checkpoint-150/trainer_state.json

{
  "best_global_step": 150,
  "best_metric": 19.888904571533203,
  "best_model_checkpoint": "./mbart-large-50-finetuned-question-generation-arab/checkpoint-150",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 37.02599334716797,
      "eval_runtime": 5.1623,
      "eval_samples_per_second": 5.811,
      "eval_steps_per_second": 1.55,
      "step": 15
    },
    {
      "epoch": 2.0,
      "eval_loss": 35.49879455566406,
      "eval_runtime": 5.292,
      "eval_samples_per_second": 5.669,
      "eval_steps_per_second": 1.512,
      "step": 30
    },
    {
      "epoch": 3.0,
      "eval_loss": 34.025047302246094,
      "eval_runtime": 5.4264,
      "eval_samples_per_second": 5.529,
      "eval_steps_per_second": 1.474,
      "step": 45
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 8.457286834716797,
      "learning_rate": 2.608e-05,
      "loss": 34.8404,
      "step": 50
    },
    {
      "epoch": 4.0,
      "eval_loss": 32.63771438598633,
      "eval_runtime": 5.2783,
      "eval_samples_per_second": 5.684,
      "eval_steps_per_second": 1.516,
      "step": 60
    },
    {
      "epoch": 5.0,
      "eval_loss": 31.108373641967773,
      "eval_runtime": 5.1216,
      "eval_samples_per_second": 5.858,
      "eval_steps_per_second": 1.562,
      "step": 75
    },
    {
      "epoch": 6.0,
      "eval_loss": 29.284595489501953,
      "eval_runtime": 5.1789,
      "eval_samples_per_second": 5.793,
      "eval_steps_per_second": 1.545,
      "step": 90
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 10.995285034179688,
      "learning_rate": 2.208e-05,
      "loss": 30.0211,
      "step": 100
    },
    {
      "epoch": 7.0,
      "eval_loss": 27.029993057250977,
      "eval_runtime": 5.2918,
      "eval_samples_per_second": 5.669,
      "eval_steps_per_second": 1.512,
      "step": 105
    },
    {
      "epoch": 8.0,
      "eval_loss": 24.575008392333984,
      "eval_runtime": 5.4135,
      "eval_samples_per_second": 5.542,
      "eval_steps_per_second": 1.478,
      "step": 120
    },
    {
      "epoch": 9.0,
      "eval_loss": 22.200883865356445,
      "eval_runtime": 5.345,
      "eval_samples_per_second": 5.613,
      "eval_steps_per_second": 1.497,
      "step": 135
    },
    {
      "epoch": 10.0,
      "grad_norm": 8.086270332336426,
      "learning_rate": 1.808e-05,
      "loss": 24.3026,
      "step": 150
    },
    {
      "epoch": 10.0,
      "eval_loss": 19.888904571533203,
      "eval_runtime": 5.1154,
      "eval_samples_per_second": 5.865,
      "eval_steps_per_second": 1.564,
      "step": 150
    }
  ],
  "logging_steps": 50,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2783116158566400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}