checkpoint-250/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05555555555555555,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "completion_length": 309.04,
      "epoch": 0.011111111111111112,
      "grad_norm": NaN,
      "kl": 222.66988746643065,
      "learning_rate": 5.444444444444444e-07,
      "loss": 8.9068,
      "reward": -18.06266725540161,
      "reward_std": 6.391496688127518,
      "rewards/check_first_pass": -9.93666666984558,
      "rewards/check_solution": -7.600000243186951,
      "rewards/check_solution_words": -6.068000079095364,
      "rewards/check_word_guesses": 5.54200014591217,
      "step": 50
    },
    {
      "completion_length": 368.64,
      "epoch": 0.022222222222222223,
      "grad_norm": NaN,
      "kl": 557.3866543316841,
      "learning_rate": 1.1e-06,
      "loss": 22.2955,
      "reward": -17.431167125701904,
      "reward_std": 5.4497878611087796,
      "rewards/check_first_pass": -9.859833374023438,
      "rewards/check_solution": -7.2583335638046265,
      "rewards/check_solution_words": -5.878333521187305,
      "rewards/check_word_guesses": 5.565333509445191,
      "step": 100
    },
    {
      "completion_length": 346.92,
      "epoch": 0.03333333333333333,
      "grad_norm": NaN,
      "kl": 4737.8455329227445,
      "learning_rate": 1.6555555555555559e-06,
      "loss": 189.5138,
      "reward": -18.070500688552855,
      "reward_std": 7.8515861177444455,
      "rewards/check_first_pass": -9.786166725158692,
      "rewards/check_solution": -7.325000324249268,
      "rewards/check_solution_words": -7.050333592891693,
      "rewards/check_word_guesses": 6.091000156402588,
      "step": 150
    },
    {
      "completion_length": 322.2,
      "epoch": 0.044444444444444446,
      "grad_norm": NaN,
      "kl": 32057.38775477886,
      "learning_rate": 2.2111111111111113e-06,
      "loss": 1282.2956,
      "reward": -15.816333751678467,
      "reward_std": 6.191992573738098,
      "rewards/check_first_pass": -9.895000038146973,
      "rewards/check_solution": -7.100000200271606,
      "rewards/check_solution_words": -4.8800000631809235,
      "rewards/check_word_guesses": 6.058666839599609,
      "step": 200
    },
    {
      "completion_length": 349.9,
      "epoch": 0.05555555555555555,
      "grad_norm": NaN,
      "kl": 5074.338300862312,
      "learning_rate": 2.766666666666667e-06,
      "loss": 202.9736,
      "reward": -17.724167308807374,
      "reward_std": 6.207637655735016,
      "rewards/check_first_pass": -9.912833366394043,
      "rewards/check_solution": -7.358333556652069,
      "rewards/check_solution_words": -6.180666843354702,
      "rewards/check_word_guesses": 5.727666816711426,
      "step": 250
    }
  ],
  "logging_steps": 50,
  "max_steps": 4500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 12,
  "trial_name": null,
  "trial_params": null
}