checkpoint-200/trainer_state.json

{
  "best_global_step": 200,
  "best_metric": 64.22461160550755,
  "best_model_checkpoint": "./HAUSA_B/checkpoint-200",
  "epoch": 0.2708192281651997,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027081922816519974,
      "grad_norm": 106.59215545654297,
      "learning_rate": 8.000000000000001e-07,
      "loss": 6.1915,
      "step": 20
    },
    {
      "epoch": 0.05416384563303995,
      "grad_norm": 30.563518524169922,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 4.5886,
      "step": 40
    },
    {
      "epoch": 0.08124576844955991,
      "grad_norm": 16.528457641601562,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 3.0338,
      "step": 60
    },
    {
      "epoch": 0.1083276912660799,
      "grad_norm": 13.852096557617188,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 2.3188,
      "step": 80
    },
    {
      "epoch": 0.13540961408259986,
      "grad_norm": 13.284646987915039,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.9725,
      "step": 100
    },
    {
      "epoch": 0.16249153689911983,
      "grad_norm": 13.212055206298828,
      "learning_rate": 5.8e-06,
      "loss": 1.7839,
      "step": 120
    },
    {
      "epoch": 0.1895734597156398,
      "grad_norm": 12.006990432739258,
      "learning_rate": 6.800000000000001e-06,
      "loss": 1.5991,
      "step": 140
    },
    {
      "epoch": 0.2166553825321598,
      "grad_norm": 12.490514755249023,
      "learning_rate": 7.800000000000002e-06,
      "loss": 1.4411,
      "step": 160
    },
    {
      "epoch": 0.24373730534867977,
      "grad_norm": 11.587646484375,
      "learning_rate": 8.8e-06,
      "loss": 1.3487,
      "step": 180
    },
    {
      "epoch": 0.2708192281651997,
      "grad_norm": 11.574933052062988,
      "learning_rate": 9.800000000000001e-06,
      "loss": 1.2119,
      "step": 200
    },
    {
      "epoch": 0.2708192281651997,
      "eval_loss": 1.1157827377319336,
      "eval_runtime": 1601.2991,
      "eval_samples_per_second": 3.688,
      "eval_steps_per_second": 0.462,
      "eval_wer": 64.22461160550755,
      "step": 200
    }
  ],
  "logging_steps": 20,
  "max_steps": 2214,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.846946562048e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}