{
  "best_metric": 0.41785159707069397,
  "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_gulf/checkpoint-3344",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 7524,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.0378659963607788,
      "learning_rate": 4.896424167694204e-05,
      "loss": 1.8893,
      "step": 836
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.3817836670274851,
      "eval_loss": 0.4814806580543518,
      "eval_rouge1": 0.53445667160678,
      "eval_rouge2": 0.2556577725762693,
      "eval_rougeL": 0.5334625759517182,
      "eval_runtime": 13.5021,
      "eval_samples_per_second": 123.833,
      "eval_steps_per_second": 15.479,
      "step": 836
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.1964277029037476,
      "learning_rate": 4.638717632552405e-05,
      "loss": 0.4211,
      "step": 1672
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.39468460167151326,
      "eval_loss": 0.4300891160964966,
      "eval_rouge1": 0.5886104983083813,
      "eval_rouge2": 0.30839577052783973,
      "eval_rougeL": 0.5877200747673375,
      "eval_runtime": 5.8159,
      "eval_samples_per_second": 287.485,
      "eval_steps_per_second": 35.936,
      "step": 1672
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0570303201675415,
      "learning_rate": 4.3810110974106046e-05,
      "loss": 0.3307,
      "step": 2508
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.40983966101019575,
      "eval_loss": 0.4181276261806488,
      "eval_rouge1": 0.6130185046348249,
      "eval_rouge2": 0.33816617915935476,
      "eval_rougeL": 0.6119109322410228,
      "eval_runtime": 18.13,
      "eval_samples_per_second": 92.223,
      "eval_steps_per_second": 11.528,
      "step": 2508
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0588442087173462,
      "learning_rate": 4.1233045622688044e-05,
      "loss": 0.2641,
      "step": 3344
    },
    {
      "epoch": 4.0,
      "eval_bleu": 0.4093436818765597,
      "eval_loss": 0.41785159707069397,
      "eval_rouge1": 0.6308594985430711,
      "eval_rouge2": 0.35871585587023913,
      "eval_rougeL": 0.6297639876498756,
      "eval_runtime": 5.6414,
      "eval_samples_per_second": 296.382,
      "eval_steps_per_second": 37.048,
      "step": 3344
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.3207675218582153,
      "learning_rate": 3.8655980271270036e-05,
      "loss": 0.2135,
      "step": 4180
    },
    {
      "epoch": 5.0,
      "eval_bleu": 0.41246868412584214,
      "eval_loss": 0.4242132008075714,
      "eval_rouge1": 0.6373073919820111,
      "eval_rouge2": 0.36914621811033116,
      "eval_rougeL": 0.6359208794207342,
      "eval_runtime": 5.3736,
      "eval_samples_per_second": 311.149,
      "eval_steps_per_second": 38.894,
      "step": 4180
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.1845903396606445,
      "learning_rate": 3.6078914919852034e-05,
      "loss": 0.1765,
      "step": 5016
    },
    {
      "epoch": 6.0,
      "eval_bleu": 0.41560183658228855,
      "eval_loss": 0.43002957105636597,
      "eval_rouge1": 0.6465581796614536,
      "eval_rouge2": 0.382979021316462,
      "eval_rougeL": 0.6453232583485639,
      "eval_runtime": 5.4874,
      "eval_samples_per_second": 304.7,
      "eval_steps_per_second": 38.088,
      "step": 5016
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.9745954871177673,
      "learning_rate": 3.350184956843403e-05,
      "loss": 0.1492,
      "step": 5852
    },
    {
      "epoch": 7.0,
      "eval_bleu": 0.41879193694803385,
      "eval_loss": 0.4348294138908386,
      "eval_rouge1": 0.6460454718776507,
      "eval_rouge2": 0.3852436451416871,
      "eval_rougeL": 0.6448992585011752,
      "eval_runtime": 12.7816,
      "eval_samples_per_second": 130.813,
      "eval_steps_per_second": 16.352,
      "step": 5852
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.8118007779121399,
      "learning_rate": 3.092478421701603e-05,
      "loss": 0.1293,
      "step": 6688
    },
    {
      "epoch": 8.0,
      "eval_bleu": 0.4190463110305805,
      "eval_loss": 0.44312888383865356,
      "eval_rouge1": 0.6492735112653347,
      "eval_rouge2": 0.389473573727392,
      "eval_rougeL": 0.6482287927411368,
      "eval_runtime": 5.4157,
      "eval_samples_per_second": 308.729,
      "eval_steps_per_second": 38.591,
      "step": 6688
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.9986652135848999,
      "learning_rate": 2.8347718865598028e-05,
      "loss": 0.1155,
      "step": 7524
    },
    {
      "epoch": 9.0,
      "eval_bleu": 0.4202341801445125,
      "eval_loss": 0.449709415435791,
      "eval_rouge1": 0.6498383797626817,
      "eval_rouge2": 0.39052732019696323,
      "eval_rougeL": 0.6488280555236853,
      "eval_runtime": 5.4735,
      "eval_samples_per_second": 305.473,
      "eval_steps_per_second": 38.184,
      "step": 7524
    },
    {
      "epoch": 9.0,
      "step": 7524,
      "total_flos": 3930158776320000.0,
      "train_loss": 0.40989596332913064,
      "train_runtime": 1923.2663,
      "train_samples_per_second": 69.517,
      "train_steps_per_second": 8.694
    }
  ],
  "logging_steps": 500,
  "max_steps": 16720,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3930158776320000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}