trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.027285129604365622,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0068212824010914054,
      "grad_norm": 1.9269121253558394,
      "learning_rate": 4.7288159402146e-05,
      "loss": 0.8471,
      "num_tokens": 3759146.0,
      "step": 5
    },
    {
      "epoch": 0.013642564802182811,
      "grad_norm": 0.5808226827267438,
      "learning_rate": 3.3023423460667985e-05,
      "loss": 0.7116,
      "num_tokens": 7668808.0,
      "step": 10
    },
    {
      "epoch": 0.020463847203274217,
      "grad_norm": 0.37829142833477414,
      "learning_rate": 1.5193666442245402e-05,
      "loss": 0.6539,
      "num_tokens": 11368873.0,
      "step": 15
    },
    {
      "epoch": 0.027285129604365622,
      "grad_norm": 0.29058282503596367,
      "learning_rate": 5.3068706734387484e-06,
      "loss": 0.6388,
      "num_tokens": 15118063.0,
      "step": 20
    },
    {
      "epoch": 0.027285129604365622,
      "step": 20,
      "total_flos": 30770262441984.0,
      "train_loss": 0.712840223312378,
      "train_runtime": 169.7887,
      "train_samples_per_second": 15.078,
      "train_steps_per_second": 0.118
    }
  ],
  "logging_steps": 5,
  "max_steps": 20,
  "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": 30770262441984.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}