checkpoint-15/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100.0,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.07217105478048325,
      "learning_rate": 0.0002828184038479814,
      "loss": 0.5082,
      "step": 5
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.1449793428182602,
      "learning_rate": 0.00013191949796170156,
      "loss": 0.2802,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.09720945358276367,
      "learning_rate": 4.358727386092198e-06,
      "loss": 0.1643,
      "step": 15
    }
  ],
  "logging_steps": 5,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8019787351261184e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}