trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9966329966329966,
  "eval_steps": 500,
  "global_step": 148,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04713804713804714,
      "grad_norm": NaN,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": NaN,
      "learning_rate": 4.642857142857143e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": NaN,
      "learning_rate": 4.975670171853926e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": NaN,
      "learning_rate": 4.88646908061933e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": NaN,
      "learning_rate": 4.734081600808531e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": NaN,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": NaN,
      "learning_rate": 4.257452643564155e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": NaN,
      "learning_rate": 3.945830840419966e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": NaN,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": NaN,
      "learning_rate": 3.217008081777726e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": NaN,
      "learning_rate": 2.8191041196514873e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": NaN,
      "learning_rate": 2.4127512582437485e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.6127946127946128,
      "grad_norm": NaN,
      "learning_rate": 2.0087084761679245e-05,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.6599326599326599,
      "grad_norm": NaN,
      "learning_rate": 1.617673588215328e-05,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": NaN,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": NaN,
      "learning_rate": 9.154225815032242e-06,
      "loss": 0.0,
      "step": 112
    },
    {
      "epoch": 0.8013468013468014,
      "grad_norm": NaN,
      "learning_rate": 6.22799917546252e-06,
      "loss": 0.0,
      "step": 119
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": NaN,
      "learning_rate": 3.798797596089351e-06,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.8956228956228957,
      "grad_norm": NaN,
      "learning_rate": 1.9309388911139426e-06,
      "loss": 0.0,
      "step": 133
    },
    {
      "epoch": 0.9427609427609428,
      "grad_norm": NaN,
      "learning_rate": 6.738782355044049e-07,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": NaN,
      "learning_rate": 6.089874350439506e-08,
      "loss": 0.0,
      "step": 147
    }
  ],
  "logging_steps": 7,
  "max_steps": 148,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 74,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1296015690362880.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}