trainer_state.json

{
  "best_metric": 0.31592875719070435,
  "best_model_checkpoint": "gal_enpt_XLM-R/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": 0.8747239941118744,
      "eval_f1": 0.5165929203539823,
      "eval_loss": 0.46114709973335266,
      "eval_precision": 0.5705061082024433,
      "eval_recall": 0.47198960438925786,
      "eval_runtime": 5.1534,
      "eval_samples_per_second": 193.466,
      "eval_steps_per_second": 12.225,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.6032,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9003618743866536,
      "eval_f1": 0.6379219210148759,
      "eval_loss": 0.35644981265068054,
      "eval_precision": 0.6686718378977363,
      "eval_recall": 0.6098758302050246,
      "eval_runtime": 5.0374,
      "eval_samples_per_second": 197.92,
      "eval_steps_per_second": 12.507,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8970191364082434,
      "eval_f1": 0.6530527481655822,
      "eval_loss": 0.3476572632789612,
      "eval_precision": 0.6272606382978724,
      "eval_recall": 0.6810568870921166,
      "eval_runtime": 5.0473,
      "eval_samples_per_second": 197.53,
      "eval_steps_per_second": 12.482,
      "step": 750
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.295,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9082127085377821,
      "eval_f1": 0.6739380022962113,
      "eval_loss": 0.3241439461708069,
      "eval_precision": 0.6699001426533524,
      "eval_recall": 0.678024833958995,
      "eval_runtime": 5.0718,
      "eval_samples_per_second": 196.577,
      "eval_steps_per_second": 12.422,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9141928361138371,
      "eval_f1": 0.6944585663446875,
      "eval_loss": 0.31592875719070435,
      "eval_precision": 0.6986701739003361,
      "eval_recall": 0.690297429974011,
      "eval_runtime": 5.2185,
      "eval_samples_per_second": 191.053,
      "eval_steps_per_second": 12.073,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.88e-05,
      "loss": 0.2208,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9090100588812562,
      "eval_f1": 0.6787516883486174,
      "eval_loss": 0.3298513889312744,
      "eval_precision": 0.6685338187928862,
      "eval_recall": 0.6892867455963038,
      "eval_runtime": 5.1124,
      "eval_samples_per_second": 195.015,
      "eval_steps_per_second": 12.323,
      "step": 1500
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 925793237842200.0,
  "trial_name": null,
  "trial_params": null
}