{
  "best_metric": 0.44344472885131836,
  "best_model_checkpoint": "miner_id_24/checkpoint-258",
  "epoch": 0.7972190034762456,
  "eval_steps": 43,
  "global_step": 258,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003089996137504828,
      "eval_loss": 0.9680678844451904,
      "eval_runtime": 70.6551,
      "eval_samples_per_second": 21.555,
      "eval_steps_per_second": 1.359,
      "step": 1
    },
    {
      "epoch": 0.1328698339127076,
      "grad_norm": 4.317602157592773,
      "learning_rate": 0.000172,
      "loss": 5.2607,
      "step": 43
    },
    {
      "epoch": 0.1328698339127076,
      "eval_loss": 0.5098581314086914,
      "eval_runtime": 70.3781,
      "eval_samples_per_second": 21.64,
      "eval_steps_per_second": 1.364,
      "step": 43
    },
    {
      "epoch": 0.2657396678254152,
      "grad_norm": 3.0645856857299805,
      "learning_rate": 0.000344,
      "loss": 3.7852,
      "step": 86
    },
    {
      "epoch": 0.2657396678254152,
      "eval_loss": 0.47387948632240295,
      "eval_runtime": 70.3748,
      "eval_samples_per_second": 21.641,
      "eval_steps_per_second": 1.364,
      "step": 86
    },
    {
      "epoch": 0.3986095017381228,
      "grad_norm": 2.754756212234497,
      "learning_rate": 0.0003999991994587628,
      "loss": 3.5777,
      "step": 129
    },
    {
      "epoch": 0.3986095017381228,
      "eval_loss": 0.4599356949329376,
      "eval_runtime": 70.5469,
      "eval_samples_per_second": 21.588,
      "eval_steps_per_second": 1.361,
      "step": 129
    },
    {
      "epoch": 0.5314793356508304,
      "grad_norm": 3.3679282665252686,
      "learning_rate": 0.00039999506540847,
      "loss": 3.5413,
      "step": 172
    },
    {
      "epoch": 0.5314793356508304,
      "eval_loss": 0.4521632790565491,
      "eval_runtime": 70.6931,
      "eval_samples_per_second": 21.544,
      "eval_steps_per_second": 1.358,
      "step": 172
    },
    {
      "epoch": 0.6643491695635381,
      "grad_norm": 3.5148468017578125,
      "learning_rate": 0.00039998741135094016,
      "loss": 3.5797,
      "step": 215
    },
    {
      "epoch": 0.6643491695635381,
      "eval_loss": 0.44831588864326477,
      "eval_runtime": 71.0876,
      "eval_samples_per_second": 21.424,
      "eval_steps_per_second": 1.35,
      "step": 215
    },
    {
      "epoch": 0.7972190034762456,
      "grad_norm": 3.9321422576904297,
      "learning_rate": 0.00039997623742088825,
      "loss": 3.5561,
      "step": 258
    },
    {
      "epoch": 0.7972190034762456,
      "eval_loss": 0.44344472885131836,
      "eval_runtime": 70.4613,
      "eval_samples_per_second": 21.615,
      "eval_steps_per_second": 1.362,
      "step": 258
    }
  ],
  "logging_steps": 43,
  "max_steps": 32300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 43,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3502583541145272e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}