trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9885057471264368,
  "eval_steps": 500,
  "global_step": 43,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022988505747126436,
      "grad_norm": 23.497586183908798,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.9349,
      "step": 1
    },
    {
      "epoch": 0.22988505747126436,
      "grad_norm": 2.43441988696975,
      "learning_rate": 9.578866633275289e-06,
      "loss": 1.5695,
      "step": 10
    },
    {
      "epoch": 0.45977011494252873,
      "grad_norm": 1.638981778394223,
      "learning_rate": 6.6234973460234184e-06,
      "loss": 1.1714,
      "step": 20
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 1.6565492884067081,
      "learning_rate": 2.6202630348146323e-06,
      "loss": 1.0604,
      "step": 30
    },
    {
      "epoch": 0.9195402298850575,
      "grad_norm": 1.6656152182027797,
      "learning_rate": 1.5299867030334815e-07,
      "loss": 1.005,
      "step": 40
    },
    {
      "epoch": 0.9885057471264368,
      "step": 43,
      "total_flos": 4084507607040.0,
      "train_loss": 1.1981246249620305,
      "train_runtime": 824.5041,
      "train_samples_per_second": 1.687,
      "train_steps_per_second": 0.052
    }
  ],
  "logging_steps": 10,
  "max_steps": 43,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4084507607040.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}