trainer_state.json

{
  "best_metric": 0.24358895421028137,
  "best_model_checkpoint": "spa_enpt_XLM-R/checkpoint-4480",
  "epoch": 6.0,
  "global_step": 5376,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.56,
      "learning_rate": 1.988839285714286e-05,
      "loss": 1.0911,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8993505848708121,
      "eval_f1": 0.7075863466018435,
      "eval_loss": 0.3950195908546448,
      "eval_precision": 0.7227394992758122,
      "eval_recall": 0.6930555555555555,
      "eval_runtime": 5.3418,
      "eval_samples_per_second": 309.633,
      "eval_steps_per_second": 19.469,
      "step": 896
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.9776785714285716e-05,
      "loss": 0.4741,
      "step": 1000
    },
    {
      "epoch": 1.67,
      "learning_rate": 1.9665178571428575e-05,
      "loss": 0.3541,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9222886421861657,
      "eval_f1": 0.7796375160938893,
      "eval_loss": 0.2917722463607788,
      "eval_precision": 0.7783270713861974,
      "eval_recall": 0.780952380952381,
      "eval_runtime": 5.3059,
      "eval_samples_per_second": 311.729,
      "eval_steps_per_second": 19.601,
      "step": 1792
    },
    {
      "epoch": 2.23,
      "learning_rate": 1.955357142857143e-05,
      "loss": 0.3006,
      "step": 2000
    },
    {
      "epoch": 2.79,
      "learning_rate": 1.944196428571429e-05,
      "loss": 0.2596,
      "step": 2500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9271145711278375,
      "eval_f1": 0.7927471370277741,
      "eval_loss": 0.26859569549560547,
      "eval_precision": 0.7889048991354467,
      "eval_recall": 0.7966269841269841,
      "eval_runtime": 5.3629,
      "eval_samples_per_second": 308.413,
      "eval_steps_per_second": 19.392,
      "step": 2688
    },
    {
      "epoch": 3.35,
      "learning_rate": 1.9330357142857144e-05,
      "loss": 0.2241,
      "step": 3000
    },
    {
      "epoch": 3.91,
      "learning_rate": 1.9218750000000003e-05,
      "loss": 0.1999,
      "step": 3500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9218318670188469,
      "eval_f1": 0.7742510228322556,
      "eval_loss": 0.28371667861938477,
      "eval_precision": 0.7725177771925205,
      "eval_recall": 0.7759920634920635,
      "eval_runtime": 5.3287,
      "eval_samples_per_second": 310.397,
      "eval_steps_per_second": 19.517,
      "step": 3584
    },
    {
      "epoch": 4.46,
      "learning_rate": 1.910714285714286e-05,
      "loss": 0.1816,
      "step": 4000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9376005401862848,
      "eval_f1": 0.8258814976372229,
      "eval_loss": 0.24358895421028137,
      "eval_precision": 0.825308764282412,
      "eval_recall": 0.8264550264550264,
      "eval_runtime": 5.3581,
      "eval_samples_per_second": 308.694,
      "eval_steps_per_second": 19.41,
      "step": 4480
    },
    {
      "epoch": 5.02,
      "learning_rate": 1.8995535714285717e-05,
      "loss": 0.1685,
      "step": 4500
    },
    {
      "epoch": 5.58,
      "learning_rate": 1.8883928571428573e-05,
      "loss": 0.141,
      "step": 5000
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9380175957738367,
      "eval_f1": 0.8282768389498304,
      "eval_loss": 0.24781708419322968,
      "eval_precision": 0.8250968038327755,
      "eval_recall": 0.8314814814814815,
      "eval_runtime": 5.3393,
      "eval_samples_per_second": 309.778,
      "eval_steps_per_second": 19.478,
      "step": 5376
    }
  ],
  "max_steps": 89600,
  "num_train_epochs": 100,
  "total_flos": 4159153391462784.0,
  "trial_name": null,
  "trial_params": null
}