last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001993559270050606,
  "eval_steps": 10,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015335071308081582,
      "eval_loss": 10.366971015930176,
      "eval_runtime": 12.0125,
      "eval_samples_per_second": 228.595,
      "eval_steps_per_second": 114.298,
      "step": 1
    },
    {
      "epoch": 0.0007667535654040791,
      "grad_norm": 0.06585351377725601,
      "learning_rate": 5e-05,
      "loss": 10.3697,
      "step": 5
    },
    {
      "epoch": 0.0015335071308081583,
      "grad_norm": 0.05857785418629646,
      "learning_rate": 0.0001,
      "loss": 10.3674,
      "step": 10
    },
    {
      "epoch": 0.0015335071308081583,
      "eval_loss": 10.366765022277832,
      "eval_runtime": 12.0286,
      "eval_samples_per_second": 228.29,
      "eval_steps_per_second": 114.145,
      "step": 10
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 168101806080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}