{
  "best_metric": 129.73334545596236,
  "best_model_checkpoint": "./models/rootflo/fauna-v3.3_2/checkpoint-500",
  "epoch": 1.0869565217391304,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.4133610427379608,
      "learning_rate": 9.980760446763691e-08,
      "loss": 0.103,
      "step": 100
    },
    {
      "epoch": 0.21739130434782608,
      "eval_loss": 0.07003876566886902,
      "eval_runtime": 2873.8384,
      "eval_samples_per_second": 1.392,
      "eval_steps_per_second": 0.004,
      "eval_wer": 129.6748970658908,
      "step": 100
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.45984333753585815,
      "learning_rate": 9.827731266378837e-08,
      "loss": 0.1027,
      "step": 200
    },
    {
      "epoch": 0.43478260869565216,
      "eval_loss": 0.06984159350395203,
      "eval_runtime": 2864.2512,
      "eval_samples_per_second": 1.397,
      "eval_steps_per_second": 0.004,
      "eval_wer": 129.7658167837799,
      "step": 200
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.42810264229774475,
      "learning_rate": 9.526374583254453e-08,
      "loss": 0.1014,
      "step": 300
    },
    {
      "epoch": 0.6521739130434783,
      "eval_loss": 0.06970909982919693,
      "eval_runtime": 2907.1874,
      "eval_samples_per_second": 1.376,
      "eval_steps_per_second": 0.004,
      "eval_wer": 129.7255523372862,
      "step": 300
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.4411391317844391,
      "learning_rate": 9.085949298057401e-08,
      "loss": 0.1012,
      "step": 400
    },
    {
      "epoch": 0.8695652173913043,
      "eval_loss": 0.0696246400475502,
      "eval_runtime": 2912.1845,
      "eval_samples_per_second": 1.374,
      "eval_steps_per_second": 0.004,
      "eval_wer": 129.71646036549726,
      "step": 400
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 0.4338875114917755,
      "learning_rate": 8.519987063460971e-08,
      "loss": 0.1012,
      "step": 500
    },
    {
      "epoch": 1.0869565217391304,
      "eval_loss": 0.06950458139181137,
      "eval_runtime": 2890.5128,
      "eval_samples_per_second": 1.384,
      "eval_steps_per_second": 0.004,
      "eval_wer": 129.73334545596236,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 1840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.01
      },
      "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": 1.3046393318036577e+21,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}