trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9230769230769231,
  "eval_steps": 500,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": -5.921875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1020.0,
      "completions/mean_length": 674.978515625,
      "completions/mean_terminated_length": 620.6162719726562,
      "completions/min_length": 44.0,
      "completions/min_terminated_length": 44.0,
      "epoch": 0.3076923076923077,
      "frac_reward_zero_std": 0.28125,
      "grad_norm": 0.24190807765558528,
      "kl": 0.00023603439331054688,
      "learning_rate": 0.0,
      "loss": 0.0155,
      "num_tokens": 417029.0,
      "reward": 0.06982421875,
      "reward_std": 0.17549802362918854,
      "rewards/accuracy_reward/mean": 0.05078125,
      "rewards/accuracy_reward/std": 0.21976542472839355,
      "rewards/format_reward/mean": 0.001953125,
      "rewards/format_reward/std": 0.04419417306780815,
      "rewards/tag_count_reward/mean": 0.01708984375,
      "rewards/tag_count_reward/std": 0.10527165234088898,
      "step": 1
    },
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": -6.3671875,
      "completions/max_length": 1024.0,
      "completions/max_terminated_length": 1023.0,
      "completions/mean_length": 652.9970703125,
      "completions/mean_terminated_length": 621.1537475585938,
      "completions/min_length": 82.5,
      "completions/min_terminated_length": 82.5,
      "epoch": 0.9230769230769231,
      "frac_reward_zero_std": 0.171875,
      "kl": 0.006235480308532715,
      "num_tokens": 1242274.0,
      "reward": 0.33154296875,
      "reward_std": 0.2335953712463379,
      "rewards/accuracy_reward/mean": 0.0263671875,
      "rewards/accuracy_reward/std": 0.1589299514889717,
      "rewards/format_reward/mean": 0.009765625,
      "rewards/format_reward/std": 0.09631745889782906,
      "rewards/tag_count_reward/mean": 0.29541015625,
      "rewards/tag_count_reward/std": 0.2025153785943985,
      "step": 3,
      "total_flos": 0.0,
      "train_loss": 0.011118112752834955,
      "train_runtime": 226.5086,
      "train_samples_per_second": 0.441,
      "train_steps_per_second": 0.018
    }
  ],
  "logging_steps": 10,
  "max_steps": 4,
  "num_input_tokens_seen": 1242274,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}