trainer_state.json

{
  "best_metric": 0.2969047427177429,
  "best_model_checkpoint": "gal_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": 0.8587769872423945,
      "eval_f1": 0.43071868583162215,
      "eval_loss": 0.5011889338493347,
      "eval_precision": 0.49952371880358165,
      "eval_recall": 0.3785734911926076,
      "eval_runtime": 5.1414,
      "eval_samples_per_second": 193.916,
      "eval_steps_per_second": 12.253,
      "step": 250
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.6549,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.896896467124632,
      "eval_f1": 0.6211732770321218,
      "eval_loss": 0.37466686964035034,
      "eval_precision": 0.650094696969697,
      "eval_recall": 0.5947155645394167,
      "eval_runtime": 5.2223,
      "eval_samples_per_second": 190.913,
      "eval_steps_per_second": 12.064,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8944430814524044,
      "eval_f1": 0.6271806415306697,
      "eval_loss": 0.3451153635978699,
      "eval_precision": 0.6115226337448559,
      "eval_recall": 0.6436615651169506,
      "eval_runtime": 5.2634,
      "eval_samples_per_second": 189.421,
      "eval_steps_per_second": 11.969,
      "step": 750
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.3055,
      "step": 1000
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8942590775269872,
      "eval_f1": 0.6139852188743605,
      "eval_loss": 0.35699811577796936,
      "eval_precision": 0.6045340050377834,
      "eval_recall": 0.623736644527866,
      "eval_runtime": 5.1743,
      "eval_samples_per_second": 192.683,
      "eval_steps_per_second": 12.176,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9164622178606477,
      "eval_f1": 0.7048362611147256,
      "eval_loss": 0.2969047427177429,
      "eval_precision": 0.7058057043578978,
      "eval_recall": 0.7038694773317933,
      "eval_runtime": 5.1399,
      "eval_samples_per_second": 193.971,
      "eval_steps_per_second": 12.257,
      "step": 1250
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.88e-05,
      "loss": 0.228,
      "step": 1500
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9075993621197253,
      "eval_f1": 0.6804787569118779,
      "eval_loss": 0.33213135600090027,
      "eval_precision": 0.6603722320336911,
      "eval_recall": 0.7018481085763789,
      "eval_runtime": 5.1274,
      "eval_samples_per_second": 194.445,
      "eval_steps_per_second": 12.287,
      "step": 1500
    }
  ],
  "max_steps": 25000,
  "num_train_epochs": 100,
  "total_flos": 925793237842200.0,
  "trial_name": null,
  "trial_params": null
}