{
  "best_metric": 0.9047268629074097,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.3157894736842105,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010526315789473684,
      "eval_loss": 1.1589558124542236,
      "eval_runtime": 2.2599,
      "eval_samples_per_second": 17.7,
      "eval_steps_per_second": 8.85,
      "step": 1
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 0.883650541305542,
      "learning_rate": 6e-05,
      "loss": 4.8296,
      "step": 3
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 1.1520354747772217,
      "eval_runtime": 2.2486,
      "eval_samples_per_second": 17.789,
      "eval_steps_per_second": 8.894,
      "step": 5
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 1.0573056936264038,
      "learning_rate": 0.00012,
      "loss": 4.5506,
      "step": 6
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 1.1577221155166626,
      "learning_rate": 0.00018,
      "loss": 4.4901,
      "step": 9
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 1.054699420928955,
      "eval_runtime": 2.2476,
      "eval_samples_per_second": 17.797,
      "eval_steps_per_second": 8.899,
      "step": 10
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 1.3357572555541992,
      "learning_rate": 0.00019510565162951537,
      "loss": 4.3172,
      "step": 12
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.4287821054458618,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.7414,
      "step": 15
    },
    {
      "epoch": 0.15789473684210525,
      "eval_loss": 0.9715863466262817,
      "eval_runtime": 2.2532,
      "eval_samples_per_second": 17.753,
      "eval_steps_per_second": 8.876,
      "step": 15
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 1.5150578022003174,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.9713,
      "step": 18
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 0.9302014112472534,
      "eval_runtime": 2.2574,
      "eval_samples_per_second": 17.719,
      "eval_steps_per_second": 8.86,
      "step": 20
    },
    {
      "epoch": 0.22105263157894736,
      "grad_norm": 1.3578708171844482,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.659,
      "step": 21
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 1.4836304187774658,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.7008,
      "step": 24
    },
    {
      "epoch": 0.2631578947368421,
      "eval_loss": 0.9081043004989624,
      "eval_runtime": 2.2898,
      "eval_samples_per_second": 17.469,
      "eval_steps_per_second": 8.735,
      "step": 25
    },
    {
      "epoch": 0.28421052631578947,
      "grad_norm": 1.30848228931427,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.6191,
      "step": 27
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.1682331562042236,
      "learning_rate": 0.0,
      "loss": 3.549,
      "step": 30
    },
    {
      "epoch": 0.3157894736842105,
      "eval_loss": 0.9047268629074097,
      "eval_runtime": 2.2628,
      "eval_samples_per_second": 17.677,
      "eval_steps_per_second": 8.839,
      "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": 1802813193584640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}