trainer_state.json

{
  "best_metric": 0.6498554348945618,
  "best_model_checkpoint": "/home/iais_marenpielka/Bouthaina/res_nw_dj/checkpoint-8109",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 8109,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.3912957906723022,
      "learning_rate": 3.552372190826653e-05,
      "loss": 1.2513,
      "step": 2703
    },
    {
      "epoch": 1.0,
      "eval_bleu": 0.22005527068442493,
      "eval_loss": 0.7111806869506836,
      "eval_rouge1": 0.5171822713118965,
      "eval_rouge2": 0.253317924025756,
      "eval_rougeL": 0.5148202154962768,
      "eval_runtime": 21.8652,
      "eval_samples_per_second": 247.197,
      "eval_steps_per_second": 30.917,
      "step": 2703
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4323362112045288,
      "learning_rate": 1.7761860954133264e-05,
      "loss": 0.6462,
      "step": 5406
    },
    {
      "epoch": 2.0,
      "eval_bleu": 0.24508343939723337,
      "eval_loss": 0.6569304466247559,
      "eval_rouge1": 0.557883823201639,
      "eval_rouge2": 0.2973836473978787,
      "eval_rougeL": 0.5553146565104614,
      "eval_runtime": 150.8243,
      "eval_samples_per_second": 35.836,
      "eval_steps_per_second": 4.482,
      "step": 5406
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2555302381515503,
      "learning_rate": 0.0,
      "loss": 0.5673,
      "step": 8109
    },
    {
      "epoch": 3.0,
      "eval_bleu": 0.2518224574721449,
      "eval_loss": 0.6498554348945618,
      "eval_rouge1": 0.57015304568835,
      "eval_rouge2": 0.3118394078609683,
      "eval_rougeL": 0.5676740384593599,
      "eval_runtime": 172.9357,
      "eval_samples_per_second": 31.254,
      "eval_steps_per_second": 3.909,
      "step": 8109
    },
    {
      "epoch": 3.0,
      "step": 8109,
      "total_flos": 4237242236928000.0,
      "train_loss": 0.8216270929436044,
      "train_runtime": 2338.2192,
      "train_samples_per_second": 27.742,
      "train_steps_per_second": 3.468
    }
  ],
  "logging_steps": 500,
  "max_steps": 8109,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 4237242236928000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}