trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 647,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1545595054095827,
      "grad_norm": 0.2346014678478241,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.2952,
      "step": 100
    },
    {
      "epoch": 0.3091190108191654,
      "grad_norm": 0.17673051357269287,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.2563,
      "step": 200
    },
    {
      "epoch": 0.46367851622874806,
      "grad_norm": 0.30051079392433167,
      "learning_rate": 2e-05,
      "loss": 2.1728,
      "step": 300
    },
    {
      "epoch": 0.6182380216383307,
      "grad_norm": 0.4798201024532318,
      "learning_rate": 1.617403910924919e-05,
      "loss": 2.0259,
      "step": 400
    },
    {
      "epoch": 0.7727975270479135,
      "grad_norm": 0.611906886100769,
      "learning_rate": 7.623751784507707e-06,
      "loss": 1.9245,
      "step": 500
    },
    {
      "epoch": 0.9273570324574961,
      "grad_norm": 0.652037501335144,
      "learning_rate": 8.917510076042058e-07,
      "loss": 1.8847,
      "step": 600
    },
    {
      "epoch": 1.0,
      "step": 647,
      "total_flos": 1.17580762841088e+16,
      "train_loss": 2.0752741063396565,
      "train_runtime": 203.1277,
      "train_samples_per_second": 6.37,
      "train_steps_per_second": 3.185
    }
  ],
  "logging_steps": 100,
  "max_steps": 647,
  "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": 1.17580762841088e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}