trainer_state.json

{
  "best_metric": 0.3187411427497864,
  "best_model_checkpoint": "gal_en_mBERT/checkpoint-1250",
  "epoch": 6.0,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8779133954857704,
      "eval_f1": 0.5262912258867455,
      "eval_loss": 0.44472846388816833,
      "eval_precision": 0.5704890387858348,
      "eval_recall": 0.4884493213976321,
      "eval_runtime": 5.3275,
      "eval_samples_per_second": 187.141,
      "eval_steps_per_second": 11.825,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.5654,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.897479146221786,
      "eval_f1": 0.6228456315750205,
      "eval_loss": 0.36001163721084595,
      "eval_precision": 0.6444341516134012,
      "eval_recall": 0.6026566560785446,
      "eval_runtime": 5.2617,
      "eval_samples_per_second": 189.481,
      "eval_steps_per_second": 11.973,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9003312070657508,
      "eval_f1": 0.6522937725312786,
      "eval_loss": 0.3470691740512848,
      "eval_precision": 0.6389696717906107,
      "eval_recall": 0.666185388391568,
      "eval_runtime": 5.3516,
      "eval_samples_per_second": 186.3,
      "eval_steps_per_second": 11.772,
      "step": 750
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.2726,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9087953876349362,
      "eval_f1": 0.6704950207167261,
      "eval_loss": 0.32999733090400696,
      "eval_precision": 0.6751573708095447,
      "eval_recall": 0.6658966214265089,
      "eval_runtime": 5.2725,
      "eval_samples_per_second": 189.094,
      "eval_steps_per_second": 11.949,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.914407507360157,
      "eval_f1": 0.6932259245697546,
      "eval_loss": 0.3187411427497864,
      "eval_precision": 0.7033734581661465,
      "eval_recall": 0.6833670228125902,
      "eval_runtime": 5.3299,
      "eval_samples_per_second": 187.056,
      "eval_steps_per_second": 11.82,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.88e-05,
      "loss": 0.1882,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9141008341511285,
      "eval_f1": 0.7037852425253888,
      "eval_loss": 0.33032578229904175,
      "eval_precision": 0.6925227113906359,
      "eval_recall": 0.7154201559341611,
      "eval_runtime": 5.4015,
      "eval_samples_per_second": 184.577,
      "eval_steps_per_second": 11.663,
      "step": 1500
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 934904811170400.0,
  "trial_name": null,
  "trial_params": null
}