checkpoint-57/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.8860759493670884,
  "eval_steps": 100,
  "global_step": 57,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 5.980856418609619,
      "learning_rate": 4.8e-05,
      "loss": 2.6323,
      "step": 25
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 3.955669403076172,
      "learning_rate": 9.8e-05,
      "loss": 0.2566,
      "step": 50
    }
  ],
  "logging_steps": 25,
  "max_steps": 57,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 4.6849425408e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}