trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 18.0,
  "eval_steps": 500,
  "global_step": 198,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.91,
      "grad_norm": NaN,
      "learning_rate": 9.792746113989638e-05,
      "loss": 6.5924,
      "step": 10
    },
    {
      "epoch": 1.82,
      "grad_norm": 216.1022186279297,
      "learning_rate": 9.27461139896373e-05,
      "loss": 3.366,
      "step": 20
    },
    {
      "epoch": 2.73,
      "grad_norm": 7.143238544464111,
      "learning_rate": 8.756476683937824e-05,
      "loss": 0.1969,
      "step": 30
    },
    {
      "epoch": 3.64,
      "grad_norm": 3.410977840423584,
      "learning_rate": 8.238341968911918e-05,
      "loss": 0.1357,
      "step": 40
    },
    {
      "epoch": 4.55,
      "grad_norm": 0.2958386540412903,
      "learning_rate": 7.72020725388601e-05,
      "loss": 0.1401,
      "step": 50
    },
    {
      "epoch": 5.45,
      "grad_norm": 0.38453906774520874,
      "learning_rate": 7.202072538860104e-05,
      "loss": 0.135,
      "step": 60
    },
    {
      "epoch": 6.36,
      "grad_norm": 0.4751676917076111,
      "learning_rate": 6.683937823834198e-05,
      "loss": 0.1351,
      "step": 70
    },
    {
      "epoch": 7.27,
      "grad_norm": 0.21170476078987122,
      "learning_rate": 6.16580310880829e-05,
      "loss": 0.1344,
      "step": 80
    },
    {
      "epoch": 8.18,
      "grad_norm": 0.26213210821151733,
      "learning_rate": 5.6476683937823835e-05,
      "loss": 0.1331,
      "step": 90
    },
    {
      "epoch": 9.09,
      "grad_norm": 0.8721823692321777,
      "learning_rate": 5.129533678756477e-05,
      "loss": 0.1341,
      "step": 100
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.4364111125469208,
      "learning_rate": 4.61139896373057e-05,
      "loss": 0.1335,
      "step": 110
    },
    {
      "epoch": 10.91,
      "grad_norm": 0.1868221014738083,
      "learning_rate": 4.093264248704664e-05,
      "loss": 0.1344,
      "step": 120
    },
    {
      "epoch": 11.82,
      "grad_norm": 0.1278260350227356,
      "learning_rate": 3.575129533678757e-05,
      "loss": 0.134,
      "step": 130
    },
    {
      "epoch": 12.73,
      "grad_norm": 0.12410124391317368,
      "learning_rate": 3.05699481865285e-05,
      "loss": 0.133,
      "step": 140
    },
    {
      "epoch": 13.64,
      "grad_norm": 0.14499032497406006,
      "learning_rate": 2.538860103626943e-05,
      "loss": 0.1338,
      "step": 150
    },
    {
      "epoch": 14.55,
      "grad_norm": 0.2002447247505188,
      "learning_rate": 2.0207253886010365e-05,
      "loss": 0.1335,
      "step": 160
    },
    {
      "epoch": 15.45,
      "grad_norm": 0.23757795989513397,
      "learning_rate": 1.5025906735751296e-05,
      "loss": 0.1338,
      "step": 170
    },
    {
      "epoch": 16.36,
      "grad_norm": 0.190875843167305,
      "learning_rate": 9.84455958549223e-06,
      "loss": 0.1339,
      "step": 180
    },
    {
      "epoch": 17.27,
      "grad_norm": 0.06863386929035187,
      "learning_rate": 4.663212435233161e-06,
      "loss": 0.134,
      "step": 190
    },
    {
      "epoch": 18.0,
      "step": 198,
      "total_flos": 802379702310912.0,
      "train_loss": 0.6269946122410321,
      "train_runtime": 5507.7046,
      "train_samples_per_second": 0.575,
      "train_steps_per_second": 0.036
    }
  ],
  "logging_steps": 10,
  "max_steps": 198,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 18,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 802379702310912.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}