checkpoint-1000/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.48496605237633367,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24248302618816683,
      "grad_norm": 22.99319839477539,
      "learning_rate": 2.929668552950687e-05,
      "loss": 1.9432,
      "step": 500
    },
    {
      "epoch": 0.48496605237633367,
      "grad_norm": 29.776500701904297,
      "learning_rate": 2.5254648342764755e-05,
      "loss": 1.0335,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 4124,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1060022550528000.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}