trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5384615384615383,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 1.0270750522613525,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5994,
      "step": 10
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 1.0943247079849243,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.306,
      "step": 20
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.8214321732521057,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.2207,
      "step": 30
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.7468852400779724,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.1827,
      "step": 40
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 0.5866342782974243,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.1552,
      "step": 50
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.3692125678062439,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1458,
      "step": 60
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 0.33734169602394104,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.1356,
      "step": 70
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.29717421531677246,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.1356,
      "step": 80
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}