{
  "best_metric": 0.9259882253994953,
  "best_model_checkpoint": "enver/cat-sounds/checkpoint-891",
  "epoch": 2.9974768713204374,
  "eval_steps": 500,
  "global_step": 891,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 5.555555555555556e-06,
      "loss": 2.3176,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 2.2754,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.2346,
      "step": 30
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 2.1605,
      "step": 40
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.777777777777778e-05,
      "loss": 2.0691,
      "step": 50
    },
    {
      "epoch": 0.2,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.9679,
      "step": 60
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.8312,
      "step": 70
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.6983,
      "step": 80
    },
    {
      "epoch": 0.3,
      "learning_rate": 5e-05,
      "loss": 1.5913,
      "step": 90
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.937578027465668e-05,
      "loss": 1.4524,
      "step": 100
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.875156054931336e-05,
      "loss": 1.3422,
      "step": 110
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.812734082397004e-05,
      "loss": 1.1812,
      "step": 120
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.750312109862672e-05,
      "loss": 1.2109,
      "step": 130
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.6878901373283394e-05,
      "loss": 1.1491,
      "step": 140
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.625468164794008e-05,
      "loss": 1.0259,
      "step": 150
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.563046192259676e-05,
      "loss": 1.002,
      "step": 160
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.500624219725343e-05,
      "loss": 1.1162,
      "step": 170
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.438202247191011e-05,
      "loss": 0.8804,
      "step": 180
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.37578027465668e-05,
      "loss": 0.9022,
      "step": 190
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.313358302122347e-05,
      "loss": 0.8509,
      "step": 200
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.250936329588015e-05,
      "loss": 0.814,
      "step": 210
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.188514357053683e-05,
      "loss": 0.8451,
      "step": 220
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.126092384519351e-05,
      "loss": 0.9322,
      "step": 230
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.063670411985019e-05,
      "loss": 0.7668,
      "step": 240
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.001248439450687e-05,
      "loss": 0.8153,
      "step": 250
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.938826466916355e-05,
      "loss": 0.7569,
      "step": 260
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.876404494382023e-05,
      "loss": 0.8009,
      "step": 270
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.813982521847691e-05,
      "loss": 0.6789,
      "step": 280
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.751560549313358e-05,
      "loss": 0.6474,
      "step": 290
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8359966358284272,
      "eval_f1": 0.8379685951133469,
      "eval_loss": 0.6715514659881592,
      "eval_precision": 0.8527444218731524,
      "eval_recall": 0.8359966358284272,
      "eval_runtime": 138.4497,
      "eval_samples_per_second": 8.588,
      "eval_steps_per_second": 2.152,
      "step": 297
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.689138576779027e-05,
      "loss": 0.7577,
      "step": 300
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.626716604244694e-05,
      "loss": 0.5251,
      "step": 310
    },
    {
      "epoch": 1.08,
      "learning_rate": 3.564294631710362e-05,
      "loss": 0.6098,
      "step": 320
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.5018726591760305e-05,
      "loss": 0.5334,
      "step": 330
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.439450686641698e-05,
      "loss": 0.5506,
      "step": 340
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.377028714107366e-05,
      "loss": 0.6034,
      "step": 350
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.314606741573034e-05,
      "loss": 0.4747,
      "step": 360
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.252184769038702e-05,
      "loss": 0.5192,
      "step": 370
    },
    {
      "epoch": 1.28,
      "learning_rate": 3.1897627965043697e-05,
      "loss": 0.4885,
      "step": 380
    },
    {
      "epoch": 1.31,
      "learning_rate": 3.1273408239700376e-05,
      "loss": 0.5599,
      "step": 390
    },
    {
      "epoch": 1.35,
      "learning_rate": 3.0649188514357056e-05,
      "loss": 0.5168,
      "step": 400
    },
    {
      "epoch": 1.38,
      "learning_rate": 3.0024968789013735e-05,
      "loss": 0.4305,
      "step": 410
    },
    {
      "epoch": 1.41,
      "learning_rate": 2.940074906367041e-05,
      "loss": 0.4534,
      "step": 420
    },
    {
      "epoch": 1.45,
      "learning_rate": 2.877652933832709e-05,
      "loss": 0.5032,
      "step": 430
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.8152309612983774e-05,
      "loss": 0.4587,
      "step": 440
    },
    {
      "epoch": 1.51,
      "learning_rate": 2.752808988764045e-05,
      "loss": 0.4103,
      "step": 450
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.690387016229713e-05,
      "loss": 0.3474,
      "step": 460
    },
    {
      "epoch": 1.58,
      "learning_rate": 2.6279650436953806e-05,
      "loss": 0.4218,
      "step": 470
    },
    {
      "epoch": 1.61,
      "learning_rate": 2.565543071161049e-05,
      "loss": 0.3609,
      "step": 480
    },
    {
      "epoch": 1.65,
      "learning_rate": 2.503121098626717e-05,
      "loss": 0.3032,
      "step": 490
    },
    {
      "epoch": 1.68,
      "learning_rate": 2.4406991260923848e-05,
      "loss": 0.4611,
      "step": 500
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.3782771535580524e-05,
      "loss": 0.4433,
      "step": 510
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.3158551810237207e-05,
      "loss": 0.4522,
      "step": 520
    },
    {
      "epoch": 1.78,
      "learning_rate": 2.2534332084893883e-05,
      "loss": 0.4488,
      "step": 530
    },
    {
      "epoch": 1.82,
      "learning_rate": 2.1910112359550563e-05,
      "loss": 0.4003,
      "step": 540
    },
    {
      "epoch": 1.85,
      "learning_rate": 2.1285892634207243e-05,
      "loss": 0.3832,
      "step": 550
    },
    {
      "epoch": 1.88,
      "learning_rate": 2.0661672908863922e-05,
      "loss": 0.2996,
      "step": 560
    },
    {
      "epoch": 1.92,
      "learning_rate": 2.00374531835206e-05,
      "loss": 0.3441,
      "step": 570
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.9413233458177278e-05,
      "loss": 0.3271,
      "step": 580
    },
    {
      "epoch": 1.98,
      "learning_rate": 1.8789013732833958e-05,
      "loss": 0.413,
      "step": 590
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8999158957106812,
      "eval_f1": 0.9013231777661141,
      "eval_loss": 0.42947980761528015,
      "eval_precision": 0.9097523236239999,
      "eval_recall": 0.8999158957106812,
      "eval_runtime": 138.7049,
      "eval_samples_per_second": 8.572,
      "eval_steps_per_second": 2.148,
      "step": 594
    },
    {
      "epoch": 2.02,
      "learning_rate": 1.8164794007490637e-05,
      "loss": 0.3428,
      "step": 600
    },
    {
      "epoch": 2.05,
      "learning_rate": 1.7540574282147317e-05,
      "loss": 0.2994,
      "step": 610
    },
    {
      "epoch": 2.09,
      "learning_rate": 1.6916354556803996e-05,
      "loss": 0.2385,
      "step": 620
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.6292134831460676e-05,
      "loss": 0.3453,
      "step": 630
    },
    {
      "epoch": 2.15,
      "learning_rate": 1.5667915106117352e-05,
      "loss": 0.3042,
      "step": 640
    },
    {
      "epoch": 2.19,
      "learning_rate": 1.5043695380774033e-05,
      "loss": 0.2582,
      "step": 650
    },
    {
      "epoch": 2.22,
      "learning_rate": 1.4419475655430711e-05,
      "loss": 0.2912,
      "step": 660
    },
    {
      "epoch": 2.25,
      "learning_rate": 1.3795255930087393e-05,
      "loss": 0.2173,
      "step": 670
    },
    {
      "epoch": 2.29,
      "learning_rate": 1.3171036204744069e-05,
      "loss": 0.2286,
      "step": 680
    },
    {
      "epoch": 2.32,
      "learning_rate": 1.254681647940075e-05,
      "loss": 0.2235,
      "step": 690
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.192259675405743e-05,
      "loss": 0.238,
      "step": 700
    },
    {
      "epoch": 2.39,
      "learning_rate": 1.1298377028714107e-05,
      "loss": 0.2113,
      "step": 710
    },
    {
      "epoch": 2.42,
      "learning_rate": 1.0674157303370787e-05,
      "loss": 0.2061,
      "step": 720
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.0049937578027465e-05,
      "loss": 0.1937,
      "step": 730
    },
    {
      "epoch": 2.49,
      "learning_rate": 9.425717852684144e-06,
      "loss": 0.1994,
      "step": 740
    },
    {
      "epoch": 2.52,
      "learning_rate": 8.801498127340826e-06,
      "loss": 0.2239,
      "step": 750
    },
    {
      "epoch": 2.56,
      "learning_rate": 8.177278401997504e-06,
      "loss": 0.2161,
      "step": 760
    },
    {
      "epoch": 2.59,
      "learning_rate": 7.553058676654183e-06,
      "loss": 0.2486,
      "step": 770
    },
    {
      "epoch": 2.62,
      "learning_rate": 6.928838951310862e-06,
      "loss": 0.2777,
      "step": 780
    },
    {
      "epoch": 2.66,
      "learning_rate": 6.304619225967541e-06,
      "loss": 0.1885,
      "step": 790
    },
    {
      "epoch": 2.69,
      "learning_rate": 5.68039950062422e-06,
      "loss": 0.1919,
      "step": 800
    },
    {
      "epoch": 2.72,
      "learning_rate": 5.056179775280899e-06,
      "loss": 0.2593,
      "step": 810
    },
    {
      "epoch": 2.76,
      "learning_rate": 4.431960049937578e-06,
      "loss": 0.224,
      "step": 820
    },
    {
      "epoch": 2.79,
      "learning_rate": 3.8077403245942577e-06,
      "loss": 0.2105,
      "step": 830
    },
    {
      "epoch": 2.83,
      "learning_rate": 3.1835205992509364e-06,
      "loss": 0.1998,
      "step": 840
    },
    {
      "epoch": 2.86,
      "learning_rate": 2.5593008739076156e-06,
      "loss": 0.154,
      "step": 850
    },
    {
      "epoch": 2.89,
      "learning_rate": 1.9350811485642947e-06,
      "loss": 0.2342,
      "step": 860
    },
    {
      "epoch": 2.93,
      "learning_rate": 1.310861423220974e-06,
      "loss": 0.1484,
      "step": 870
    },
    {
      "epoch": 2.96,
      "learning_rate": 6.86641697877653e-07,
      "loss": 0.1661,
      "step": 880
    },
    {
      "epoch": 2.99,
      "learning_rate": 6.242197253433209e-08,
      "loss": 0.2144,
      "step": 890
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9259882253994953,
      "eval_f1": 0.9268755487412734,
      "eval_loss": 0.32298851013183594,
      "eval_precision": 0.9315188840219485,
      "eval_recall": 0.9259882253994953,
      "eval_runtime": 141.4553,
      "eval_samples_per_second": 8.405,
      "eval_steps_per_second": 2.107,
      "step": 891
    },
    {
      "epoch": 3.0,
      "step": 891,
      "total_flos": 1.104340029133824e+18,
      "train_loss": 0.6521745291690099,
      "train_runtime": 2345.9873,
      "train_samples_per_second": 6.078,
      "train_steps_per_second": 0.38
    }
  ],
  "logging_steps": 10,
  "max_steps": 891,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 1.104340029133824e+18,
  "trial_name": null,
  "trial_params": null
}