{
  "best_metric": 0.1553138643503189,
  "best_model_checkpoint": "speech-multiclassifier-run-2/checkpoint-6384",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 9576,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15664160401002505,
      "grad_norm": 11.20281982421875,
      "learning_rate": 1.8955722639933167e-05,
      "loss": 0.1599,
      "step": 500
    },
    {
      "epoch": 0.3132832080200501,
      "grad_norm": 16.948055267333984,
      "learning_rate": 1.7911445279866332e-05,
      "loss": 0.2132,
      "step": 1000
    },
    {
      "epoch": 0.4699248120300752,
      "grad_norm": 15.359735488891602,
      "learning_rate": 1.68671679197995e-05,
      "loss": 0.2101,
      "step": 1500
    },
    {
      "epoch": 0.6265664160401002,
      "grad_norm": 0.13909225165843964,
      "learning_rate": 1.5822890559732666e-05,
      "loss": 0.1868,
      "step": 2000
    },
    {
      "epoch": 0.7832080200501254,
      "grad_norm": 1.7620573043823242,
      "learning_rate": 1.4778613199665832e-05,
      "loss": 0.1824,
      "step": 2500
    },
    {
      "epoch": 0.9398496240601504,
      "grad_norm": 2.3290231227874756,
      "learning_rate": 1.3734335839598997e-05,
      "loss": 0.1678,
      "step": 3000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.15620405972003937,
      "eval_overall-accuracy": 0.9531360112755461,
      "eval_overall-f1": 0.9531360112755461,
      "eval_overall-precision": 0.9531360112755461,
      "eval_overall-recall": 0.9531360112755461,
      "eval_runtime": 5.7139,
      "eval_samples_per_second": 496.687,
      "eval_steps_per_second": 31.152,
      "step": 3192
    },
    {
      "epoch": 1.0964912280701755,
      "grad_norm": 0.4430443048477173,
      "learning_rate": 1.2690058479532166e-05,
      "loss": 0.1655,
      "step": 3500
    },
    {
      "epoch": 1.2531328320802004,
      "grad_norm": 5.565830707550049,
      "learning_rate": 1.1645781119465331e-05,
      "loss": 0.1499,
      "step": 4000
    },
    {
      "epoch": 1.4097744360902256,
      "grad_norm": 0.9018378257751465,
      "learning_rate": 1.0601503759398497e-05,
      "loss": 0.1443,
      "step": 4500
    },
    {
      "epoch": 1.5664160401002505,
      "grad_norm": 0.3591144382953644,
      "learning_rate": 9.557226399331662e-06,
      "loss": 0.1399,
      "step": 5000
    },
    {
      "epoch": 1.7230576441102756,
      "grad_norm": 0.4499484598636627,
      "learning_rate": 8.512949039264829e-06,
      "loss": 0.1559,
      "step": 5500
    },
    {
      "epoch": 1.8796992481203008,
      "grad_norm": 8.649208068847656,
      "learning_rate": 7.468671679197995e-06,
      "loss": 0.1522,
      "step": 6000
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.1553138643503189,
      "eval_overall-accuracy": 0.9531360112755461,
      "eval_overall-f1": 0.9531360112755461,
      "eval_overall-precision": 0.9531360112755461,
      "eval_overall-recall": 0.9531360112755461,
      "eval_runtime": 5.7234,
      "eval_samples_per_second": 495.858,
      "eval_steps_per_second": 31.1,
      "step": 6384
    },
    {
      "epoch": 2.036340852130326,
      "grad_norm": 1.2995306253433228,
      "learning_rate": 6.424394319131162e-06,
      "loss": 0.1398,
      "step": 6500
    },
    {
      "epoch": 2.192982456140351,
      "grad_norm": 0.18944260478019714,
      "learning_rate": 5.380116959064328e-06,
      "loss": 0.1164,
      "step": 7000
    },
    {
      "epoch": 2.3496240601503757,
      "grad_norm": 4.408690929412842,
      "learning_rate": 4.335839598997494e-06,
      "loss": 0.1154,
      "step": 7500
    },
    {
      "epoch": 2.506265664160401,
      "grad_norm": 0.7239732146263123,
      "learning_rate": 3.29156223893066e-06,
      "loss": 0.1208,
      "step": 8000
    },
    {
      "epoch": 2.662907268170426,
      "grad_norm": 6.512196063995361,
      "learning_rate": 2.2472848788638263e-06,
      "loss": 0.1115,
      "step": 8500
    },
    {
      "epoch": 2.819548872180451,
      "grad_norm": 1.97010338306427,
      "learning_rate": 1.2030075187969925e-06,
      "loss": 0.1169,
      "step": 9000
    },
    {
      "epoch": 2.9761904761904763,
      "grad_norm": 1.1876590251922607,
      "learning_rate": 1.5873015873015874e-07,
      "loss": 0.1157,
      "step": 9500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.16947361826896667,
      "eval_overall-accuracy": 0.9534883720930233,
      "eval_overall-f1": 0.9534883720930233,
      "eval_overall-precision": 0.9534883720930233,
      "eval_overall-recall": 0.9534883720930233,
      "eval_runtime": 5.6944,
      "eval_samples_per_second": 498.388,
      "eval_steps_per_second": 31.259,
      "step": 9576
    }
  ],
  "logging_steps": 500,
  "max_steps": 9576,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2641161396896352.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}