trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1650,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.941824197769165,
      "learning_rate": 0.0002,
      "loss": 0.8625,
      "step": 250
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.808902382850647,
      "learning_rate": 0.0002,
      "loss": 0.4086,
      "step": 500
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 1.3147000074386597,
      "learning_rate": 0.0002,
      "loss": 0.2634,
      "step": 750
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.5747100710868835,
      "learning_rate": 0.0002,
      "loss": 0.2017,
      "step": 1000
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.7775928378105164,
      "learning_rate": 0.0002,
      "loss": 0.1724,
      "step": 1250
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.7940827012062073,
      "learning_rate": 0.0002,
      "loss": 0.1548,
      "step": 1500
    }
  ],
  "logging_steps": 250,
  "max_steps": 1650,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.333719808200704e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}