trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015278838808250573,
  "eval_steps": 500,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003819709702062643,
      "grad_norm": 20.709548452094197,
      "learning_rate": 2.531645569620253e-08,
      "loss": 1.6738,
      "step": 1
    },
    {
      "epoch": 0.0007639419404125286,
      "grad_norm": 22.272614353028157,
      "learning_rate": 5.063291139240506e-08,
      "loss": 1.848,
      "step": 2
    },
    {
      "epoch": 0.001145912910618793,
      "grad_norm": 19.9635718773857,
      "learning_rate": 7.59493670886076e-08,
      "loss": 1.6288,
      "step": 3
    },
    {
      "epoch": 0.0015278838808250573,
      "grad_norm": 21.57708535766677,
      "learning_rate": 1.0126582278481012e-07,
      "loss": 1.7674,
      "step": 4
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 2618,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1192507047936.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}