last-checkpoint/trainer_state.json

{
  "best_metric": 0.5410714745521545,
  "best_model_checkpoint": "./opt_trained2/checkpoint-129",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 129,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.5563850402832031,
      "eval_runtime": 16.8934,
      "eval_samples_per_second": 17.758,
      "eval_steps_per_second": 4.44,
      "step": 43
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5786572694778442,
      "eval_runtime": 16.9078,
      "eval_samples_per_second": 17.743,
      "eval_steps_per_second": 4.436,
      "step": 86
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.5410714745521545,
      "eval_runtime": 16.9111,
      "eval_samples_per_second": 17.74,
      "eval_steps_per_second": 4.435,
      "step": 129
    }
  ],
  "logging_steps": 500,
  "max_steps": 840,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5904571275820800.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}