trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 155,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 3.3882408142089844,
      "learning_rate": 1.125e-05,
      "loss": 0.5392,
      "step": 10
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": 1.0038115978240967,
      "learning_rate": 1.99770217861636e-05,
      "loss": 0.1627,
      "step": 20
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 0.6339080929756165,
      "learning_rate": 1.9571451231564523e-05,
      "loss": 0.0999,
      "step": 30
    },
    {
      "epoch": 0.2588996763754045,
      "grad_norm": 0.41973698139190674,
      "learning_rate": 1.86790270392905e-05,
      "loss": 0.0729,
      "step": 40
    },
    {
      "epoch": 0.32362459546925565,
      "grad_norm": 0.46516239643096924,
      "learning_rate": 1.734514253098589e-05,
      "loss": 0.0725,
      "step": 50
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.4504494369029999,
      "learning_rate": 1.5637645988943008e-05,
      "loss": 0.0641,
      "step": 60
    },
    {
      "epoch": 0.45307443365695793,
      "grad_norm": 0.3512699007987976,
      "learning_rate": 1.3643389540670963e-05,
      "loss": 0.0564,
      "step": 70
    },
    {
      "epoch": 0.517799352750809,
      "grad_norm": 0.3928837180137634,
      "learning_rate": 1.1463811409361667e-05,
      "loss": 0.0511,
      "step": 80
    },
    {
      "epoch": 0.5825242718446602,
      "grad_norm": 0.325100839138031,
      "learning_rate": 9.209776239900453e-06,
      "loss": 0.0515,
      "step": 90
    },
    {
      "epoch": 0.6472491909385113,
      "grad_norm": 0.308345764875412,
      "learning_rate": 6.995935948193294e-06,
      "loss": 0.0483,
      "step": 100
    },
    {
      "epoch": 0.7119741100323624,
      "grad_norm": 0.3138153553009033,
      "learning_rate": 4.934897930252887e-06,
      "loss": 0.0442,
      "step": 110
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 0.3170579671859741,
      "learning_rate": 3.1314972661673572e-06,
      "loss": 0.0456,
      "step": 120
    },
    {
      "epoch": 0.8414239482200647,
      "grad_norm": 0.3011327385902405,
      "learning_rate": 1.6774642643563955e-06,
      "loss": 0.0476,
      "step": 130
    },
    {
      "epoch": 0.9061488673139159,
      "grad_norm": 0.24439357221126556,
      "learning_rate": 6.467585824627886e-07,
      "loss": 0.043,
      "step": 140
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 0.27276483178138733,
      "learning_rate": 9.180725568338045e-08,
      "loss": 0.0447,
      "step": 150
    },
    {
      "epoch": 1.0,
      "step": 155,
      "total_flos": 3.151751208448819e+17,
      "train_loss": 0.0941466587205087,
      "train_runtime": 2000.2548,
      "train_samples_per_second": 4.943,
      "train_steps_per_second": 0.077
    }
  ],
  "logging_steps": 10,
  "max_steps": 155,
  "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": 3.151751208448819e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}