last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 2,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1111111111111111,
      "eval_loss": 1.5672025680541992,
      "eval_runtime": 0.357,
      "eval_samples_per_second": 11.204,
      "eval_steps_per_second": 5.602,
      "step": 1
    },
    {
      "epoch": 0.2222222222222222,
      "eval_loss": 1.5623606443405151,
      "eval_runtime": 0.3589,
      "eval_samples_per_second": 11.146,
      "eval_steps_per_second": 5.573,
      "step": 2
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 1.517507791519165,
      "eval_runtime": 0.3654,
      "eval_samples_per_second": 10.946,
      "eval_steps_per_second": 5.473,
      "step": 4
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 4.244422912597656,
      "learning_rate": 5e-05,
      "loss": 1.3554,
      "step": 5
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 1.4443533420562744,
      "eval_runtime": 0.3782,
      "eval_samples_per_second": 10.576,
      "eval_steps_per_second": 5.288,
      "step": 6
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 1.3792885541915894,
      "eval_runtime": 0.3582,
      "eval_samples_per_second": 11.168,
      "eval_steps_per_second": 5.584,
      "step": 8
    }
  ],
  "logging_steps": 5,
  "max_steps": 9,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2409922339799040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}