trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 401,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24937655860349128,
      "grad_norm": 0.9138969779014587,
      "learning_rate": 0.00015012468827930176,
      "loss": 1.6682,
      "step": 100
    },
    {
      "epoch": 0.49875311720698257,
      "grad_norm": 0.9227935075759888,
      "learning_rate": 0.0001002493765586035,
      "loss": 1.4274,
      "step": 200
    },
    {
      "epoch": 0.7481296758104738,
      "grad_norm": 0.9506911039352417,
      "learning_rate": 5.037406483790524e-05,
      "loss": 1.4323,
      "step": 300
    },
    {
      "epoch": 0.9975062344139651,
      "grad_norm": 0.7986575961112976,
      "learning_rate": 4.987531172069825e-07,
      "loss": 1.3683,
      "step": 400
    }
  ],
  "logging_steps": 100,
  "max_steps": 401,
  "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": 3402058752614400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}