last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014062843331136014,
  "eval_steps": 2,
  "global_step": 2,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007031421665568007,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0007031421665568007,
      "eval_loss": NaN,
      "eval_runtime": 93.4734,
      "eval_samples_per_second": 25.633,
      "eval_steps_per_second": 12.816,
      "step": 1
    },
    {
      "epoch": 0.0014062843331136014,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0014062843331136014,
      "eval_loss": NaN,
      "eval_runtime": 53.4608,
      "eval_samples_per_second": 44.818,
      "eval_steps_per_second": 22.409,
      "step": 2
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 259438606811136.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}