{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 135,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 34.00384521484375,
      "learning_rate": 9.776119402985076e-06,
      "loss": 3.5666,
      "step": 10
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 14.095426559448242,
      "learning_rate": 9.029850746268657e-06,
      "loss": 1.9468,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_cer": 0.3796859980775393,
      "eval_loss": 0.9999122619628906,
      "eval_runtime": 91.0467,
      "eval_samples_per_second": 13.872,
      "eval_steps_per_second": 0.055,
      "eval_wer": 0.9633358058705097,
      "step": 27
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 6.282424449920654,
      "learning_rate": 8.283582089552239e-06,
      "loss": 1.1917,
      "step": 30
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 4.256287574768066,
      "learning_rate": 7.537313432835821e-06,
      "loss": 0.8244,
      "step": 40
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 2.4645814895629883,
      "learning_rate": 6.791044776119403e-06,
      "loss": 0.6132,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_cer": 0.1469174661213412,
      "eval_loss": 0.468128502368927,
      "eval_runtime": 87.6022,
      "eval_samples_per_second": 14.417,
      "eval_steps_per_second": 0.057,
      "eval_wer": 0.6078202818692381,
      "step": 54
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 2.1577141284942627,
      "learning_rate": 6.044776119402986e-06,
      "loss": 0.4936,
      "step": 60
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 2.0963618755340576,
      "learning_rate": 5.298507462686567e-06,
      "loss": 0.4327,
      "step": 70
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 1.5172204971313477,
      "learning_rate": 4.5522388059701495e-06,
      "loss": 0.3976,
      "step": 80
    },
    {
      "epoch": 3.0,
      "eval_cer": 0.11282205929472078,
      "eval_loss": 0.366842657327652,
      "eval_runtime": 86.2276,
      "eval_samples_per_second": 14.647,
      "eval_steps_per_second": 0.058,
      "eval_wer": 0.5160538306665253,
      "step": 81
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 1.841143012046814,
      "learning_rate": 3.8059701492537314e-06,
      "loss": 0.3747,
      "step": 90
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 1.7737436294555664,
      "learning_rate": 3.0597014925373137e-06,
      "loss": 0.3485,
      "step": 100
    },
    {
      "epoch": 4.0,
      "eval_cer": 0.10645155210434061,
      "eval_loss": 0.33595842123031616,
      "eval_runtime": 86.4694,
      "eval_samples_per_second": 14.606,
      "eval_steps_per_second": 0.058,
      "eval_wer": 0.488926565645862,
      "step": 108
    },
    {
      "epoch": 4.074074074074074,
      "grad_norm": 1.6087193489074707,
      "learning_rate": 2.3134328358208956e-06,
      "loss": 0.3447,
      "step": 110
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 1.753946304321289,
      "learning_rate": 1.5671641791044779e-06,
      "loss": 0.338,
      "step": 120
    },
    {
      "epoch": 4.814814814814815,
      "grad_norm": 1.5161445140838623,
      "learning_rate": 8.208955223880598e-07,
      "loss": 0.3292,
      "step": 130
    },
    {
      "epoch": 5.0,
      "eval_cer": 0.10385057579584221,
      "eval_loss": 0.32716336846351624,
      "eval_runtime": 85.8417,
      "eval_samples_per_second": 14.713,
      "eval_steps_per_second": 0.058,
      "eval_wer": 0.47917770477906113,
      "step": 135
    },
    {
      "epoch": 5.0,
      "step": 135,
      "total_flos": 3.3623422081150484e+18,
      "train_loss": 0.8413535683243363,
      "train_runtime": 3448.7065,
      "train_samples_per_second": 14.737,
      "train_steps_per_second": 0.039
    }
  ],
  "logging_steps": 10,
  "max_steps": 135,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3623422081150484e+18,
  "train_batch_size": 192,
  "trial_name": null,
  "trial_params": null
}