outputs/checkpoint-100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.32,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16,
      "grad_norm": 0.17174428701400757,
      "learning_rate": 0.0001,
      "loss": 1.229,
      "step": 50
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.1649257093667984,
      "learning_rate": 0.0002,
      "loss": 1.0561,
      "step": 100
    }
  ],
  "logging_steps": 50,
  "max_steps": 1872,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.11739689200128e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}