{
  "best_metric": 19.095815786035196,
  "best_model_checkpoint": "./Graduation_Project_Whisper_base/checkpoint-2400",
  "epoch": 1.9994079336885733,
  "eval_steps": 400,
  "global_step": 2532,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03764351590438547,
      "grad_norm": 503138.9375,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.5445,
      "step": 50
    },
    {
      "epoch": 0.07528703180877094,
      "grad_norm": 226777.984375,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.1677,
      "step": 100
    },
    {
      "epoch": 0.11293054771315642,
      "grad_norm": 162510.234375,
      "learning_rate": 3e-06,
      "loss": 0.1051,
      "step": 150
    },
    {
      "epoch": 0.1505740636175419,
      "grad_norm": 163651.140625,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0785,
      "step": 200
    },
    {
      "epoch": 0.18821757952192736,
      "grad_norm": 146978.328125,
      "learning_rate": 5e-06,
      "loss": 0.0657,
      "step": 250
    },
    {
      "epoch": 0.22586109542631283,
      "grad_norm": 131384.75,
      "learning_rate": 6e-06,
      "loss": 0.054,
      "step": 300
    },
    {
      "epoch": 0.2635046113306983,
      "grad_norm": 127696.390625,
      "learning_rate": 7e-06,
      "loss": 0.0488,
      "step": 350
    },
    {
      "epoch": 0.3011481272350838,
      "grad_norm": 138088.9375,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0425,
      "step": 400
    },
    {
      "epoch": 0.3011481272350838,
      "eval_cer": 11.295171257365732,
      "eval_loss": 0.03295731544494629,
      "eval_runtime": 3971.8715,
      "eval_samples_per_second": 2.429,
      "eval_steps_per_second": 0.152,
      "eval_wer": 37.69008874996231,
      "step": 400
    },
    {
      "epoch": 0.33879164313946925,
      "grad_norm": 127706.0390625,
      "learning_rate": 9e-06,
      "loss": 0.0375,
      "step": 450
    },
    {
      "epoch": 0.3764351590438547,
      "grad_norm": 119614.671875,
      "learning_rate": 1e-05,
      "loss": 0.034,
      "step": 500
    },
    {
      "epoch": 0.4140786749482402,
      "grad_norm": 125161.125,
      "learning_rate": 9.91029509614553e-06,
      "loss": 0.0328,
      "step": 550
    },
    {
      "epoch": 0.45172219085262566,
      "grad_norm": 111814.9609375,
      "learning_rate": 9.644399172492337e-06,
      "loss": 0.0271,
      "step": 600
    },
    {
      "epoch": 0.48936570675701113,
      "grad_norm": 147685.515625,
      "learning_rate": 9.211853096347059e-06,
      "loss": 0.0298,
      "step": 650
    },
    {
      "epoch": 0.5270092226613966,
      "grad_norm": 169561.140625,
      "learning_rate": 8.628177469378995e-06,
      "loss": 0.0302,
      "step": 700
    },
    {
      "epoch": 0.564652738565782,
      "grad_norm": 72348.1328125,
      "learning_rate": 7.914315717987892e-06,
      "loss": 0.0235,
      "step": 750
    },
    {
      "epoch": 0.6022962544701675,
      "grad_norm": 95024.140625,
      "learning_rate": 7.095882602083321e-06,
      "loss": 0.0258,
      "step": 800
    },
    {
      "epoch": 0.6022962544701675,
      "eval_cer": 7.953864927074945,
      "eval_loss": 0.021815981715917587,
      "eval_runtime": 3808.1602,
      "eval_samples_per_second": 2.533,
      "eval_steps_per_second": 0.158,
      "eval_wer": 25.474153960580143,
      "step": 800
    },
    {
      "epoch": 0.639939770374553,
      "grad_norm": 77923.2734375,
      "learning_rate": 6.2022451072546926e-06,
      "loss": 0.0225,
      "step": 850
    },
    {
      "epoch": 0.6775832862789385,
      "grad_norm": 128029.6015625,
      "learning_rate": 5.265468699723748e-06,
      "loss": 0.024,
      "step": 900
    },
    {
      "epoch": 0.7152268021833239,
      "grad_norm": 132533.578125,
      "learning_rate": 4.319166754518768e-06,
      "loss": 0.0234,
      "step": 950
    },
    {
      "epoch": 0.7528703180877094,
      "grad_norm": 92432.9453125,
      "learning_rate": 3.397294441644515e-06,
      "loss": 0.0199,
      "step": 1000
    },
    {
      "epoch": 0.7905138339920948,
      "grad_norm": 94760.9453125,
      "learning_rate": 2.5329303479779855e-06,
      "loss": 0.0224,
      "step": 1050
    },
    {
      "epoch": 0.8281573498964804,
      "grad_norm": 75528.8984375,
      "learning_rate": 1.7570895526862202e-06,
      "loss": 0.0204,
      "step": 1100
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 125463.9296875,
      "learning_rate": 1.0976107453484314e-06,
      "loss": 0.0199,
      "step": 1150
    },
    {
      "epoch": 0.9034443817052513,
      "grad_norm": 139042.265625,
      "learning_rate": 5.781573191671386e-07,
      "loss": 0.0197,
      "step": 1200
    },
    {
      "epoch": 0.9034443817052513,
      "eval_cer": 7.018806706804402,
      "eval_loss": 0.01941610500216484,
      "eval_runtime": 3809.2886,
      "eval_samples_per_second": 2.532,
      "eval_steps_per_second": 0.158,
      "eval_wer": 22.336244760937955,
      "step": 1200
    },
    {
      "epoch": 0.9410878976096367,
      "grad_norm": 87157.8125,
      "learning_rate": 2.1736828200332628e-07,
      "loss": 0.0207,
      "step": 1250
    },
    {
      "epoch": 0.9787314135140223,
      "grad_norm": 90153.140625,
      "learning_rate": 2.8189452213207014e-08,
      "loss": 0.0195,
      "step": 1300
    },
    {
      "epoch": 1.0663114268798106,
      "grad_norm": 81696.2734375,
      "learning_rate": 6.269188506178019e-06,
      "loss": 0.0116,
      "step": 1350
    },
    {
      "epoch": 1.1057825143082691,
      "grad_norm": 81981.46875,
      "learning_rate": 5.891915195166075e-06,
      "loss": 0.0106,
      "step": 1400
    },
    {
      "epoch": 1.1452536017367279,
      "grad_norm": 76380.390625,
      "learning_rate": 5.509314676457187e-06,
      "loss": 0.0101,
      "step": 1450
    },
    {
      "epoch": 1.1847246891651866,
      "grad_norm": 70844.5625,
      "learning_rate": 5.123672136399975e-06,
      "loss": 0.0092,
      "step": 1500
    },
    {
      "epoch": 1.224195776593645,
      "grad_norm": 75742.8828125,
      "learning_rate": 4.737290930648428e-06,
      "loss": 0.0082,
      "step": 1550
    },
    {
      "epoch": 1.2636668640221038,
      "grad_norm": 55820.46484375,
      "learning_rate": 4.352478826739623e-06,
      "loss": 0.0083,
      "step": 1600
    },
    {
      "epoch": 1.2636668640221038,
      "eval_cer": 6.160355666025902,
      "eval_loss": 0.01826481893658638,
      "eval_runtime": 4336.2114,
      "eval_samples_per_second": 2.225,
      "eval_steps_per_second": 0.139,
      "eval_wer": 20.22252821806559,
      "step": 1600
    },
    {
      "epoch": 1.3031379514505623,
      "grad_norm": 73017.6015625,
      "learning_rate": 3.971534220320291e-06,
      "loss": 0.0085,
      "step": 1650
    },
    {
      "epoch": 1.342609038879021,
      "grad_norm": 47336.1015625,
      "learning_rate": 3.5967324073495363e-06,
      "loss": 0.0081,
      "step": 1700
    },
    {
      "epoch": 1.3820801263074798,
      "grad_norm": 79073.7421875,
      "learning_rate": 3.2303119942707794e-06,
      "loss": 0.0075,
      "step": 1750
    },
    {
      "epoch": 1.4215512137359383,
      "grad_norm": 68802.984375,
      "learning_rate": 2.8744615273218836e-06,
      "loss": 0.0074,
      "step": 1800
    },
    {
      "epoch": 1.461022301164397,
      "grad_norm": 60333.73828125,
      "learning_rate": 2.531306420843542e-06,
      "loss": 0.007,
      "step": 1850
    },
    {
      "epoch": 1.5004933885928557,
      "grad_norm": 52213.80859375,
      "learning_rate": 2.2028962626602346e-06,
      "loss": 0.007,
      "step": 1900
    },
    {
      "epoch": 1.5399644760213143,
      "grad_norm": 48230.20703125,
      "learning_rate": 1.8911925723557807e-06,
      "loss": 0.0068,
      "step": 1950
    },
    {
      "epoch": 1.5794355634497732,
      "grad_norm": 49029.17578125,
      "learning_rate": 1.5980570855606025e-06,
      "loss": 0.0066,
      "step": 2000
    },
    {
      "epoch": 1.5794355634497732,
      "eval_cer": 5.946899128741567,
      "eval_loss": 0.01755833439528942,
      "eval_runtime": 4292.0414,
      "eval_samples_per_second": 2.248,
      "eval_steps_per_second": 0.14,
      "eval_wer": 19.420461741027005,
      "step": 2000
    },
    {
      "epoch": 1.6189066508782317,
      "grad_norm": 70595.109375,
      "learning_rate": 1.3252406342259527e-06,
      "loss": 0.0069,
      "step": 2050
    },
    {
      "epoch": 1.6583777383066902,
      "grad_norm": 50325.43359375,
      "learning_rate": 1.0743726893007257e-06,
      "loss": 0.0065,
      "step": 2100
    },
    {
      "epoch": 1.6978488257351492,
      "grad_norm": 45970.44921875,
      "learning_rate": 8.469516282700979e-07,
      "loss": 0.0067,
      "step": 2150
    },
    {
      "epoch": 1.7373199131636077,
      "grad_norm": 70741.96875,
      "learning_rate": 6.443357856857563e-07,
      "loss": 0.0067,
      "step": 2200
    },
    {
      "epoch": 1.7767910005920662,
      "grad_norm": 51143.1953125,
      "learning_rate": 4.677353401408974e-07,
      "loss": 0.0063,
      "step": 2250
    },
    {
      "epoch": 1.816262088020525,
      "grad_norm": 58438.66796875,
      "learning_rate": 3.182050861472541e-07,
      "loss": 0.0067,
      "step": 2300
    },
    {
      "epoch": 1.8557331754489836,
      "grad_norm": 65700.25,
      "learning_rate": 1.9663813408607845e-07,
      "loss": 0.0065,
      "step": 2350
    },
    {
      "epoch": 1.8952042628774421,
      "grad_norm": 52580.59765625,
      "learning_rate": 1.0376057586187538e-07,
      "loss": 0.0065,
      "step": 2400
    },
    {
      "epoch": 1.8952042628774421,
      "eval_cer": 5.860923579002043,
      "eval_loss": 0.017402183264493942,
      "eval_runtime": 4269.4409,
      "eval_samples_per_second": 2.26,
      "eval_steps_per_second": 0.141,
      "eval_wer": 19.095815786035196,
      "step": 2400
    },
    {
      "epoch": 1.9346753503059009,
      "grad_norm": 53811.92578125,
      "learning_rate": 4.012714811970464e-08,
      "loss": 0.0059,
      "step": 2450
    },
    {
      "epoch": 1.9741464377343596,
      "grad_norm": 51623.82421875,
      "learning_rate": 6.117918928693623e-09,
      "loss": 0.0066,
      "step": 2500
    },
    {
      "epoch": 1.9994079336885733,
      "step": 2532,
      "total_flos": 1.051043265773568e+19,
      "train_loss": 0.003555825636332257,
      "train_runtime": 25310.9727,
      "train_samples_per_second": 6.405,
      "train_steps_per_second": 0.1
    }
  ],
  "logging_steps": 50,
  "max_steps": 2532,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.051043265773568e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}