{
  "best_global_step": 210,
  "best_metric": 0.896,
  "best_model_checkpoint": "C:\\Users\\azizmohamed.miladi_a\\Desktop\\GuichetOI_ML\\models\\classifier\\checkpoint-210",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2898550724637681,
      "grad_norm": 9.624526977539062,
      "learning_rate": 3.91304347826087e-06,
      "loss": 3.6916267395019533,
      "step": 10
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 14.441962242126465,
      "learning_rate": 8.260869565217392e-06,
      "loss": 3.6258655548095704,
      "step": 20
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 8.163778305053711,
      "learning_rate": 1.2608695652173915e-05,
      "loss": 3.4986854553222657,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6,
      "eval_loss": 1.6575028896331787,
      "eval_runtime": 148.9919,
      "eval_samples_per_second": 0.839,
      "eval_steps_per_second": 0.107,
      "step": 35
    },
    {
      "epoch": 1.144927536231884,
      "grad_norm": 31.98755645751953,
      "learning_rate": 1.6956521739130437e-05,
      "loss": 3.070163917541504,
      "step": 40
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 28.577415466308594,
      "learning_rate": 1.999519459156716e-05,
      "loss": 2.9280990600585937,
      "step": 50
    },
    {
      "epoch": 1.7246376811594204,
      "grad_norm": 21.18294334411621,
      "learning_rate": 1.9909893526171745e-05,
      "loss": 2.360361099243164,
      "step": 60
    },
    {
      "epoch": 2.0,
      "grad_norm": 14.277557373046875,
      "learning_rate": 1.9718853502700783e-05,
      "loss": 2.2741134643554686,
      "step": 70
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.776,
      "eval_loss": 0.9326786398887634,
      "eval_runtime": 146.9167,
      "eval_samples_per_second": 0.851,
      "eval_steps_per_second": 0.109,
      "step": 70
    },
    {
      "epoch": 2.289855072463768,
      "grad_norm": 14.20412826538086,
      "learning_rate": 1.942411292580304e-05,
      "loss": 1.7156837463378907,
      "step": 80
    },
    {
      "epoch": 2.579710144927536,
      "grad_norm": 16.971263885498047,
      "learning_rate": 1.902881668915688e-05,
      "loss": 1.8933340072631837,
      "step": 90
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 27.035112380981445,
      "learning_rate": 1.853718261932964e-05,
      "loss": 1.401157760620117,
      "step": 100
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.856,
      "eval_loss": 0.6431578993797302,
      "eval_runtime": 147.2608,
      "eval_samples_per_second": 0.849,
      "eval_steps_per_second": 0.109,
      "step": 105
    },
    {
      "epoch": 3.1449275362318843,
      "grad_norm": 19.40919303894043,
      "learning_rate": 1.7954456471400393e-05,
      "loss": 1.2568418502807617,
      "step": 110
    },
    {
      "epoch": 3.4347826086956523,
      "grad_norm": 33.98841094970703,
      "learning_rate": 1.7286855956544616e-05,
      "loss": 1.4773143768310546,
      "step": 120
    },
    {
      "epoch": 3.7246376811594204,
      "grad_norm": 42.596099853515625,
      "learning_rate": 1.6541504398808633e-05,
      "loss": 1.325703239440918,
      "step": 130
    },
    {
      "epoch": 4.0,
      "grad_norm": 9.05463981628418,
      "learning_rate": 1.5726354728958736e-05,
      "loss": 0.936131477355957,
      "step": 140
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.848,
      "eval_loss": 0.5704618096351624,
      "eval_runtime": 146.5658,
      "eval_samples_per_second": 0.853,
      "eval_steps_per_second": 0.109,
      "step": 140
    },
    {
      "epoch": 4.2898550724637685,
      "grad_norm": 22.953588485717773,
      "learning_rate": 1.4850104626393598e-05,
      "loss": 0.8413548469543457,
      "step": 150
    },
    {
      "epoch": 4.579710144927536,
      "grad_norm": 11.811186790466309,
      "learning_rate": 1.392210371455913e-05,
      "loss": 0.8283905982971191,
      "step": 160
    },
    {
      "epoch": 4.869565217391305,
      "grad_norm": 10.801919937133789,
      "learning_rate": 1.2952253800094467e-05,
      "loss": 1.2056690216064454,
      "step": 170
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.872,
      "eval_loss": 0.4952421486377716,
      "eval_runtime": 143.0417,
      "eval_samples_per_second": 0.874,
      "eval_steps_per_second": 0.112,
      "step": 175
    },
    {
      "epoch": 5.144927536231884,
      "grad_norm": 7.648271560668945,
      "learning_rate": 1.1950903220161286e-05,
      "loss": 0.8253307342529297,
      "step": 180
    },
    {
      "epoch": 5.434782608695652,
      "grad_norm": 31.05258560180664,
      "learning_rate": 1.0928736425274702e-05,
      "loss": 0.6119639873504639,
      "step": 190
    },
    {
      "epoch": 5.72463768115942,
      "grad_norm": 18.84103775024414,
      "learning_rate": 9.89665997579133e-06,
      "loss": 0.8575582504272461,
      "step": 200
    },
    {
      "epoch": 6.0,
      "grad_norm": 11.322463989257812,
      "learning_rate": 8.865686168476458e-06,
      "loss": 0.74702467918396,
      "step": 210
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.896,
      "eval_loss": 0.44246727228164673,
      "eval_runtime": 147.6208,
      "eval_samples_per_second": 0.847,
      "eval_steps_per_second": 0.108,
      "step": 210
    }
  ],
  "logging_steps": 10,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 879062029664256.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}