trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9968454258675079,
  "eval_steps": 500,
  "global_step": 158,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06309148264984227,
      "grad_norm": 3.9812393188476562,
      "learning_rate": 7.99912273389938e-06,
      "loss": 1.7721,
      "step": 10
    },
    {
      "epoch": 0.12618296529968454,
      "grad_norm": 1.7699296474456787,
      "learning_rate": 7.89431561149264e-06,
      "loss": 1.5926,
      "step": 20
    },
    {
      "epoch": 0.1892744479495268,
      "grad_norm": 1.4895917177200317,
      "learning_rate": 7.619308209864078e-06,
      "loss": 1.4542,
      "step": 30
    },
    {
      "epoch": 0.25236593059936907,
      "grad_norm": 1.315661907196045,
      "learning_rate": 7.1861196720967844e-06,
      "loss": 1.3731,
      "step": 40
    },
    {
      "epoch": 0.31545741324921134,
      "grad_norm": 1.2776089906692505,
      "learning_rate": 6.613682415960422e-06,
      "loss": 1.3256,
      "step": 50
    },
    {
      "epoch": 0.3785488958990536,
      "grad_norm": 1.3066082000732422,
      "learning_rate": 5.9270146964068605e-06,
      "loss": 1.2842,
      "step": 60
    },
    {
      "epoch": 0.4416403785488959,
      "grad_norm": 1.2110307216644287,
      "learning_rate": 5.156127187777886e-06,
      "loss": 1.2698,
      "step": 70
    },
    {
      "epoch": 0.5047318611987381,
      "grad_norm": 1.25718355178833,
      "learning_rate": 4.334711373329263e-06,
      "loss": 1.2558,
      "step": 80
    },
    {
      "epoch": 0.5678233438485805,
      "grad_norm": 1.1852293014526367,
      "learning_rate": 3.498667065742782e-06,
      "loss": 1.2268,
      "step": 90
    },
    {
      "epoch": 0.6309148264984227,
      "grad_norm": 1.1762120723724365,
      "learning_rate": 2.6845334130456668e-06,
      "loss": 1.2238,
      "step": 100
    },
    {
      "epoch": 0.694006309148265,
      "grad_norm": 1.1798163652420044,
      "learning_rate": 1.9278919625074795e-06,
      "loss": 1.2093,
      "step": 110
    },
    {
      "epoch": 0.7570977917981072,
      "grad_norm": 1.1991688013076782,
      "learning_rate": 1.2618115762852451e-06,
      "loss": 1.227,
      "step": 120
    },
    {
      "epoch": 0.8201892744479495,
      "grad_norm": 1.1350749731063843,
      "learning_rate": 7.154031634651838e-07,
      "loss": 1.2058,
      "step": 130
    },
    {
      "epoch": 0.8832807570977917,
      "grad_norm": 1.1695517301559448,
      "learning_rate": 3.1254739364599835e-07,
      "loss": 1.208,
      "step": 140
    },
    {
      "epoch": 0.9463722397476341,
      "grad_norm": 1.1390548944473267,
      "learning_rate": 7.085099708524556e-08,
      "loss": 1.2032,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 158,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6672282252869632e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}