checkpoint-2455/trainer_state.json

{
  "best_metric": 0.15390127897262573,
  "best_model_checkpoint": "/home/paperspace/microsoft_deberta-v3-base_cpt_64aa255e/checkpoint-2455",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2455,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 9.709048588885654e-07,
      "loss": 0.5526,
      "step": 500
    },
    {
      "epoch": 0.41,
      "learning_rate": 9.418097177771311e-07,
      "loss": 0.2449,
      "step": 1000
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.127145766656967e-07,
      "loss": 0.1637,
      "step": 1500
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.836194355542625e-07,
      "loss": 0.1627,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9574516238542492,
      "eval_f1": 0.9576402605174089,
      "eval_loss": 0.15390127897262573,
      "eval_precision": 0.9583932523988209,
      "eval_recall": 0.9574516238542492,
      "eval_runtime": 11.3772,
      "eval_samples_per_second": 776.73,
      "eval_steps_per_second": 48.606,
      "step": 2455
    }
  ],
  "logging_steps": 500,
  "max_steps": 17185,
  "num_train_epochs": 7,
  "save_steps": 500,
  "total_flos": 953230934474388.0,
  "trial_name": null,
  "trial_params": null
}