trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 30.619651794433594,
      "learning_rate": 8.16e-06,
      "loss": 1.8291,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 155.9861297607422,
      "learning_rate": 6.24e-06,
      "loss": 1.8251,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 59.954654693603516,
      "learning_rate": 4.2800000000000005e-06,
      "loss": 1.8171,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 32.81400680541992,
      "learning_rate": 2.28e-06,
      "loss": 1.7688,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 64.24483489990234,
      "learning_rate": 2.8e-07,
      "loss": 1.7759,
      "step": 250
    },
    {
      "epoch": 2.0,
      "step": 250,
      "total_flos": 9.4894217943552e+17,
      "train_loss": 1.8031856994628905,
      "train_runtime": 142.4314,
      "train_samples_per_second": 13.944,
      "train_steps_per_second": 1.755
    }
  ],
  "logging_steps": 50,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.4894217943552e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}