checkpoint-20/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3389830508474576,
  "eval_steps": 500,
  "global_step": 20,
  "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": 0.86875,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 171.5,
      "completions/mean_length": 254.9875,
      "completions/mean_terminated_length": 168.87444610595702,
      "completions/min_length": 232.6,
      "completions/min_terminated_length": 155.8,
      "entropy": 0.804140692949295,
      "epoch": 0.1694915254237288,
      "frac_reward_zero_std": 0.0,
      "grad_norm": NaN,
      "kl": 0.8103561986237764,
      "learning_rate": 4.444444444444444e-06,
      "loss": -0.0,
      "num_tokens": 88252.0,
      "reward": -9.967909282445907,
      "reward_std": 12.91413682103157,
      "rewards/reward_func/mean": 0.34375,
      "rewards/reward_func/std": 0.767050838470459,
      "step": 10
    },
    {
      "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": 0.896875,
      "completions/max_length": 256.0,
      "completions/max_terminated_length": 237.7,
      "completions/mean_length": 254.671875,
      "completions/mean_terminated_length": 233.0000015258789,
      "completions/min_length": 222.1,
      "completions/min_terminated_length": 222.1,
      "entropy": 0.8223076105117798,
      "epoch": 0.3389830508474576,
      "frac_reward_zero_std": 0.0,
      "grad_norm": 2024.283447265625,
      "kl": 0.6274451602250337,
      "learning_rate": 1.1111111111111113e-05,
      "loss": -0.0,
      "num_tokens": 176211.0,
      "reward": -7.58766188621521,
      "reward_std": 13.56590785831213,
      "rewards/reward_func/mean": 0.43125,
      "rewards/reward_func/std": 0.6230649650096893,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 177,
  "num_input_tokens_seen": 176211,
  "num_train_epochs": 3,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}