last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018635855385762207,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003727171077152441,
      "eval_loss": NaN,
      "eval_runtime": 42.0928,
      "eval_samples_per_second": 26.845,
      "eval_steps_per_second": 13.423,
      "step": 1
    },
    {
      "epoch": 0.003727171077152441,
      "grad_norm": NaN,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.004845322400298174,
      "eval_loss": NaN,
      "eval_runtime": 41.104,
      "eval_samples_per_second": 27.491,
      "eval_steps_per_second": 13.746,
      "step": 13
    },
    {
      "epoch": 0.007454342154304882,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.009690644800596348,
      "eval_loss": NaN,
      "eval_runtime": 41.1615,
      "eval_samples_per_second": 27.453,
      "eval_steps_per_second": 13.726,
      "step": 26
    },
    {
      "epoch": 0.011181513231457324,
      "grad_norm": NaN,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.2226,
      "step": 30
    },
    {
      "epoch": 0.014535967200894522,
      "eval_loss": NaN,
      "eval_runtime": 41.1646,
      "eval_samples_per_second": 27.451,
      "eval_steps_per_second": 13.725,
      "step": 39
    },
    {
      "epoch": 0.014908684308609765,
      "grad_norm": NaN,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.8835,
      "step": 40
    },
    {
      "epoch": 0.018635855385762207,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0647468949635072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}