checkpoint-630/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 30.0,
  "eval_steps": 500,
  "global_step": 630,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_runtime": 11.809,
      "eval_samples_per_second": 3.811,
      "eval_steps_per_second": 0.423,
      "step": 21
    },
    {
      "epoch": 2.0,
      "eval_runtime": 6.8145,
      "eval_samples_per_second": 6.604,
      "eval_steps_per_second": 0.734,
      "step": 42
    },
    {
      "epoch": 3.0,
      "eval_runtime": 6.0474,
      "eval_samples_per_second": 7.441,
      "eval_steps_per_second": 0.827,
      "step": 63
    },
    {
      "epoch": 4.0,
      "eval_runtime": 6.3718,
      "eval_samples_per_second": 7.062,
      "eval_steps_per_second": 0.785,
      "step": 84
    },
    {
      "epoch": 5.0,
      "eval_runtime": 6.5487,
      "eval_samples_per_second": 6.872,
      "eval_steps_per_second": 0.764,
      "step": 105
    },
    {
      "epoch": 6.0,
      "eval_runtime": 6.0733,
      "eval_samples_per_second": 7.409,
      "eval_steps_per_second": 0.823,
      "step": 126
    },
    {
      "epoch": 7.0,
      "eval_runtime": 6.0993,
      "eval_samples_per_second": 7.378,
      "eval_steps_per_second": 0.82,
      "step": 147
    },
    {
      "epoch": 8.0,
      "eval_runtime": 6.6473,
      "eval_samples_per_second": 6.77,
      "eval_steps_per_second": 0.752,
      "step": 168
    },
    {
      "epoch": 9.0,
      "eval_runtime": 6.3262,
      "eval_samples_per_second": 7.113,
      "eval_steps_per_second": 0.79,
      "step": 189
    },
    {
      "epoch": 10.0,
      "eval_runtime": 6.0277,
      "eval_samples_per_second": 7.465,
      "eval_steps_per_second": 0.829,
      "step": 210
    },
    {
      "epoch": 11.0,
      "eval_runtime": 6.6821,
      "eval_samples_per_second": 6.734,
      "eval_steps_per_second": 0.748,
      "step": 231
    },
    {
      "epoch": 12.0,
      "eval_runtime": 6.5331,
      "eval_samples_per_second": 6.888,
      "eval_steps_per_second": 0.765,
      "step": 252
    },
    {
      "epoch": 13.0,
      "eval_runtime": 6.0417,
      "eval_samples_per_second": 7.448,
      "eval_steps_per_second": 0.828,
      "step": 273
    },
    {
      "epoch": 14.0,
      "eval_runtime": 6.0373,
      "eval_samples_per_second": 7.454,
      "eval_steps_per_second": 0.828,
      "step": 294
    },
    {
      "epoch": 15.0,
      "eval_runtime": 6.6679,
      "eval_samples_per_second": 6.749,
      "eval_steps_per_second": 0.75,
      "step": 315
    },
    {
      "epoch": 16.0,
      "eval_runtime": 6.4137,
      "eval_samples_per_second": 7.016,
      "eval_steps_per_second": 0.78,
      "step": 336
    },
    {
      "epoch": 17.0,
      "eval_runtime": 6.106,
      "eval_samples_per_second": 7.37,
      "eval_steps_per_second": 0.819,
      "step": 357
    },
    {
      "epoch": 18.0,
      "eval_runtime": 6.6353,
      "eval_samples_per_second": 6.782,
      "eval_steps_per_second": 0.754,
      "step": 378
    },
    {
      "epoch": 19.0,
      "eval_runtime": 6.5796,
      "eval_samples_per_second": 6.839,
      "eval_steps_per_second": 0.76,
      "step": 399
    },
    {
      "epoch": 20.0,
      "eval_runtime": 6.0621,
      "eval_samples_per_second": 7.423,
      "eval_steps_per_second": 0.825,
      "step": 420
    },
    {
      "epoch": 21.0,
      "eval_runtime": 6.0837,
      "eval_samples_per_second": 7.397,
      "eval_steps_per_second": 0.822,
      "step": 441
    },
    {
      "epoch": 22.0,
      "eval_runtime": 6.7734,
      "eval_samples_per_second": 6.644,
      "eval_steps_per_second": 0.738,
      "step": 462
    },
    {
      "epoch": 23.0,
      "eval_runtime": 6.3665,
      "eval_samples_per_second": 7.068,
      "eval_steps_per_second": 0.785,
      "step": 483
    },
    {
      "epoch": 23.80952380952381,
      "grad_norm": 0.07010962069034576,
      "learning_rate": 6.878306878306877e-05,
      "loss": 9.2521,
      "step": 500
    },
    {
      "epoch": 24.0,
      "eval_runtime": 6.0991,
      "eval_samples_per_second": 7.378,
      "eval_steps_per_second": 0.82,
      "step": 504
    },
    {
      "epoch": 25.0,
      "eval_runtime": 6.7598,
      "eval_samples_per_second": 6.657,
      "eval_steps_per_second": 0.74,
      "step": 525
    },
    {
      "epoch": 26.0,
      "eval_runtime": 6.5824,
      "eval_samples_per_second": 6.836,
      "eval_steps_per_second": 0.76,
      "step": 546
    },
    {
      "epoch": 27.0,
      "eval_runtime": 6.1001,
      "eval_samples_per_second": 7.377,
      "eval_steps_per_second": 0.82,
      "step": 567
    },
    {
      "epoch": 28.0,
      "eval_runtime": 6.4201,
      "eval_samples_per_second": 7.009,
      "eval_steps_per_second": 0.779,
      "step": 588
    },
    {
      "epoch": 29.0,
      "eval_runtime": 6.5591,
      "eval_samples_per_second": 6.861,
      "eval_steps_per_second": 0.762,
      "step": 609
    },
    {
      "epoch": 30.0,
      "eval_runtime": 6.0655,
      "eval_samples_per_second": 7.419,
      "eval_steps_per_second": 0.824,
      "step": 630
    }
  ],
  "logging_steps": 500,
  "max_steps": 630,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "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": 2949254422732800.0,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}