checkpoint-20/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.32,
  "eval_steps": 10,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "eval_logits/chosen": -2.8025150299072266,
      "eval_logits/rejected": -3.1548430919647217,
      "eval_logps/chosen": -285.6490478515625,
      "eval_logps/rejected": -73.34615325927734,
      "eval_loss": 1.696915387583431e-05,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 11.185397148132324,
      "eval_rewards/margins": 12.019237518310547,
      "eval_rewards/rejected": -0.833840548992157,
      "eval_runtime": 68.9632,
      "eval_samples_per_second": 1.45,
      "eval_steps_per_second": 0.363,
      "step": 10
    },
    {
      "epoch": 0.32,
      "eval_logits/chosen": -2.7328505516052246,
      "eval_logits/rejected": -3.097344398498535,
      "eval_logps/chosen": -248.98631286621094,
      "eval_logps/rejected": -93.10418701171875,
      "eval_loss": 1.2917519143229583e-07,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/chosen": 14.851668357849121,
      "eval_rewards/margins": 17.661312103271484,
      "eval_rewards/rejected": -2.8096444606781006,
      "eval_runtime": 68.7434,
      "eval_samples_per_second": 1.455,
      "eval_steps_per_second": 0.364,
      "step": 20
    }
  ],
  "logging_steps": 50,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}