trainer_state.json

{
  "best_metric": 0.8093220591545105,
  "best_model_checkpoint": "OUTPUT/bert-base-multilingual-cased/FalseTrue-0/2/checkpoint-140",
  "epoch": 5.0,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7076271176338196,
      "eval_loss": 0.5130524635314941,
      "eval_runtime": 3.5832,
      "eval_samples_per_second": 65.863,
      "step": 28
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7669491767883301,
      "eval_loss": 0.6092923283576965,
      "eval_runtime": 3.5959,
      "eval_samples_per_second": 65.631,
      "step": 56
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7966101765632629,
      "eval_loss": 0.6468168497085571,
      "eval_runtime": 3.6394,
      "eval_samples_per_second": 64.846,
      "step": 84
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7754237055778503,
      "eval_loss": 0.8418569564819336,
      "eval_runtime": 3.5908,
      "eval_samples_per_second": 65.724,
      "step": 112
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8093220591545105,
      "eval_loss": 0.8701808452606201,
      "eval_runtime": 3.5987,
      "eval_samples_per_second": 65.579,
      "step": 140
    }
  ],
  "max_steps": 252,
  "num_train_epochs": 9,
  "total_flos": 119245359969792.0,
  "trial_name": null,
  "trial_params": null
}