{
  "best_metric": 0.9134324193000793,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.005658242172764994,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001886080724254998,
      "eval_loss": 1.3765872716903687,
      "eval_runtime": 277.0595,
      "eval_samples_per_second": 8.06,
      "eval_steps_per_second": 4.032,
      "step": 1
    },
    {
      "epoch": 0.0005658242172764995,
      "grad_norm": 12.088170051574707,
      "learning_rate": 6e-05,
      "loss": 4.5636,
      "step": 3
    },
    {
      "epoch": 0.000943040362127499,
      "eval_loss": 1.2751835584640503,
      "eval_runtime": 278.1439,
      "eval_samples_per_second": 8.028,
      "eval_steps_per_second": 4.016,
      "step": 5
    },
    {
      "epoch": 0.001131648434552999,
      "grad_norm": 15.993000030517578,
      "learning_rate": 0.00012,
      "loss": 5.2696,
      "step": 6
    },
    {
      "epoch": 0.0016974726518294984,
      "grad_norm": 12.59005069732666,
      "learning_rate": 0.00018,
      "loss": 4.3524,
      "step": 9
    },
    {
      "epoch": 0.001886080724254998,
      "eval_loss": 1.0645207166671753,
      "eval_runtime": 278.0198,
      "eval_samples_per_second": 8.032,
      "eval_steps_per_second": 4.018,
      "step": 10
    },
    {
      "epoch": 0.002263296869105998,
      "grad_norm": 9.773409843444824,
      "learning_rate": 0.00019510565162951537,
      "loss": 4.2777,
      "step": 12
    },
    {
      "epoch": 0.002829121086382497,
      "grad_norm": 12.977853775024414,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.7979,
      "step": 15
    },
    {
      "epoch": 0.002829121086382497,
      "eval_loss": 0.9974586367607117,
      "eval_runtime": 277.9368,
      "eval_samples_per_second": 8.034,
      "eval_steps_per_second": 4.019,
      "step": 15
    },
    {
      "epoch": 0.0033949453036589967,
      "grad_norm": 11.413963317871094,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.9885,
      "step": 18
    },
    {
      "epoch": 0.003772161448509996,
      "eval_loss": 0.941416323184967,
      "eval_runtime": 277.8552,
      "eval_samples_per_second": 8.037,
      "eval_steps_per_second": 4.02,
      "step": 20
    },
    {
      "epoch": 0.003960769520935496,
      "grad_norm": 7.903290271759033,
      "learning_rate": 8.435655349597689e-05,
      "loss": 4.116,
      "step": 21
    },
    {
      "epoch": 0.004526593738211996,
      "grad_norm": 10.213263511657715,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.6046,
      "step": 24
    },
    {
      "epoch": 0.004715201810637495,
      "eval_loss": 0.9226500391960144,
      "eval_runtime": 277.7881,
      "eval_samples_per_second": 8.039,
      "eval_steps_per_second": 4.021,
      "step": 25
    },
    {
      "epoch": 0.005092417955488495,
      "grad_norm": 9.46810531616211,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.6933,
      "step": 27
    },
    {
      "epoch": 0.005658242172764994,
      "grad_norm": 10.925247192382812,
      "learning_rate": 0.0,
      "loss": 3.6785,
      "step": 30
    },
    {
      "epoch": 0.005658242172764994,
      "eval_loss": 0.9134324193000793,
      "eval_runtime": 277.7965,
      "eval_samples_per_second": 8.038,
      "eval_steps_per_second": 4.021,
      "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": 1.054695455981568e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}