{
  "best_metric": 24.56800162634682,
  "best_model_checkpoint": "./checkpoint-1000",
  "epoch": 166.004,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.6e-07,
      "loss": 1.2564,
      "step": 25
    },
    {
      "epoch": 3.0,
      "learning_rate": 9.6e-07,
      "loss": 1.0031,
      "step": 50
    },
    {
      "epoch": 4.01,
      "learning_rate": 9.906122448979592e-07,
      "loss": 0.5375,
      "step": 75
    },
    {
      "epoch": 6.0,
      "learning_rate": 9.80408163265306e-07,
      "loss": 0.3396,
      "step": 100
    },
    {
      "epoch": 8.0,
      "learning_rate": 9.70204081632653e-07,
      "loss": 0.2754,
      "step": 125
    },
    {
      "epoch": 9.01,
      "learning_rate": 9.6e-07,
      "loss": 0.2336,
      "step": 150
    },
    {
      "epoch": 11.0,
      "learning_rate": 9.497959183673469e-07,
      "loss": 0.197,
      "step": 175
    },
    {
      "epoch": 13.0,
      "learning_rate": 9.395918367346939e-07,
      "loss": 0.1695,
      "step": 200
    },
    {
      "epoch": 14.01,
      "learning_rate": 9.293877551020408e-07,
      "loss": 0.1478,
      "step": 225
    },
    {
      "epoch": 16.0,
      "learning_rate": 9.191836734693877e-07,
      "loss": 0.1242,
      "step": 250
    },
    {
      "epoch": 18.0,
      "learning_rate": 9.089795918367347e-07,
      "loss": 0.1056,
      "step": 275
    },
    {
      "epoch": 19.01,
      "learning_rate": 8.987755102040815e-07,
      "loss": 0.0889,
      "step": 300
    },
    {
      "epoch": 21.0,
      "learning_rate": 8.885714285714285e-07,
      "loss": 0.0733,
      "step": 325
    },
    {
      "epoch": 23.0,
      "learning_rate": 8.783673469387755e-07,
      "loss": 0.0592,
      "step": 350
    },
    {
      "epoch": 24.01,
      "learning_rate": 8.681632653061224e-07,
      "loss": 0.0502,
      "step": 375
    },
    {
      "epoch": 26.0,
      "learning_rate": 8.579591836734693e-07,
      "loss": 0.0383,
      "step": 400
    },
    {
      "epoch": 28.0,
      "learning_rate": 8.477551020408162e-07,
      "loss": 0.0313,
      "step": 425
    },
    {
      "epoch": 29.01,
      "learning_rate": 8.375510204081633e-07,
      "loss": 0.0244,
      "step": 450
    },
    {
      "epoch": 31.0,
      "learning_rate": 8.273469387755102e-07,
      "loss": 0.0199,
      "step": 475
    },
    {
      "epoch": 33.0,
      "learning_rate": 8.171428571428571e-07,
      "loss": 0.0174,
      "step": 500
    },
    {
      "epoch": 33.0,
      "eval_loss": 0.6206670999526978,
      "eval_runtime": 252.4938,
      "eval_samples_per_second": 5.252,
      "eval_steps_per_second": 0.166,
      "eval_wer": 24.66964830250051,
      "step": 500
    },
    {
      "epoch": 34.01,
      "learning_rate": 8.06938775510204e-07,
      "loss": 0.015,
      "step": 525
    },
    {
      "epoch": 36.0,
      "learning_rate": 7.96734693877551e-07,
      "loss": 0.0134,
      "step": 550
    },
    {
      "epoch": 38.0,
      "learning_rate": 7.86530612244898e-07,
      "loss": 0.012,
      "step": 575
    },
    {
      "epoch": 39.01,
      "learning_rate": 7.763265306122448e-07,
      "loss": 0.011,
      "step": 600
    },
    {
      "epoch": 41.0,
      "learning_rate": 7.661224489795918e-07,
      "loss": 0.01,
      "step": 625
    },
    {
      "epoch": 43.0,
      "learning_rate": 7.559183673469387e-07,
      "loss": 0.0092,
      "step": 650
    },
    {
      "epoch": 44.01,
      "learning_rate": 7.457142857142856e-07,
      "loss": 0.0087,
      "step": 675
    },
    {
      "epoch": 46.0,
      "learning_rate": 7.355102040816326e-07,
      "loss": 0.0081,
      "step": 700
    },
    {
      "epoch": 48.0,
      "learning_rate": 7.253061224489796e-07,
      "loss": 0.0075,
      "step": 725
    },
    {
      "epoch": 49.01,
      "learning_rate": 7.151020408163266e-07,
      "loss": 0.0072,
      "step": 750
    },
    {
      "epoch": 51.0,
      "learning_rate": 7.048979591836734e-07,
      "loss": 0.0068,
      "step": 775
    },
    {
      "epoch": 53.0,
      "learning_rate": 6.946938775510204e-07,
      "loss": 0.0064,
      "step": 800
    },
    {
      "epoch": 54.01,
      "learning_rate": 6.844897959183673e-07,
      "loss": 0.0061,
      "step": 825
    },
    {
      "epoch": 56.0,
      "learning_rate": 6.742857142857143e-07,
      "loss": 0.0058,
      "step": 850
    },
    {
      "epoch": 58.0,
      "learning_rate": 6.640816326530611e-07,
      "loss": 0.0055,
      "step": 875
    },
    {
      "epoch": 59.01,
      "learning_rate": 6.538775510204081e-07,
      "loss": 0.0054,
      "step": 900
    },
    {
      "epoch": 61.0,
      "learning_rate": 6.43673469387755e-07,
      "loss": 0.0051,
      "step": 925
    },
    {
      "epoch": 63.0,
      "learning_rate": 6.334693877551021e-07,
      "loss": 0.0049,
      "step": 950
    },
    {
      "epoch": 64.01,
      "learning_rate": 6.23265306122449e-07,
      "loss": 0.0047,
      "step": 975
    },
    {
      "epoch": 66.0,
      "learning_rate": 6.130612244897959e-07,
      "loss": 0.0045,
      "step": 1000
    },
    {
      "epoch": 66.0,
      "eval_loss": 0.6704666614532471,
      "eval_runtime": 250.1153,
      "eval_samples_per_second": 5.302,
      "eval_steps_per_second": 0.168,
      "eval_wer": 24.56800162634682,
      "step": 1000
    },
    {
      "epoch": 68.0,
      "learning_rate": 6.028571428571429e-07,
      "loss": 0.0044,
      "step": 1025
    },
    {
      "epoch": 69.01,
      "learning_rate": 5.926530612244898e-07,
      "loss": 0.0042,
      "step": 1050
    },
    {
      "epoch": 71.0,
      "learning_rate": 5.824489795918367e-07,
      "loss": 0.0041,
      "step": 1075
    },
    {
      "epoch": 73.0,
      "learning_rate": 5.722448979591836e-07,
      "loss": 0.004,
      "step": 1100
    },
    {
      "epoch": 74.01,
      "learning_rate": 5.620408163265306e-07,
      "loss": 0.0038,
      "step": 1125
    },
    {
      "epoch": 76.0,
      "learning_rate": 5.518367346938774e-07,
      "loss": 0.0037,
      "step": 1150
    },
    {
      "epoch": 78.0,
      "learning_rate": 5.416326530612245e-07,
      "loss": 0.0036,
      "step": 1175
    },
    {
      "epoch": 79.01,
      "learning_rate": 5.314285714285715e-07,
      "loss": 0.0035,
      "step": 1200
    },
    {
      "epoch": 81.0,
      "learning_rate": 5.212244897959184e-07,
      "loss": 0.0034,
      "step": 1225
    },
    {
      "epoch": 83.0,
      "learning_rate": 5.110204081632653e-07,
      "loss": 0.0033,
      "step": 1250
    },
    {
      "epoch": 84.01,
      "learning_rate": 5.008163265306122e-07,
      "loss": 0.0033,
      "step": 1275
    },
    {
      "epoch": 86.0,
      "learning_rate": 4.906122448979592e-07,
      "loss": 0.0031,
      "step": 1300
    },
    {
      "epoch": 88.0,
      "learning_rate": 4.804081632653061e-07,
      "loss": 0.0031,
      "step": 1325
    },
    {
      "epoch": 89.01,
      "learning_rate": 4.7020408163265303e-07,
      "loss": 0.0031,
      "step": 1350
    },
    {
      "epoch": 91.0,
      "learning_rate": 4.6e-07,
      "loss": 0.003,
      "step": 1375
    },
    {
      "epoch": 93.0,
      "learning_rate": 4.4979591836734695e-07,
      "loss": 0.0029,
      "step": 1400
    },
    {
      "epoch": 94.01,
      "learning_rate": 4.3959183673469385e-07,
      "loss": 0.0029,
      "step": 1425
    },
    {
      "epoch": 96.0,
      "learning_rate": 4.293877551020408e-07,
      "loss": 0.0028,
      "step": 1450
    },
    {
      "epoch": 98.0,
      "learning_rate": 4.191836734693877e-07,
      "loss": 0.0027,
      "step": 1475
    },
    {
      "epoch": 99.01,
      "learning_rate": 4.089795918367347e-07,
      "loss": 0.0027,
      "step": 1500
    },
    {
      "epoch": 99.01,
      "eval_loss": 0.6944558024406433,
      "eval_runtime": 263.7584,
      "eval_samples_per_second": 5.027,
      "eval_steps_per_second": 0.159,
      "eval_wer": 25.27952835942265,
      "step": 1500
    },
    {
      "epoch": 101.0,
      "learning_rate": 3.987755102040816e-07,
      "loss": 0.0026,
      "step": 1525
    },
    {
      "epoch": 103.0,
      "learning_rate": 3.8857142857142853e-07,
      "loss": 0.0026,
      "step": 1550
    },
    {
      "epoch": 104.01,
      "learning_rate": 3.783673469387755e-07,
      "loss": 0.0025,
      "step": 1575
    },
    {
      "epoch": 106.0,
      "learning_rate": 3.681632653061224e-07,
      "loss": 0.0025,
      "step": 1600
    },
    {
      "epoch": 108.0,
      "learning_rate": 3.579591836734694e-07,
      "loss": 0.0024,
      "step": 1625
    },
    {
      "epoch": 109.01,
      "learning_rate": 3.477551020408163e-07,
      "loss": 0.0024,
      "step": 1650
    },
    {
      "epoch": 111.0,
      "learning_rate": 3.3755102040816326e-07,
      "loss": 0.0023,
      "step": 1675
    },
    {
      "epoch": 113.0,
      "learning_rate": 3.2734693877551016e-07,
      "loss": 0.0023,
      "step": 1700
    },
    {
      "epoch": 114.01,
      "learning_rate": 3.171428571428571e-07,
      "loss": 0.0023,
      "step": 1725
    },
    {
      "epoch": 116.0,
      "learning_rate": 3.0693877551020407e-07,
      "loss": 0.0023,
      "step": 1750
    },
    {
      "epoch": 118.0,
      "learning_rate": 2.9673469387755103e-07,
      "loss": 0.0022,
      "step": 1775
    },
    {
      "epoch": 119.01,
      "learning_rate": 2.8653061224489793e-07,
      "loss": 0.0022,
      "step": 1800
    },
    {
      "epoch": 121.0,
      "learning_rate": 2.763265306122449e-07,
      "loss": 0.0022,
      "step": 1825
    },
    {
      "epoch": 123.0,
      "learning_rate": 2.6612244897959185e-07,
      "loss": 0.0021,
      "step": 1850
    },
    {
      "epoch": 124.01,
      "learning_rate": 2.559183673469388e-07,
      "loss": 0.0021,
      "step": 1875
    },
    {
      "epoch": 126.0,
      "learning_rate": 2.457142857142857e-07,
      "loss": 0.0021,
      "step": 1900
    },
    {
      "epoch": 128.0,
      "learning_rate": 2.3551020408163264e-07,
      "loss": 0.0021,
      "step": 1925
    },
    {
      "epoch": 129.01,
      "learning_rate": 2.253061224489796e-07,
      "loss": 0.002,
      "step": 1950
    },
    {
      "epoch": 131.0,
      "learning_rate": 2.1510204081632652e-07,
      "loss": 0.002,
      "step": 1975
    },
    {
      "epoch": 133.0,
      "learning_rate": 2.0489795918367345e-07,
      "loss": 0.002,
      "step": 2000
    },
    {
      "epoch": 133.0,
      "eval_loss": 0.7078843116760254,
      "eval_runtime": 279.582,
      "eval_samples_per_second": 4.743,
      "eval_steps_per_second": 0.15,
      "eval_wer": 26.478959138036185,
      "step": 2000
    },
    {
      "epoch": 134.01,
      "learning_rate": 1.946938775510204e-07,
      "loss": 0.002,
      "step": 2025
    },
    {
      "epoch": 136.0,
      "learning_rate": 1.8448979591836734e-07,
      "loss": 0.002,
      "step": 2050
    },
    {
      "epoch": 138.0,
      "learning_rate": 1.742857142857143e-07,
      "loss": 0.0019,
      "step": 2075
    },
    {
      "epoch": 139.01,
      "learning_rate": 1.6408163265306123e-07,
      "loss": 0.0019,
      "step": 2100
    },
    {
      "epoch": 141.0,
      "learning_rate": 1.5387755102040818e-07,
      "loss": 0.0019,
      "step": 2125
    },
    {
      "epoch": 143.0,
      "learning_rate": 1.4367346938775509e-07,
      "loss": 0.0019,
      "step": 2150
    },
    {
      "epoch": 144.01,
      "learning_rate": 1.3346938775510202e-07,
      "loss": 0.0019,
      "step": 2175
    },
    {
      "epoch": 146.0,
      "learning_rate": 1.2326530612244897e-07,
      "loss": 0.0019,
      "step": 2200
    },
    {
      "epoch": 148.0,
      "learning_rate": 1.130612244897959e-07,
      "loss": 0.0019,
      "step": 2225
    },
    {
      "epoch": 149.01,
      "learning_rate": 1.0285714285714285e-07,
      "loss": 0.0018,
      "step": 2250
    },
    {
      "epoch": 151.0,
      "learning_rate": 9.265306122448979e-08,
      "loss": 0.0018,
      "step": 2275
    },
    {
      "epoch": 153.0,
      "learning_rate": 8.244897959183673e-08,
      "loss": 0.0018,
      "step": 2300
    },
    {
      "epoch": 154.01,
      "learning_rate": 7.224489795918368e-08,
      "loss": 0.0018,
      "step": 2325
    },
    {
      "epoch": 156.0,
      "learning_rate": 6.20408163265306e-08,
      "loss": 0.0018,
      "step": 2350
    },
    {
      "epoch": 158.0,
      "learning_rate": 5.183673469387754e-08,
      "loss": 0.0018,
      "step": 2375
    },
    {
      "epoch": 159.01,
      "learning_rate": 4.1632653061224486e-08,
      "loss": 0.0018,
      "step": 2400
    },
    {
      "epoch": 161.0,
      "learning_rate": 3.142857142857143e-08,
      "loss": 0.0018,
      "step": 2425
    },
    {
      "epoch": 163.0,
      "learning_rate": 2.122448979591837e-08,
      "loss": 0.0018,
      "step": 2450
    },
    {
      "epoch": 164.01,
      "learning_rate": 1.1020408163265306e-08,
      "loss": 0.0018,
      "step": 2475
    },
    {
      "epoch": 166.0,
      "learning_rate": 8.163265306122449e-10,
      "loss": 0.0018,
      "step": 2500
    },
    {
      "epoch": 166.0,
      "eval_loss": 0.7126978635787964,
      "eval_runtime": 279.4326,
      "eval_samples_per_second": 4.745,
      "eval_steps_per_second": 0.15,
      "eval_wer": 26.397641797113238,
      "step": 2500
    },
    {
      "epoch": 166.0,
      "step": 2500,
      "total_flos": 4.579042263957504e+19,
      "train_loss": 0.05099657071977854,
      "train_runtime": 22043.5536,
      "train_samples_per_second": 7.258,
      "train_steps_per_second": 0.113
    }
  ],
  "logging_steps": 25,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 4.579042263957504e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}