trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 0,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 11.311515808105469,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.1143,
      "step": 1
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 7.503225803375244,
      "learning_rate": 7.77777777777778e-06,
      "loss": 0.936,
      "step": 2
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 10.568900108337402,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.864,
      "step": 3
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.4477643966674805,
      "learning_rate": 5.555555555555557e-06,
      "loss": 0.8292,
      "step": 4
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 2.3272294998168945,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.8024,
      "step": 5
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.5451749563217163,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.7686,
      "step": 6
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 1.785913348197937,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.7647,
      "step": 7
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.3362054824829102,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.7441,
      "step": 8
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.1093463897705078,
      "learning_rate": 0.0,
      "loss": 0.7718,
      "step": 9
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 9,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2309601097678848.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}