trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_logits/chosen": -108.79365539550781,
      "eval_logits/rejected": -151.2770233154297,
      "eval_logps/chosen": -267.2356872558594,
      "eval_logps/rejected": -185.09524536132812,
      "eval_loss": 0.6931471824645996,
      "eval_rewards/accuracies": 0.0,
      "eval_rewards/chosen": 0.0,
      "eval_rewards/margins": 0.0,
      "eval_rewards/rejected": 0.0,
      "eval_runtime": 0.5516,
      "eval_samples_per_second": 9.064,
      "eval_steps_per_second": 1.813,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_logits/chosen": -108.78112030029297,
      "eval_logits/rejected": -151.3362274169922,
      "eval_logps/chosen": -268.0252380371094,
      "eval_logps/rejected": -187.6125946044922,
      "eval_loss": 0.6203721761703491,
      "eval_rewards/accuracies": 0.6000000238418579,
      "eval_rewards/chosen": -0.07895644754171371,
      "eval_rewards/margins": 0.1727786362171173,
      "eval_rewards/rejected": -0.2517350912094116,
      "eval_runtime": 0.5661,
      "eval_samples_per_second": 8.832,
      "eval_steps_per_second": 1.766,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_logits/chosen": -108.68714904785156,
      "eval_logits/rejected": -151.747314453125,
      "eval_logps/chosen": -266.5977783203125,
      "eval_logps/rejected": -185.63877868652344,
      "eval_loss": 0.6367835402488708,
      "eval_rewards/accuracies": 0.800000011920929,
      "eval_rewards/chosen": 0.06378966569900513,
      "eval_rewards/margins": 0.11814422905445099,
      "eval_rewards/rejected": -0.05435454845428467,
      "eval_runtime": 0.5628,
      "eval_samples_per_second": 8.884,
      "eval_steps_per_second": 1.777,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_logits/chosen": -109.2767333984375,
      "eval_logits/rejected": -152.4813232421875,
      "eval_logps/chosen": -267.413818359375,
      "eval_logps/rejected": -187.46786499023438,
      "eval_loss": 0.5958372950553894,
      "eval_rewards/accuracies": 0.800000011920929,
      "eval_rewards/chosen": -0.017816483974456787,
      "eval_rewards/margins": 0.21944628655910492,
      "eval_rewards/rejected": -0.23726272583007812,
      "eval_runtime": 0.5642,
      "eval_samples_per_second": 8.862,
      "eval_steps_per_second": 1.772,
      "step": 4
    }
  ],
  "logging_steps": 10,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}