{
  "best_metric": 0.644947350025177,
  "best_model_checkpoint": "./whisper-tiny-Persian/checkpoint-5000",
  "epoch": 2.076,
  "eval_steps": 1000,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.9657,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 9.800000000000001e-06,
      "loss": 1.5744,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.902040816326531e-06,
      "loss": 1.3358,
      "step": 150
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.800000000000001e-06,
      "loss": 1.2028,
      "step": 200
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.697959183673469e-06,
      "loss": 1.1233,
      "step": 250
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.595918367346939e-06,
      "loss": 1.0437,
      "step": 300
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.493877551020409e-06,
      "loss": 1.0204,
      "step": 350
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.391836734693878e-06,
      "loss": 1.0191,
      "step": 400
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.289795918367348e-06,
      "loss": 0.9594,
      "step": 450
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.187755102040818e-06,
      "loss": 0.9302,
      "step": 500
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.085714285714286e-06,
      "loss": 0.8917,
      "step": 550
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.983673469387756e-06,
      "loss": 0.8777,
      "step": 600
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.881632653061226e-06,
      "loss": 0.8833,
      "step": 650
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.779591836734694e-06,
      "loss": 0.8953,
      "step": 700
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.677551020408164e-06,
      "loss": 0.8275,
      "step": 750
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.575510204081633e-06,
      "loss": 0.8382,
      "step": 800
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.473469387755101e-06,
      "loss": 0.8223,
      "step": 850
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.371428571428573e-06,
      "loss": 0.7951,
      "step": 900
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.269387755102043e-06,
      "loss": 0.8289,
      "step": 950
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.16734693877551e-06,
      "loss": 0.7777,
      "step": 1000
    },
    {
      "epoch": 0.2,
      "eval_loss": 0.820560872554779,
      "eval_runtime": 471.8233,
      "eval_samples_per_second": 24.431,
      "eval_steps_per_second": 0.765,
      "step": 1000
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.06530612244898e-06,
      "loss": 0.8194,
      "step": 1050
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.96326530612245e-06,
      "loss": 0.7904,
      "step": 1100
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.861224489795918e-06,
      "loss": 0.7771,
      "step": 1150
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.759183673469388e-06,
      "loss": 0.7776,
      "step": 1200
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.657142857142858e-06,
      "loss": 0.7738,
      "step": 1250
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.555102040816327e-06,
      "loss": 0.7857,
      "step": 1300
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.4530612244897974e-06,
      "loss": 0.7376,
      "step": 1350
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.351020408163266e-06,
      "loss": 0.7199,
      "step": 1400
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.248979591836735e-06,
      "loss": 0.7251,
      "step": 1450
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.146938775510205e-06,
      "loss": 0.7467,
      "step": 1500
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.044897959183674e-06,
      "loss": 0.7426,
      "step": 1550
    },
    {
      "epoch": 0.32,
      "learning_rate": 6.942857142857144e-06,
      "loss": 0.7123,
      "step": 1600
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.840816326530613e-06,
      "loss": 0.7011,
      "step": 1650
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.738775510204082e-06,
      "loss": 0.7227,
      "step": 1700
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.636734693877551e-06,
      "loss": 0.7159,
      "step": 1750
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.53469387755102e-06,
      "loss": 0.7344,
      "step": 1800
    },
    {
      "epoch": 0.37,
      "learning_rate": 6.432653061224491e-06,
      "loss": 0.7193,
      "step": 1850
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.33061224489796e-06,
      "loss": 0.7116,
      "step": 1900
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.22857142857143e-06,
      "loss": 0.7031,
      "step": 1950
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.126530612244899e-06,
      "loss": 0.7103,
      "step": 2000
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.718885600566864,
      "eval_runtime": 450.8836,
      "eval_samples_per_second": 25.565,
      "eval_steps_per_second": 0.801,
      "step": 2000
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.0244897959183675e-06,
      "loss": 0.7022,
      "step": 2050
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.922448979591837e-06,
      "loss": 0.6814,
      "step": 2100
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.820408163265306e-06,
      "loss": 0.6918,
      "step": 2150
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.718367346938776e-06,
      "loss": 0.684,
      "step": 2200
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.616326530612245e-06,
      "loss": 0.673,
      "step": 2250
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.514285714285714e-06,
      "loss": 0.6684,
      "step": 2300
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.4122448979591845e-06,
      "loss": 0.6604,
      "step": 2350
    },
    {
      "epoch": 1.02,
      "learning_rate": 5.310204081632654e-06,
      "loss": 0.6738,
      "step": 2400
    },
    {
      "epoch": 1.03,
      "learning_rate": 5.208163265306123e-06,
      "loss": 0.6747,
      "step": 2450
    },
    {
      "epoch": 1.04,
      "learning_rate": 5.106122448979592e-06,
      "loss": 0.6749,
      "step": 2500
    },
    {
      "epoch": 1.05,
      "learning_rate": 5.004081632653062e-06,
      "loss": 0.6671,
      "step": 2550
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.902040816326531e-06,
      "loss": 0.6407,
      "step": 2600
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.800000000000001e-06,
      "loss": 0.6715,
      "step": 2650
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.69795918367347e-06,
      "loss": 0.6554,
      "step": 2700
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.595918367346939e-06,
      "loss": 0.6585,
      "step": 2750
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.493877551020408e-06,
      "loss": 0.6539,
      "step": 2800
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.391836734693878e-06,
      "loss": 0.6184,
      "step": 2850
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.289795918367347e-06,
      "loss": 0.6445,
      "step": 2900
    },
    {
      "epoch": 1.13,
      "learning_rate": 4.187755102040817e-06,
      "loss": 0.6205,
      "step": 2950
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.0857142857142865e-06,
      "loss": 0.6751,
      "step": 3000
    },
    {
      "epoch": 1.14,
      "eval_loss": 0.6741017699241638,
      "eval_runtime": 471.6166,
      "eval_samples_per_second": 24.441,
      "eval_steps_per_second": 0.765,
      "step": 3000
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.9836734693877555e-06,
      "loss": 0.6215,
      "step": 3050
    },
    {
      "epoch": 1.16,
      "learning_rate": 3.881632653061224e-06,
      "loss": 0.6438,
      "step": 3100
    },
    {
      "epoch": 1.17,
      "learning_rate": 3.779591836734694e-06,
      "loss": 0.6404,
      "step": 3150
    },
    {
      "epoch": 1.18,
      "learning_rate": 3.677551020408164e-06,
      "loss": 0.6123,
      "step": 3200
    },
    {
      "epoch": 1.19,
      "learning_rate": 3.575510204081633e-06,
      "loss": 0.6229,
      "step": 3250
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.4734693877551022e-06,
      "loss": 0.6221,
      "step": 3300
    },
    {
      "epoch": 1.21,
      "learning_rate": 3.3714285714285716e-06,
      "loss": 0.6391,
      "step": 3350
    },
    {
      "epoch": 1.22,
      "learning_rate": 3.269387755102041e-06,
      "loss": 0.636,
      "step": 3400
    },
    {
      "epoch": 1.23,
      "learning_rate": 3.1673469387755107e-06,
      "loss": 0.6257,
      "step": 3450
    },
    {
      "epoch": 1.24,
      "learning_rate": 3.06530612244898e-06,
      "loss": 0.6325,
      "step": 3500
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.9632653061224494e-06,
      "loss": 0.633,
      "step": 3550
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.8612244897959183e-06,
      "loss": 0.6472,
      "step": 3600
    },
    {
      "epoch": 1.27,
      "learning_rate": 2.7591836734693877e-06,
      "loss": 0.6172,
      "step": 3650
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.6571428571428575e-06,
      "loss": 0.6015,
      "step": 3700
    },
    {
      "epoch": 1.29,
      "learning_rate": 2.555102040816327e-06,
      "loss": 0.5997,
      "step": 3750
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.453061224489796e-06,
      "loss": 0.6359,
      "step": 3800
    },
    {
      "epoch": 1.31,
      "learning_rate": 2.3510204081632655e-06,
      "loss": 0.6317,
      "step": 3850
    },
    {
      "epoch": 1.32,
      "learning_rate": 2.248979591836735e-06,
      "loss": 0.5946,
      "step": 3900
    },
    {
      "epoch": 1.33,
      "learning_rate": 2.1469387755102042e-06,
      "loss": 0.6068,
      "step": 3950
    },
    {
      "epoch": 1.34,
      "learning_rate": 2.0448979591836736e-06,
      "loss": 0.6104,
      "step": 4000
    },
    {
      "epoch": 1.34,
      "eval_loss": 0.6528713703155518,
      "eval_runtime": 474.8867,
      "eval_samples_per_second": 24.273,
      "eval_steps_per_second": 0.76,
      "step": 4000
    },
    {
      "epoch": 1.35,
      "learning_rate": 1.942857142857143e-06,
      "loss": 0.6057,
      "step": 4050
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.8428571428571428e-06,
      "loss": 0.6371,
      "step": 4100
    },
    {
      "epoch": 1.37,
      "learning_rate": 1.7408163265306124e-06,
      "loss": 0.6209,
      "step": 4150
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.6387755102040818e-06,
      "loss": 0.6349,
      "step": 4200
    },
    {
      "epoch": 1.39,
      "learning_rate": 1.5367346938775513e-06,
      "loss": 0.6053,
      "step": 4250
    },
    {
      "epoch": 1.4,
      "learning_rate": 1.4346938775510205e-06,
      "loss": 0.6237,
      "step": 4300
    },
    {
      "epoch": 1.41,
      "learning_rate": 1.3326530612244898e-06,
      "loss": 0.6297,
      "step": 4350
    },
    {
      "epoch": 1.42,
      "learning_rate": 1.2306122448979594e-06,
      "loss": 0.596,
      "step": 4400
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.1285714285714285e-06,
      "loss": 0.6118,
      "step": 4450
    },
    {
      "epoch": 1.44,
      "learning_rate": 1.026530612244898e-06,
      "loss": 0.5947,
      "step": 4500
    },
    {
      "epoch": 1.45,
      "learning_rate": 9.244897959183675e-07,
      "loss": 0.6087,
      "step": 4550
    },
    {
      "epoch": 1.46,
      "learning_rate": 8.224489795918368e-07,
      "loss": 0.6041,
      "step": 4600
    },
    {
      "epoch": 2.01,
      "learning_rate": 7.204081632653063e-07,
      "loss": 0.5945,
      "step": 4650
    },
    {
      "epoch": 2.02,
      "learning_rate": 6.183673469387755e-07,
      "loss": 0.6078,
      "step": 4700
    },
    {
      "epoch": 2.03,
      "learning_rate": 5.16326530612245e-07,
      "loss": 0.6056,
      "step": 4750
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.142857142857143e-07,
      "loss": 0.6164,
      "step": 4800
    },
    {
      "epoch": 2.05,
      "learning_rate": 3.122448979591837e-07,
      "loss": 0.6162,
      "step": 4850
    },
    {
      "epoch": 2.06,
      "learning_rate": 2.1020408163265306e-07,
      "loss": 0.5843,
      "step": 4900
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.0816326530612245e-07,
      "loss": 0.6012,
      "step": 4950
    },
    {
      "epoch": 2.08,
      "learning_rate": 6.1224489795918365e-09,
      "loss": 0.6213,
      "step": 5000
    },
    {
      "epoch": 2.08,
      "eval_loss": 0.644947350025177,
      "eval_runtime": 426.4329,
      "eval_samples_per_second": 27.031,
      "eval_steps_per_second": 0.847,
      "step": 5000
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 1000,
  "total_flos": 3.93744601055232e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}