{
  "best_metric": 1.4706422090530396,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.008259343382201115,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002753114460733705,
      "eval_loss": 1.6776834726333618,
      "eval_runtime": 565.3728,
      "eval_samples_per_second": 5.411,
      "eval_steps_per_second": 1.353,
      "step": 1
    },
    {
      "epoch": 0.0008259343382201115,
      "grad_norm": 1.4549866914749146,
      "learning_rate": 0.00012,
      "loss": 6.8102,
      "step": 3
    },
    {
      "epoch": 0.0013765572303668526,
      "eval_loss": 1.633891224861145,
      "eval_runtime": 566.9521,
      "eval_samples_per_second": 5.396,
      "eval_steps_per_second": 1.349,
      "step": 5
    },
    {
      "epoch": 0.001651868676440223,
      "grad_norm": 2.4863996505737305,
      "learning_rate": 0.0001992114701314478,
      "loss": 6.4763,
      "step": 6
    },
    {
      "epoch": 0.0024778030146603344,
      "grad_norm": 2.857356071472168,
      "learning_rate": 0.00018763066800438636,
      "loss": 5.7785,
      "step": 9
    },
    {
      "epoch": 0.002753114460733705,
      "eval_loss": 1.5512588024139404,
      "eval_runtime": 565.6939,
      "eval_samples_per_second": 5.408,
      "eval_steps_per_second": 1.352,
      "step": 10
    },
    {
      "epoch": 0.003303737352880446,
      "grad_norm": 1.9613248109817505,
      "learning_rate": 0.000163742398974869,
      "loss": 5.9518,
      "step": 12
    },
    {
      "epoch": 0.0041296716911005575,
      "grad_norm": 1.704720139503479,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.1739,
      "step": 15
    },
    {
      "epoch": 0.0041296716911005575,
      "eval_loss": 1.5082776546478271,
      "eval_runtime": 566.6509,
      "eval_samples_per_second": 5.398,
      "eval_steps_per_second": 1.35,
      "step": 15
    },
    {
      "epoch": 0.004955606029320669,
      "grad_norm": 1.9121348857879639,
      "learning_rate": 9.372094804706867e-05,
      "loss": 5.8429,
      "step": 18
    },
    {
      "epoch": 0.00550622892146741,
      "eval_loss": 1.482903242111206,
      "eval_runtime": 563.6215,
      "eval_samples_per_second": 5.427,
      "eval_steps_per_second": 1.357,
      "step": 20
    },
    {
      "epoch": 0.005781540367540781,
      "grad_norm": 1.5870171785354614,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 6.2068,
      "step": 21
    },
    {
      "epoch": 0.006607474705760892,
      "grad_norm": 1.581892728805542,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 5.4184,
      "step": 24
    },
    {
      "epoch": 0.006882786151834262,
      "eval_loss": 1.4732974767684937,
      "eval_runtime": 565.2388,
      "eval_samples_per_second": 5.412,
      "eval_steps_per_second": 1.353,
      "step": 25
    },
    {
      "epoch": 0.007433409043981004,
      "grad_norm": 2.517833709716797,
      "learning_rate": 7.022351411174866e-06,
      "loss": 6.0225,
      "step": 27
    },
    {
      "epoch": 0.008259343382201115,
      "grad_norm": 3.1702394485473633,
      "learning_rate": 0.0,
      "loss": 5.9461,
      "step": 30
    },
    {
      "epoch": 0.008259343382201115,
      "eval_loss": 1.4706422090530396,
      "eval_runtime": 565.5253,
      "eval_samples_per_second": 5.409,
      "eval_steps_per_second": 1.353,
      "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": 7165736858419200.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}