{
  "best_metric": 0.9259054064750671,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.132890365448505,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004429678848283499,
      "eval_loss": 1.2574131488800049,
      "eval_runtime": 26.372,
      "eval_samples_per_second": 7.205,
      "eval_steps_per_second": 1.82,
      "step": 1
    },
    {
      "epoch": 0.013289036544850499,
      "grad_norm": 4.626389980316162,
      "learning_rate": 0.00012,
      "loss": 4.871,
      "step": 3
    },
    {
      "epoch": 0.0221483942414175,
      "eval_loss": 1.1578865051269531,
      "eval_runtime": 26.8269,
      "eval_samples_per_second": 7.082,
      "eval_steps_per_second": 1.789,
      "step": 5
    },
    {
      "epoch": 0.026578073089700997,
      "grad_norm": 3.5244829654693604,
      "learning_rate": 0.0001992114701314478,
      "loss": 4.5071,
      "step": 6
    },
    {
      "epoch": 0.03986710963455149,
      "grad_norm": 3.0460095405578613,
      "learning_rate": 0.00018763066800438636,
      "loss": 4.0276,
      "step": 9
    },
    {
      "epoch": 0.044296788482835,
      "eval_loss": 1.0519311428070068,
      "eval_runtime": 26.8819,
      "eval_samples_per_second": 7.068,
      "eval_steps_per_second": 1.786,
      "step": 10
    },
    {
      "epoch": 0.053156146179401995,
      "grad_norm": 3.294666051864624,
      "learning_rate": 0.000163742398974869,
      "loss": 3.8937,
      "step": 12
    },
    {
      "epoch": 0.0664451827242525,
      "grad_norm": 3.9453964233398438,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.7398,
      "step": 15
    },
    {
      "epoch": 0.0664451827242525,
      "eval_loss": 0.9935552477836609,
      "eval_runtime": 26.8927,
      "eval_samples_per_second": 7.065,
      "eval_steps_per_second": 1.785,
      "step": 15
    },
    {
      "epoch": 0.07973421926910298,
      "grad_norm": 2.8438596725463867,
      "learning_rate": 9.372094804706867e-05,
      "loss": 3.6897,
      "step": 18
    },
    {
      "epoch": 0.08859357696567,
      "eval_loss": 0.9526168704032898,
      "eval_runtime": 26.9074,
      "eval_samples_per_second": 7.061,
      "eval_steps_per_second": 1.784,
      "step": 20
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 3.65950345993042,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 3.7001,
      "step": 21
    },
    {
      "epoch": 0.10631229235880399,
      "grad_norm": 3.0816593170166016,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 3.6398,
      "step": 24
    },
    {
      "epoch": 0.11074197120708748,
      "eval_loss": 0.9307340979576111,
      "eval_runtime": 26.9226,
      "eval_samples_per_second": 7.057,
      "eval_steps_per_second": 1.783,
      "step": 25
    },
    {
      "epoch": 0.11960132890365449,
      "grad_norm": 3.3297533988952637,
      "learning_rate": 7.022351411174866e-06,
      "loss": 3.7367,
      "step": 27
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 2.909958600997925,
      "learning_rate": 0.0,
      "loss": 3.6293,
      "step": 30
    },
    {
      "epoch": 0.132890365448505,
      "eval_loss": 0.9259054064750671,
      "eval_runtime": 26.9221,
      "eval_samples_per_second": 7.057,
      "eval_steps_per_second": 1.783,
      "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": 2.109388496044032e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}