last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015432098765432098,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017146776406035664,
      "grad_norm": 59.66114044189453,
      "learning_rate": 2e-05,
      "loss": 16.22,
      "step": 1
    },
    {
      "epoch": 0.0003429355281207133,
      "grad_norm": 46.88684844970703,
      "learning_rate": 4e-05,
      "loss": 17.9129,
      "step": 2
    },
    {
      "epoch": 0.00051440329218107,
      "grad_norm": 50.64372634887695,
      "learning_rate": 6e-05,
      "loss": 15.5299,
      "step": 3
    },
    {
      "epoch": 0.00051440329218107,
      "eval_loss": 4.17085075378418,
      "eval_runtime": 55.0584,
      "eval_samples_per_second": 44.607,
      "eval_steps_per_second": 22.304,
      "step": 3
    },
    {
      "epoch": 0.0006858710562414266,
      "grad_norm": 73.80441284179688,
      "learning_rate": 8e-05,
      "loss": 17.9721,
      "step": 4
    },
    {
      "epoch": 0.0008573388203017832,
      "grad_norm": 51.07341766357422,
      "learning_rate": 0.0001,
      "loss": 15.2132,
      "step": 5
    },
    {
      "epoch": 0.00102880658436214,
      "grad_norm": 73.77809143066406,
      "learning_rate": 0.00012,
      "loss": 18.699,
      "step": 6
    },
    {
      "epoch": 0.00102880658436214,
      "eval_loss": 4.13886833190918,
      "eval_runtime": 53.0262,
      "eval_samples_per_second": 46.317,
      "eval_steps_per_second": 23.158,
      "step": 6
    },
    {
      "epoch": 0.0012002743484224967,
      "grad_norm": 53.89808654785156,
      "learning_rate": 0.00014,
      "loss": 17.6091,
      "step": 7
    },
    {
      "epoch": 0.0013717421124828531,
      "grad_norm": 49.97898864746094,
      "learning_rate": 0.00016,
      "loss": 18.8421,
      "step": 8
    },
    {
      "epoch": 0.0015432098765432098,
      "grad_norm": 60.67934036254883,
      "learning_rate": 0.00018,
      "loss": 17.5318,
      "step": 9
    },
    {
      "epoch": 0.0015432098765432098,
      "eval_loss": 4.035857677459717,
      "eval_runtime": 53.3948,
      "eval_samples_per_second": 45.997,
      "eval_steps_per_second": 22.999,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 78955709202432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}