grad_norm": 0.6650062799453735,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.4093,
      "step": 18
    },
    {
      "epoch": 0.015479876160990712,
      "eval_loss": 1.5553081035614014,
      "eval_runtime": 36.0132,
      "eval_samples_per_second": 15.133,
      "eval_steps_per_second": 7.581,
      "step": 20
    },
    {
      "epoch": 0.016253869969040248,
      "grad_norm": 0.8542360067367554,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.7232,
      "step": 21
    },
    {
      "epoch": 0.018575851393188854,
      "grad_norm": 0.7060607075691223,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.4711,
      "step": 24
    },
    {
      "epoch": 0.01934984520123839,
      "eval_loss": 1.5487457513809204,
      "eval_runtime": 35.9901,
      "eval_samples_per_second": 15.143,
      "eval_steps_per_second": 7.585,
      "step": 25
    },
    {
      "epoch": 0.02089783281733746,
      "grad_norm": 0.7153496742248535,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.6556,
      "step": 27
    },
    {
      "epoch": 0.02321981424148607,
      "grad_norm": 0.8175066113471985,
      "learning_rate": 0.0,
      "loss": 1.2415,
      "step": 30
    },
    {
      "epoch": 0.02321981424148607,
      "eval_loss": 1.547580361366272,
      "eval_runtime": 36.0882,
      "eval_samples_per_second": 15.102,
      "eval_steps_per_second": 7.565,
      "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": 1.3724914745868288e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}