trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.125,
      "grad_norm": 4.301389694213867,
      "learning_rate": 2e-05,
      "loss": 0.4434,
      "step": 10
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.2016409635543823,
      "learning_rate": 2e-05,
      "loss": 0.1615,
      "step": 20
    },
    {
      "epoch": 0.375,
      "grad_norm": 7.786351203918457,
      "learning_rate": 2e-05,
      "loss": 0.3108,
      "step": 30
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.272088050842285,
      "learning_rate": 2e-05,
      "loss": 0.265,
      "step": 40
    },
    {
      "epoch": 0.625,
      "grad_norm": 8.268477439880371,
      "learning_rate": 2e-05,
      "loss": 0.1791,
      "step": 50
    },
    {
      "epoch": 0.75,
      "grad_norm": 4.466449737548828,
      "learning_rate": 2e-05,
      "loss": 0.1371,
      "step": 60
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.038673318922519684,
      "learning_rate": 2e-05,
      "loss": 0.0898,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 9.542387008666992,
      "learning_rate": 2e-05,
      "loss": 0.0904,
      "step": 80
    }
  ],
  "logging_steps": 10,
  "max_steps": 80,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}