checkpoint-50/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04440497335701599,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008880994671403197,
      "grad_norm": 0.04571289196610451,
      "learning_rate": 4.999451708687114e-06,
      "logits/chosen": 14.56671142578125,
      "logits/rejected": 15.112574577331543,
      "logps/chosen": -0.26506316661834717,
      "logps/rejected": -0.3439488410949707,
      "loss": 0.9267,
      "rewards/accuracies": 0.574999988079071,
      "rewards/chosen": -0.39759472012519836,
      "rewards/margins": 0.11832849681377411,
      "rewards/rejected": -0.5159232020378113,
      "step": 10
    },
    {
      "epoch": 0.017761989342806393,
      "grad_norm": 0.0512714721262455,
      "learning_rate": 4.997807075247147e-06,
      "logits/chosen": 14.376543045043945,
      "logits/rejected": 14.862703323364258,
      "logps/chosen": -0.2708089351654053,
      "logps/rejected": -0.32412824034690857,
      "loss": 0.936,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.4062133729457855,
      "rewards/margins": 0.07997899502515793,
      "rewards/rejected": -0.4861923158168793,
      "step": 20
    },
    {
      "epoch": 0.02664298401420959,
      "grad_norm": 0.058383647352457047,
      "learning_rate": 4.9950668210706795e-06,
      "logits/chosen": 14.208717346191406,
      "logits/rejected": 15.370651245117188,
      "logps/chosen": -0.28206294775009155,
      "logps/rejected": -0.38387423753738403,
      "loss": 0.9215,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.42309442162513733,
      "rewards/margins": 0.15271687507629395,
      "rewards/rejected": -0.5758112668991089,
      "step": 30
    },
    {
      "epoch": 0.035523978685612786,
      "grad_norm": 0.06262075155973434,
      "learning_rate": 4.9912321481237616e-06,
      "logits/chosen": 14.768765449523926,
      "logits/rejected": 15.169331550598145,
      "logps/chosen": -0.27857059240341187,
      "logps/rejected": -0.3388269543647766,
      "loss": 0.9386,
      "rewards/accuracies": 0.5,
      "rewards/chosen": -0.4178559184074402,
      "rewards/margins": 0.09038447588682175,
      "rewards/rejected": -0.5082404017448425,
      "step": 40
    },
    {
      "epoch": 0.04440497335701599,
      "grad_norm": 0.06259036809206009,
      "learning_rate": 4.986304738420684e-06,
      "logits/chosen": 14.950456619262695,
      "logits/rejected": 15.232122421264648,
      "logps/chosen": -0.2961367070674896,
      "logps/rejected": -0.3322262465953827,
      "loss": 0.9317,
      "rewards/accuracies": 0.44999998807907104,
      "rewards/chosen": -0.44420504570007324,
      "rewards/margins": 0.054134320467710495,
      "rewards/rejected": -0.4983394145965576,
      "step": 50
    },
    {
      "epoch": 0.04440497335701599,
      "eval_logits/chosen": 14.56529426574707,
      "eval_logits/rejected": 14.895020484924316,
      "eval_logps/chosen": -0.2806546986103058,
      "eval_logps/rejected": -0.3486972451210022,
      "eval_loss": 0.9381324052810669,
      "eval_rewards/accuracies": 0.5274725556373596,
      "eval_rewards/chosen": -0.4209820330142975,
      "eval_rewards/margins": 0.10206379741430283,
      "eval_rewards/rejected": -0.5230458974838257,
      "eval_runtime": 25.2574,
      "eval_samples_per_second": 28.823,
      "eval_steps_per_second": 3.603,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.187616525301842e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}