{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.6775106082036775,
  "eval_steps": 100,
  "global_step": 2600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14144271570014144,
      "eval_loss": 4.10262393951416,
      "eval_runtime": 154.9611,
      "eval_samples_per_second": 36.499,
      "eval_steps_per_second": 4.562,
      "eval_wer": 1.0,
      "step": 100
    },
    {
      "epoch": 0.2828854314002829,
      "eval_loss": 3.3531899452209473,
      "eval_runtime": 152.1716,
      "eval_samples_per_second": 37.169,
      "eval_steps_per_second": 4.646,
      "eval_wer": 1.0,
      "step": 200
    },
    {
      "epoch": 0.4243281471004243,
      "eval_loss": 3.2421672344207764,
      "eval_runtime": 153.7959,
      "eval_samples_per_second": 36.776,
      "eval_steps_per_second": 4.597,
      "eval_wer": 1.0,
      "step": 300
    },
    {
      "epoch": 0.5657708628005658,
      "eval_loss": 3.0640172958374023,
      "eval_runtime": 153.0843,
      "eval_samples_per_second": 36.947,
      "eval_steps_per_second": 4.618,
      "eval_wer": 1.0,
      "step": 400
    },
    {
      "epoch": 0.7072135785007072,
      "grad_norm": 5.922334671020508,
      "learning_rate": 0.0002964,
      "loss": 3.608,
      "step": 500
    },
    {
      "epoch": 0.7072135785007072,
      "eval_loss": 3.2418580055236816,
      "eval_runtime": 154.0057,
      "eval_samples_per_second": 36.726,
      "eval_steps_per_second": 4.591,
      "eval_wer": 1.0,
      "step": 500
    },
    {
      "epoch": 0.8486562942008486,
      "eval_loss": 3.225853204727173,
      "eval_runtime": 154.2356,
      "eval_samples_per_second": 36.671,
      "eval_steps_per_second": 4.584,
      "eval_wer": 1.0,
      "step": 600
    },
    {
      "epoch": 0.9900990099009901,
      "eval_loss": 3.090954303741455,
      "eval_runtime": 152.9981,
      "eval_samples_per_second": 36.968,
      "eval_steps_per_second": 4.621,
      "eval_wer": 1.0,
      "step": 700
    },
    {
      "epoch": 1.1315417256011315,
      "eval_loss": 2.974919557571411,
      "eval_runtime": 154.1252,
      "eval_samples_per_second": 36.697,
      "eval_steps_per_second": 4.587,
      "eval_wer": 1.0,
      "step": 800
    },
    {
      "epoch": 1.272984441301273,
      "eval_loss": 2.970212697982788,
      "eval_runtime": 154.8782,
      "eval_samples_per_second": 36.519,
      "eval_steps_per_second": 4.565,
      "eval_wer": 1.0,
      "step": 900
    },
    {
      "epoch": 1.4144271570014144,
      "grad_norm": 1.7771501541137695,
      "learning_rate": 0.0002294285714285714,
      "loss": 3.0077,
      "step": 1000
    },
    {
      "epoch": 1.4144271570014144,
      "eval_loss": 2.977414846420288,
      "eval_runtime": 154.2248,
      "eval_samples_per_second": 36.674,
      "eval_steps_per_second": 4.584,
      "eval_wer": 1.0,
      "step": 1000
    },
    {
      "epoch": 1.5558698727015559,
      "eval_loss": 2.9689409732818604,
      "eval_runtime": 154.7038,
      "eval_samples_per_second": 36.56,
      "eval_steps_per_second": 4.57,
      "eval_wer": 1.0,
      "step": 1100
    },
    {
      "epoch": 1.6973125884016973,
      "eval_loss": 2.96563458442688,
      "eval_runtime": 155.7804,
      "eval_samples_per_second": 36.308,
      "eval_steps_per_second": 4.538,
      "eval_wer": 1.0,
      "step": 1200
    },
    {
      "epoch": 1.8387553041018387,
      "eval_loss": 2.998167037963867,
      "eval_runtime": 154.8051,
      "eval_samples_per_second": 36.536,
      "eval_steps_per_second": 4.567,
      "eval_wer": 1.0,
      "step": 1300
    },
    {
      "epoch": 1.9801980198019802,
      "eval_loss": 2.9851789474487305,
      "eval_runtime": 157.281,
      "eval_samples_per_second": 35.961,
      "eval_steps_per_second": 4.495,
      "eval_wer": 1.0,
      "step": 1400
    },
    {
      "epoch": 2.1216407355021216,
      "grad_norm": 1.3770530223846436,
      "learning_rate": 0.0001584285714285714,
      "loss": 2.9933,
      "step": 1500
    },
    {
      "epoch": 2.1216407355021216,
      "eval_loss": 2.983766555786133,
      "eval_runtime": 154.5498,
      "eval_samples_per_second": 36.597,
      "eval_steps_per_second": 4.575,
      "eval_wer": 1.0,
      "step": 1500
    },
    {
      "epoch": 2.263083451202263,
      "eval_loss": 2.9718267917633057,
      "eval_runtime": 154.4047,
      "eval_samples_per_second": 36.631,
      "eval_steps_per_second": 4.579,
      "eval_wer": 1.0,
      "step": 1600
    },
    {
      "epoch": 2.4045261669024045,
      "eval_loss": 2.9711246490478516,
      "eval_runtime": 156.2998,
      "eval_samples_per_second": 36.187,
      "eval_steps_per_second": 4.523,
      "eval_wer": 1.0,
      "step": 1700
    },
    {
      "epoch": 2.545968882602546,
      "eval_loss": 2.9617552757263184,
      "eval_runtime": 156.1331,
      "eval_samples_per_second": 36.226,
      "eval_steps_per_second": 4.528,
      "eval_wer": 1.0,
      "step": 1800
    },
    {
      "epoch": 2.6874115983026874,
      "eval_loss": 2.9542484283447266,
      "eval_runtime": 155.1742,
      "eval_samples_per_second": 36.449,
      "eval_steps_per_second": 4.556,
      "eval_wer": 1.0,
      "step": 1900
    },
    {
      "epoch": 2.828854314002829,
      "grad_norm": 2.6072192192077637,
      "learning_rate": 8.742857142857142e-05,
      "loss": 3.0924,
      "step": 2000
    },
    {
      "epoch": 2.828854314002829,
      "eval_loss": 2.9699807167053223,
      "eval_runtime": 156.7707,
      "eval_samples_per_second": 36.078,
      "eval_steps_per_second": 4.51,
      "eval_wer": 1.0,
      "step": 2000
    },
    {
      "epoch": 2.9702970297029703,
      "eval_loss": 2.9556074142456055,
      "eval_runtime": 156.4942,
      "eval_samples_per_second": 36.142,
      "eval_steps_per_second": 4.518,
      "eval_wer": 1.0,
      "step": 2100
    },
    {
      "epoch": 3.1117397454031117,
      "eval_loss": 2.947584629058838,
      "eval_runtime": 156.7459,
      "eval_samples_per_second": 36.084,
      "eval_steps_per_second": 4.51,
      "eval_wer": 1.0,
      "step": 2200
    },
    {
      "epoch": 3.253182461103253,
      "eval_loss": 2.9511587619781494,
      "eval_runtime": 156.6674,
      "eval_samples_per_second": 36.102,
      "eval_steps_per_second": 4.513,
      "eval_wer": 1.0,
      "step": 2300
    },
    {
      "epoch": 3.3946251768033946,
      "eval_loss": 2.949030637741089,
      "eval_runtime": 156.7295,
      "eval_samples_per_second": 36.088,
      "eval_steps_per_second": 4.511,
      "eval_wer": 1.0,
      "step": 2400
    },
    {
      "epoch": 3.536067892503536,
      "grad_norm": 5.350417613983154,
      "learning_rate": 1.6285714285714283e-05,
      "loss": 2.9765,
      "step": 2500
    },
    {
      "epoch": 3.536067892503536,
      "eval_loss": 2.9975638389587402,
      "eval_runtime": 157.876,
      "eval_samples_per_second": 35.826,
      "eval_steps_per_second": 4.478,
      "eval_wer": 1.0,
      "step": 2500
    },
    {
      "epoch": 3.6775106082036775,
      "eval_loss": 2.9536802768707275,
      "eval_runtime": 157.8256,
      "eval_samples_per_second": 35.837,
      "eval_steps_per_second": 4.48,
      "eval_wer": 1.0,
      "step": 2600
    },
    {
      "epoch": 3.6775106082036775,
      "step": 2600,
      "total_flos": 9.931497341662648e+18,
      "train_loss": 3.129935314471905,
      "train_runtime": 6863.5717,
      "train_samples_per_second": 12.122,
      "train_steps_per_second": 0.379
    }
  ],
  "logging_steps": 500,
  "max_steps": 2600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.931497341662648e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}