{
  "best_global_step": 1000,
  "best_metric": 0.9205830097198486,
  "best_model_checkpoint": "runs/emotts_ravdess\\checkpoint-1000",
  "epoch": 24.395061728395063,
  "eval_steps": 1000,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 46.678199768066406,
      "learning_rate": 4.800000000000001e-07,
      "loss": 3.4472,
      "step": 25
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 26.903335571289062,
      "learning_rate": 9.800000000000001e-07,
      "loss": 2.9051,
      "step": 50
    },
    {
      "epoch": 1.8395061728395061,
      "grad_norm": 16.712799072265625,
      "learning_rate": 1.48e-06,
      "loss": 2.2302,
      "step": 75
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 11.607951164245605,
      "learning_rate": 1.98e-06,
      "loss": 1.7683,
      "step": 100
    },
    {
      "epoch": 3.049382716049383,
      "grad_norm": 7.216983318328857,
      "learning_rate": 2.4800000000000004e-06,
      "loss": 1.5434,
      "step": 125
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 10.899630546569824,
      "learning_rate": 2.9800000000000003e-06,
      "loss": 1.4385,
      "step": 150
    },
    {
      "epoch": 4.271604938271605,
      "grad_norm": 6.701765537261963,
      "learning_rate": 3.48e-06,
      "loss": 1.3262,
      "step": 175
    },
    {
      "epoch": 4.888888888888889,
      "grad_norm": 9.419053077697754,
      "learning_rate": 3.980000000000001e-06,
      "loss": 1.285,
      "step": 200
    },
    {
      "epoch": 5.493827160493828,
      "grad_norm": 5.913278579711914,
      "learning_rate": 4.48e-06,
      "loss": 1.2503,
      "step": 225
    },
    {
      "epoch": 6.098765432098766,
      "grad_norm": 8.171669006347656,
      "learning_rate": 4.980000000000001e-06,
      "loss": 1.1868,
      "step": 250
    },
    {
      "epoch": 6.716049382716049,
      "grad_norm": 5.54558801651001,
      "learning_rate": 5.480000000000001e-06,
      "loss": 1.1478,
      "step": 275
    },
    {
      "epoch": 7.320987654320987,
      "grad_norm": 5.325434684753418,
      "learning_rate": 5.98e-06,
      "loss": 1.1245,
      "step": 300
    },
    {
      "epoch": 7.938271604938271,
      "grad_norm": 5.406148433685303,
      "learning_rate": 6.480000000000001e-06,
      "loss": 1.1145,
      "step": 325
    },
    {
      "epoch": 8.54320987654321,
      "grad_norm": 8.461536407470703,
      "learning_rate": 6.98e-06,
      "loss": 1.0641,
      "step": 350
    },
    {
      "epoch": 9.148148148148149,
      "grad_norm": 3.8533031940460205,
      "learning_rate": 7.48e-06,
      "loss": 1.0573,
      "step": 375
    },
    {
      "epoch": 9.765432098765432,
      "grad_norm": 7.569976806640625,
      "learning_rate": 7.980000000000002e-06,
      "loss": 1.061,
      "step": 400
    },
    {
      "epoch": 10.37037037037037,
      "grad_norm": 10.156228065490723,
      "learning_rate": 8.48e-06,
      "loss": 1.0485,
      "step": 425
    },
    {
      "epoch": 10.987654320987655,
      "grad_norm": 4.668756484985352,
      "learning_rate": 8.98e-06,
      "loss": 1.0216,
      "step": 450
    },
    {
      "epoch": 11.592592592592592,
      "grad_norm": 5.087125301361084,
      "learning_rate": 9.48e-06,
      "loss": 1.0319,
      "step": 475
    },
    {
      "epoch": 12.197530864197532,
      "grad_norm": 7.943349361419678,
      "learning_rate": 9.980000000000001e-06,
      "loss": 1.0,
      "step": 500
    },
    {
      "epoch": 12.814814814814815,
      "grad_norm": 7.655898571014404,
      "learning_rate": 9.931428571428571e-06,
      "loss": 1.0052,
      "step": 525
    },
    {
      "epoch": 13.419753086419753,
      "grad_norm": 4.458106994628906,
      "learning_rate": 9.86e-06,
      "loss": 1.0001,
      "step": 550
    },
    {
      "epoch": 14.024691358024691,
      "grad_norm": 9.058222770690918,
      "learning_rate": 9.78857142857143e-06,
      "loss": 1.0015,
      "step": 575
    },
    {
      "epoch": 14.641975308641975,
      "grad_norm": 4.795205593109131,
      "learning_rate": 9.717142857142858e-06,
      "loss": 0.9836,
      "step": 600
    },
    {
      "epoch": 15.246913580246913,
      "grad_norm": 10.566876411437988,
      "learning_rate": 9.645714285714286e-06,
      "loss": 1.0019,
      "step": 625
    },
    {
      "epoch": 15.864197530864198,
      "grad_norm": 7.610626220703125,
      "learning_rate": 9.574285714285715e-06,
      "loss": 0.9779,
      "step": 650
    },
    {
      "epoch": 16.469135802469136,
      "grad_norm": 6.008159637451172,
      "learning_rate": 9.502857142857144e-06,
      "loss": 0.9798,
      "step": 675
    },
    {
      "epoch": 17.074074074074073,
      "grad_norm": 6.685286521911621,
      "learning_rate": 9.431428571428573e-06,
      "loss": 0.9753,
      "step": 700
    },
    {
      "epoch": 17.691358024691358,
      "grad_norm": 2.7540247440338135,
      "learning_rate": 9.360000000000002e-06,
      "loss": 0.967,
      "step": 725
    },
    {
      "epoch": 18.296296296296298,
      "grad_norm": 4.825072288513184,
      "learning_rate": 9.28857142857143e-06,
      "loss": 0.9575,
      "step": 750
    },
    {
      "epoch": 18.91358024691358,
      "grad_norm": 6.618119716644287,
      "learning_rate": 9.217142857142858e-06,
      "loss": 0.9675,
      "step": 775
    },
    {
      "epoch": 19.51851851851852,
      "grad_norm": 5.465808391571045,
      "learning_rate": 9.145714285714287e-06,
      "loss": 0.9626,
      "step": 800
    },
    {
      "epoch": 20.123456790123456,
      "grad_norm": 4.9501051902771,
      "learning_rate": 9.074285714285716e-06,
      "loss": 0.9638,
      "step": 825
    },
    {
      "epoch": 20.74074074074074,
      "grad_norm": 4.926831245422363,
      "learning_rate": 9.002857142857144e-06,
      "loss": 0.9582,
      "step": 850
    },
    {
      "epoch": 21.34567901234568,
      "grad_norm": 6.605464458465576,
      "learning_rate": 8.931428571428573e-06,
      "loss": 0.9551,
      "step": 875
    },
    {
      "epoch": 21.962962962962962,
      "grad_norm": 5.774538040161133,
      "learning_rate": 8.860000000000002e-06,
      "loss": 0.9596,
      "step": 900
    },
    {
      "epoch": 22.567901234567902,
      "grad_norm": 4.304802417755127,
      "learning_rate": 8.788571428571429e-06,
      "loss": 0.9489,
      "step": 925
    },
    {
      "epoch": 23.17283950617284,
      "grad_norm": 5.171604633331299,
      "learning_rate": 8.717142857142858e-06,
      "loss": 0.953,
      "step": 950
    },
    {
      "epoch": 23.790123456790123,
      "grad_norm": 7.152281761169434,
      "learning_rate": 8.645714285714287e-06,
      "loss": 0.9604,
      "step": 975
    },
    {
      "epoch": 24.395061728395063,
      "grad_norm": 4.954558849334717,
      "learning_rate": 8.574285714285714e-06,
      "loss": 0.9489,
      "step": 1000
    },
    {
      "epoch": 24.395061728395063,
      "eval_loss": 0.9205830097198486,
      "eval_runtime": 2.2708,
      "eval_samples_per_second": 63.413,
      "eval_steps_per_second": 31.707,
      "step": 1000
    }
  ],
  "logging_steps": 25,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 98,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 821472814356480.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}