{
  "best_metric": 15.901153962951717,
  "best_model_checkpoint": "./checkpoint-3000",
  "epoch": 9.049,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.2e-06,
      "loss": 0.9692,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.7e-06,
      "loss": 0.309,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 7.2e-06,
      "loss": 0.1594,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.7e-06,
      "loss": 0.1527,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.22e-05,
      "loss": 0.1466,
      "step": 125
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.47e-05,
      "loss": 0.1414,
      "step": 150
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.7199999999999998e-05,
      "loss": 0.1506,
      "step": 175
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.97e-05,
      "loss": 0.1633,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.22e-05,
      "loss": 0.1928,
      "step": 225
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.47e-05,
      "loss": 0.187,
      "step": 250
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.7200000000000004e-05,
      "loss": 0.1939,
      "step": 275
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.97e-05,
      "loss": 0.1699,
      "step": 300
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.2200000000000003e-05,
      "loss": 0.198,
      "step": 325
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.4699999999999996e-05,
      "loss": 0.2113,
      "step": 350
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.72e-05,
      "loss": 0.1882,
      "step": 375
    },
    {
      "epoch": 1.03,
      "learning_rate": 3.97e-05,
      "loss": 0.144,
      "step": 400
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.22e-05,
      "loss": 0.1408,
      "step": 425
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.47e-05,
      "loss": 0.1388,
      "step": 450
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.72e-05,
      "loss": 0.1444,
      "step": 475
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.97e-05,
      "loss": 0.1456,
      "step": 500
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.956e-05,
      "loss": 0.16,
      "step": 525
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.906e-05,
      "loss": 0.1578,
      "step": 550
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.856e-05,
      "loss": 0.1387,
      "step": 575
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.8060000000000004e-05,
      "loss": 0.1499,
      "step": 600
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.7560000000000005e-05,
      "loss": 0.1323,
      "step": 625
    },
    {
      "epoch": 2.01,
      "learning_rate": 4.706000000000001e-05,
      "loss": 0.158,
      "step": 650
    },
    {
      "epoch": 2.01,
      "learning_rate": 4.656e-05,
      "loss": 0.1479,
      "step": 675
    },
    {
      "epoch": 2.02,
      "learning_rate": 4.606e-05,
      "loss": 0.1252,
      "step": 700
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.5560000000000004e-05,
      "loss": 0.1246,
      "step": 725
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.506e-05,
      "loss": 0.1201,
      "step": 750
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.456e-05,
      "loss": 0.0986,
      "step": 775
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.406e-05,
      "loss": 0.1088,
      "step": 800
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.356e-05,
      "loss": 0.1078,
      "step": 825
    },
    {
      "epoch": 2.07,
      "learning_rate": 4.306e-05,
      "loss": 0.1135,
      "step": 850
    },
    {
      "epoch": 2.08,
      "learning_rate": 4.256e-05,
      "loss": 0.1058,
      "step": 875
    },
    {
      "epoch": 2.09,
      "learning_rate": 4.206e-05,
      "loss": 0.0886,
      "step": 900
    },
    {
      "epoch": 2.1,
      "learning_rate": 4.156e-05,
      "loss": 0.0906,
      "step": 925
    },
    {
      "epoch": 2.11,
      "learning_rate": 4.106e-05,
      "loss": 0.0828,
      "step": 950
    },
    {
      "epoch": 3.01,
      "learning_rate": 4.0560000000000005e-05,
      "loss": 0.0957,
      "step": 975
    },
    {
      "epoch": 3.02,
      "learning_rate": 4.0060000000000006e-05,
      "loss": 0.0856,
      "step": 1000
    },
    {
      "epoch": 3.02,
      "eval_loss": 0.3732326328754425,
      "eval_runtime": 7430.1269,
      "eval_samples_per_second": 1.365,
      "eval_steps_per_second": 0.043,
      "eval_wer": 20.67643486182812,
      "step": 1000
    },
    {
      "epoch": 3.02,
      "learning_rate": 3.956e-05,
      "loss": 0.0715,
      "step": 1025
    },
    {
      "epoch": 3.03,
      "learning_rate": 3.906e-05,
      "loss": 0.0813,
      "step": 1050
    },
    {
      "epoch": 3.04,
      "learning_rate": 3.8560000000000004e-05,
      "loss": 0.0681,
      "step": 1075
    },
    {
      "epoch": 3.05,
      "learning_rate": 3.806e-05,
      "loss": 0.0654,
      "step": 1100
    },
    {
      "epoch": 3.06,
      "learning_rate": 3.756e-05,
      "loss": 0.0698,
      "step": 1125
    },
    {
      "epoch": 3.07,
      "learning_rate": 3.706e-05,
      "loss": 0.0633,
      "step": 1150
    },
    {
      "epoch": 3.07,
      "learning_rate": 3.656e-05,
      "loss": 0.0657,
      "step": 1175
    },
    {
      "epoch": 3.08,
      "learning_rate": 3.606e-05,
      "loss": 0.0532,
      "step": 1200
    },
    {
      "epoch": 3.09,
      "learning_rate": 3.5560000000000005e-05,
      "loss": 0.0545,
      "step": 1225
    },
    {
      "epoch": 3.1,
      "learning_rate": 3.5060000000000007e-05,
      "loss": 0.0511,
      "step": 1250
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.456e-05,
      "loss": 0.0654,
      "step": 1275
    },
    {
      "epoch": 4.01,
      "learning_rate": 3.406e-05,
      "loss": 0.063,
      "step": 1300
    },
    {
      "epoch": 4.02,
      "learning_rate": 3.3560000000000004e-05,
      "loss": 0.0532,
      "step": 1325
    },
    {
      "epoch": 4.03,
      "learning_rate": 3.3060000000000005e-05,
      "loss": 0.0427,
      "step": 1350
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.256e-05,
      "loss": 0.0483,
      "step": 1375
    },
    {
      "epoch": 4.04,
      "learning_rate": 3.206e-05,
      "loss": 0.0462,
      "step": 1400
    },
    {
      "epoch": 4.05,
      "learning_rate": 3.156e-05,
      "loss": 0.0417,
      "step": 1425
    },
    {
      "epoch": 4.06,
      "learning_rate": 3.106e-05,
      "loss": 0.0408,
      "step": 1450
    },
    {
      "epoch": 4.07,
      "learning_rate": 3.056e-05,
      "loss": 0.0355,
      "step": 1475
    },
    {
      "epoch": 4.08,
      "learning_rate": 3.006e-05,
      "loss": 0.0426,
      "step": 1500
    },
    {
      "epoch": 4.09,
      "learning_rate": 2.9559999999999998e-05,
      "loss": 0.033,
      "step": 1525
    },
    {
      "epoch": 4.09,
      "learning_rate": 2.9060000000000003e-05,
      "loss": 0.0403,
      "step": 1550
    },
    {
      "epoch": 4.1,
      "learning_rate": 2.8560000000000004e-05,
      "loss": 0.0274,
      "step": 1575
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.8060000000000002e-05,
      "loss": 0.0333,
      "step": 1600
    },
    {
      "epoch": 5.01,
      "learning_rate": 2.7560000000000004e-05,
      "loss": 0.0323,
      "step": 1625
    },
    {
      "epoch": 5.02,
      "learning_rate": 2.7060000000000002e-05,
      "loss": 0.0286,
      "step": 1650
    },
    {
      "epoch": 5.03,
      "learning_rate": 2.6560000000000003e-05,
      "loss": 0.0263,
      "step": 1675
    },
    {
      "epoch": 5.04,
      "learning_rate": 2.606e-05,
      "loss": 0.0249,
      "step": 1700
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.556e-05,
      "loss": 0.0218,
      "step": 1725
    },
    {
      "epoch": 5.05,
      "learning_rate": 2.506e-05,
      "loss": 0.0201,
      "step": 1750
    },
    {
      "epoch": 5.06,
      "learning_rate": 2.4560000000000002e-05,
      "loss": 0.0219,
      "step": 1775
    },
    {
      "epoch": 5.07,
      "learning_rate": 2.4060000000000003e-05,
      "loss": 0.0219,
      "step": 1800
    },
    {
      "epoch": 5.08,
      "learning_rate": 2.356e-05,
      "loss": 0.0217,
      "step": 1825
    },
    {
      "epoch": 5.09,
      "learning_rate": 2.306e-05,
      "loss": 0.0176,
      "step": 1850
    },
    {
      "epoch": 5.1,
      "learning_rate": 2.256e-05,
      "loss": 0.0211,
      "step": 1875
    },
    {
      "epoch": 5.11,
      "learning_rate": 2.206e-05,
      "loss": 0.0169,
      "step": 1900
    },
    {
      "epoch": 6.01,
      "learning_rate": 2.1560000000000004e-05,
      "loss": 0.0222,
      "step": 1925
    },
    {
      "epoch": 6.02,
      "learning_rate": 2.106e-05,
      "loss": 0.0172,
      "step": 1950
    },
    {
      "epoch": 6.02,
      "learning_rate": 2.0560000000000003e-05,
      "loss": 0.0152,
      "step": 1975
    },
    {
      "epoch": 6.03,
      "learning_rate": 2.006e-05,
      "loss": 0.0119,
      "step": 2000
    },
    {
      "epoch": 6.03,
      "eval_loss": 0.3684307634830475,
      "eval_runtime": 6884.4626,
      "eval_samples_per_second": 1.473,
      "eval_steps_per_second": 0.046,
      "eval_wer": 17.535302156088672,
      "step": 2000
    },
    {
      "epoch": 6.04,
      "learning_rate": 1.956e-05,
      "loss": 0.0107,
      "step": 2025
    },
    {
      "epoch": 6.05,
      "learning_rate": 1.906e-05,
      "loss": 0.009,
      "step": 2050
    },
    {
      "epoch": 6.06,
      "learning_rate": 1.856e-05,
      "loss": 0.0155,
      "step": 2075
    },
    {
      "epoch": 6.07,
      "learning_rate": 1.8060000000000003e-05,
      "loss": 0.0129,
      "step": 2100
    },
    {
      "epoch": 6.07,
      "learning_rate": 1.756e-05,
      "loss": 0.0119,
      "step": 2125
    },
    {
      "epoch": 6.08,
      "learning_rate": 1.706e-05,
      "loss": 0.0074,
      "step": 2150
    },
    {
      "epoch": 6.09,
      "learning_rate": 1.656e-05,
      "loss": 0.0062,
      "step": 2175
    },
    {
      "epoch": 6.1,
      "learning_rate": 1.606e-05,
      "loss": 0.0052,
      "step": 2200
    },
    {
      "epoch": 7.0,
      "learning_rate": 1.556e-05,
      "loss": 0.0091,
      "step": 2225
    },
    {
      "epoch": 7.01,
      "learning_rate": 1.5060000000000001e-05,
      "loss": 0.0086,
      "step": 2250
    },
    {
      "epoch": 7.02,
      "learning_rate": 1.4560000000000001e-05,
      "loss": 0.0079,
      "step": 2275
    },
    {
      "epoch": 7.03,
      "learning_rate": 1.4060000000000001e-05,
      "loss": 0.0076,
      "step": 2300
    },
    {
      "epoch": 7.04,
      "learning_rate": 1.356e-05,
      "loss": 0.0052,
      "step": 2325
    },
    {
      "epoch": 7.04,
      "learning_rate": 1.306e-05,
      "loss": 0.0041,
      "step": 2350
    },
    {
      "epoch": 7.05,
      "learning_rate": 1.256e-05,
      "loss": 0.004,
      "step": 2375
    },
    {
      "epoch": 7.06,
      "learning_rate": 1.206e-05,
      "loss": 0.0032,
      "step": 2400
    },
    {
      "epoch": 7.07,
      "learning_rate": 1.156e-05,
      "loss": 0.0073,
      "step": 2425
    },
    {
      "epoch": 7.08,
      "learning_rate": 1.106e-05,
      "loss": 0.0048,
      "step": 2450
    },
    {
      "epoch": 7.09,
      "learning_rate": 1.056e-05,
      "loss": 0.0027,
      "step": 2475
    },
    {
      "epoch": 7.09,
      "learning_rate": 1.006e-05,
      "loss": 0.0032,
      "step": 2500
    },
    {
      "epoch": 7.1,
      "learning_rate": 9.560000000000002e-06,
      "loss": 0.0024,
      "step": 2525
    },
    {
      "epoch": 8.0,
      "learning_rate": 9.06e-06,
      "loss": 0.0033,
      "step": 2550
    },
    {
      "epoch": 8.01,
      "learning_rate": 8.56e-06,
      "loss": 0.0022,
      "step": 2575
    },
    {
      "epoch": 8.02,
      "learning_rate": 8.06e-06,
      "loss": 0.0027,
      "step": 2600
    },
    {
      "epoch": 8.03,
      "learning_rate": 7.5600000000000005e-06,
      "loss": 0.0014,
      "step": 2625
    },
    {
      "epoch": 8.04,
      "learning_rate": 7.06e-06,
      "loss": 0.0014,
      "step": 2650
    },
    {
      "epoch": 8.05,
      "learning_rate": 6.560000000000001e-06,
      "loss": 0.0025,
      "step": 2675
    },
    {
      "epoch": 8.05,
      "learning_rate": 6.0600000000000004e-06,
      "loss": 0.0011,
      "step": 2700
    },
    {
      "epoch": 8.06,
      "learning_rate": 5.56e-06,
      "loss": 0.0008,
      "step": 2725
    },
    {
      "epoch": 8.07,
      "learning_rate": 5.06e-06,
      "loss": 0.0016,
      "step": 2750
    },
    {
      "epoch": 8.08,
      "learning_rate": 4.56e-06,
      "loss": 0.001,
      "step": 2775
    },
    {
      "epoch": 8.09,
      "learning_rate": 4.06e-06,
      "loss": 0.0005,
      "step": 2800
    },
    {
      "epoch": 8.1,
      "learning_rate": 3.5600000000000002e-06,
      "loss": 0.0009,
      "step": 2825
    },
    {
      "epoch": 8.1,
      "learning_rate": 3.06e-06,
      "loss": 0.0005,
      "step": 2850
    },
    {
      "epoch": 9.01,
      "learning_rate": 2.56e-06,
      "loss": 0.0007,
      "step": 2875
    },
    {
      "epoch": 9.02,
      "learning_rate": 2.06e-06,
      "loss": 0.0005,
      "step": 2900
    },
    {
      "epoch": 9.02,
      "learning_rate": 1.56e-06,
      "loss": 0.0007,
      "step": 2925
    },
    {
      "epoch": 9.03,
      "learning_rate": 1.06e-06,
      "loss": 0.0004,
      "step": 2950
    },
    {
      "epoch": 9.04,
      "learning_rate": 5.6e-07,
      "loss": 0.0008,
      "step": 2975
    },
    {
      "epoch": 9.05,
      "learning_rate": 6e-08,
      "loss": 0.001,
      "step": 3000
    },
    {
      "epoch": 9.05,
      "eval_loss": 0.361074298620224,
      "eval_runtime": 6919.6339,
      "eval_samples_per_second": 1.466,
      "eval_steps_per_second": 0.046,
      "eval_wer": 15.901153962951717,
      "step": 3000
    },
    {
      "epoch": 9.05,
      "step": 3000,
      "total_flos": 1.9564383714213888e+20,
      "train_loss": 0.07008407963408778,
      "train_runtime": 69355.5101,
      "train_samples_per_second": 2.768,
      "train_steps_per_second": 0.043
    }
  ],
  "max_steps": 3000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 1.9564383714213888e+20,
  "trial_name": null,
  "trial_params": null
}