{
  "best_metric": 0.7233428496645763,
  "best_model_checkpoint": "outputs/banglabert/checkpoint-1179",
  "epoch": 3.0,
  "global_step": 1179,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 3.3898305084745766e-07,
      "loss": 1.1083,
      "step": 1
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.970782280867107e-05,
      "loss": 0.7903,
      "step": 393
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7364390555201021,
      "eval_f1": 0.6591342767636649,
      "eval_loss": 0.6260421276092529,
      "eval_precision": 0.716418619657342,
      "eval_recall": 0.6696257402218171,
      "eval_runtime": 0.9075,
      "eval_samples_per_second": 1726.789,
      "eval_steps_per_second": 53.997,
      "step": 393
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.4891611687087655e-05,
      "loss": 0.5167,
      "step": 786
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7523931078493937,
      "eval_f1": 0.6965041241727926,
      "eval_loss": 0.6028799414634705,
      "eval_precision": 0.7288354571291619,
      "eval_recall": 0.6975188399488532,
      "eval_runtime": 0.907,
      "eval_samples_per_second": 1727.768,
      "eval_steps_per_second": 54.027,
      "step": 786
    },
    {
      "epoch": 3.0,
      "learning_rate": 7.540056550424129e-08,
      "loss": 0.3229,
      "step": 1179
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7587747287811104,
      "eval_f1": 0.7233428496645763,
      "eval_loss": 0.6502572298049927,
      "eval_precision": 0.7325984484643606,
      "eval_recall": 0.7204468990033644,
      "eval_runtime": 0.9072,
      "eval_samples_per_second": 1727.261,
      "eval_steps_per_second": 54.011,
      "step": 1179
    }
  ],
  "max_steps": 1179,
  "num_train_epochs": 3,
  "total_flos": 1049740313791680.0,
  "trial_name": null,
  "trial_params": null
}