checkpoint-2000/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7692307692307693,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 76.94072723388672,
      "learning_rate": 9.040384615384617e-06,
      "loss": -102.1462,
      "step": 500
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 531.77978515625,
      "learning_rate": 8.078846153846154e-06,
      "loss": -151.8301,
      "step": 1000
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 139.83151245117188,
      "learning_rate": 7.117307692307693e-06,
      "loss": -155.388,
      "step": 1500
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 114.4839096069336,
      "learning_rate": 6.15576923076923e-06,
      "loss": -158.7632,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 5200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}