checkpoint-16/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.918918918918919,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 66.02604675292969,
      "learning_rate": 2.3333553495294033e-05,
      "loss": 9.0853,
      "step": 5
    },
    {
      "epoch": 4.324324324324325,
      "grad_norm": 22.67275619506836,
      "learning_rate": 9.259748514523654e-06,
      "loss": 2.016,
      "step": 10
    },
    {
      "epoch": 6.486486486486487,
      "grad_norm": 9.565340995788574,
      "learning_rate": 2.8822079395154357e-07,
      "loss": 0.5055,
      "step": 15
    }
  ],
  "logging_steps": 5,
  "max_steps": 16,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 3.566531758742569e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}