trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5625,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.0016677959356456995,
      "learning_rate": 1.8222222222222224e-05,
      "loss": 0.0148,
      "step": 500
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.0013756826519966125,
      "learning_rate": 1.6444444444444444e-05,
      "loss": 0.0025,
      "step": 1000
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.0004886463284492493,
      "learning_rate": 1.4666666666666666e-05,
      "loss": 0.0025,
      "step": 1500
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.0004053245938848704,
      "learning_rate": 1.288888888888889e-05,
      "loss": 0.0018,
      "step": 2000
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.0003290953754913062,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 0.0006,
      "step": 2500
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.0006466731429100037,
      "learning_rate": 9.333333333333334e-06,
      "loss": 0.0012,
      "step": 3000
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.001320909010246396,
      "learning_rate": 7.555555555555556e-06,
      "loss": 0.002,
      "step": 3500
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.0003657432389445603,
      "learning_rate": 5.777777777777778e-06,
      "loss": 0.0014,
      "step": 4000
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.0008547449251636863,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0007,
      "step": 4500
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.033058132976293564,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.0016,
      "step": 5000
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.0003009486827068031,
      "learning_rate": 4.444444444444445e-07,
      "loss": 0.0004,
      "step": 5500
    },
    {
      "epoch": 1.0,
      "step": 5625,
      "total_flos": 4.717499098595328e+16,
      "train_loss": 0.0025973160221344897,
      "train_runtime": 10136.1887,
      "train_samples_per_second": 17.758,
      "train_steps_per_second": 0.555
    }
  ],
  "logging_steps": 500,
  "max_steps": 5625,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.717499098595328e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}