last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000708842814105972,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.08842814105972e-05,
      "grad_norm": 0.05572463199496269,
      "learning_rate": 2e-05,
      "loss": 10.3888,
      "step": 1
    },
    {
      "epoch": 7.08842814105972e-05,
      "eval_loss": 10.386297225952148,
      "eval_runtime": 23.9211,
      "eval_samples_per_second": 124.158,
      "eval_steps_per_second": 124.158,
      "step": 1
    },
    {
      "epoch": 0.0001417685628211944,
      "grad_norm": 0.07294921576976776,
      "learning_rate": 4e-05,
      "loss": 10.3973,
      "step": 2
    },
    {
      "epoch": 0.0002126528442317916,
      "grad_norm": 0.09582077711820602,
      "learning_rate": 6e-05,
      "loss": 10.3902,
      "step": 3
    },
    {
      "epoch": 0.0002126528442317916,
      "eval_loss": 10.38620662689209,
      "eval_runtime": 25.6376,
      "eval_samples_per_second": 115.845,
      "eval_steps_per_second": 115.845,
      "step": 3
    },
    {
      "epoch": 0.0002835371256423888,
      "grad_norm": 0.07119490206241608,
      "learning_rate": 8e-05,
      "loss": 10.3829,
      "step": 4
    },
    {
      "epoch": 0.000354421407052986,
      "grad_norm": 0.07462739944458008,
      "learning_rate": 0.0001,
      "loss": 10.3837,
      "step": 5
    },
    {
      "epoch": 0.0004253056884635832,
      "grad_norm": 0.09681621193885803,
      "learning_rate": 0.00012,
      "loss": 10.3935,
      "step": 6
    },
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 10.385847091674805,
      "eval_runtime": 25.9218,
      "eval_samples_per_second": 114.575,
      "eval_steps_per_second": 114.575,
      "step": 6
    },
    {
      "epoch": 0.0004961899698741804,
      "grad_norm": 0.07551346719264984,
      "learning_rate": 0.00014,
      "loss": 10.392,
      "step": 7
    },
    {
      "epoch": 0.0005670742512847776,
      "grad_norm": 0.10659193247556686,
      "learning_rate": 0.00016,
      "loss": 10.397,
      "step": 8
    },
    {
      "epoch": 0.0006379585326953748,
      "grad_norm": 0.09229987859725952,
      "learning_rate": 0.00018,
      "loss": 10.3807,
      "step": 9
    },
    {
      "epoch": 0.0006379585326953748,
      "eval_loss": 10.385188102722168,
      "eval_runtime": 27.1695,
      "eval_samples_per_second": 109.314,
      "eval_steps_per_second": 109.314,
      "step": 9
    },
    {
      "epoch": 0.000708842814105972,
      "grad_norm": 0.07869779318571091,
      "learning_rate": 0.0002,
      "loss": 10.382,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 139007262720.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}