trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990884229717412,
  "eval_steps": 500,
  "global_step": 137,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07292616226071102,
      "grad_norm": 2.03125,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.4613,
      "step": 10
    },
    {
      "epoch": 0.14585232452142205,
      "grad_norm": 1.21875,
      "learning_rate": 4.970701059450872e-05,
      "loss": 1.2568,
      "step": 20
    },
    {
      "epoch": 0.2187784867821331,
      "grad_norm": 0.9140625,
      "learning_rate": 4.79413289650907e-05,
      "loss": 1.2099,
      "step": 30
    },
    {
      "epoch": 0.2917046490428441,
      "grad_norm": 0.91015625,
      "learning_rate": 4.468715765333664e-05,
      "loss": 1.1924,
      "step": 40
    },
    {
      "epoch": 0.3646308113035551,
      "grad_norm": 0.81640625,
      "learning_rate": 4.015563527416595e-05,
      "loss": 1.1706,
      "step": 50
    },
    {
      "epoch": 0.4375569735642662,
      "grad_norm": 0.8046875,
      "learning_rate": 3.46407781122034e-05,
      "loss": 1.1576,
      "step": 60
    },
    {
      "epoch": 0.5104831358249772,
      "grad_norm": 0.80859375,
      "learning_rate": 2.8500403624215734e-05,
      "loss": 1.14,
      "step": 70
    },
    {
      "epoch": 0.5834092980856882,
      "grad_norm": 0.79296875,
      "learning_rate": 2.2132914365039993e-05,
      "loss": 1.1243,
      "step": 80
    },
    {
      "epoch": 0.6563354603463992,
      "grad_norm": 0.73828125,
      "learning_rate": 1.5951448652822047e-05,
      "loss": 1.1189,
      "step": 90
    },
    {
      "epoch": 0.7292616226071102,
      "grad_norm": 0.6953125,
      "learning_rate": 1.035707514179513e-05,
      "loss": 1.122,
      "step": 100
    },
    {
      "epoch": 0.8021877848678214,
      "grad_norm": 0.68359375,
      "learning_rate": 5.712770504451426e-06,
      "loss": 1.1159,
      "step": 110
    },
    {
      "epoch": 0.8751139471285324,
      "grad_norm": 0.69921875,
      "learning_rate": 2.3198686149022013e-06,
      "loss": 1.1201,
      "step": 120
    },
    {
      "epoch": 0.9480401093892434,
      "grad_norm": 0.76953125,
      "learning_rate": 3.9850926816357157e-07,
      "loss": 1.1217,
      "step": 130
    },
    {
      "epoch": 0.9990884229717412,
      "step": 137,
      "total_flos": 8.085894968356372e+17,
      "train_loss": 1.1745838492456144,
      "train_runtime": 5870.8803,
      "train_samples_per_second": 2.987,
      "train_steps_per_second": 0.023
    }
  ],
  "logging_steps": 10,
  "max_steps": 137,
  "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": 8.085894968356372e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}