last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.908737301826477,
      "eval_runtime": 11.4205,
      "eval_samples_per_second": 87.562,
      "eval_steps_per_second": 5.516,
      "step": 250
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.628467559814453,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.8909,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.6887657642364502,
      "eval_runtime": 11.4017,
      "eval_samples_per_second": 87.706,
      "eval_steps_per_second": 5.526,
      "step": 500
    }
  ],
  "logging_steps": 500,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1175877900288000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}