trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 656,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1524390243902439,
      "grad_norm": 4.109804630279541,
      "learning_rate": 4.711864406779661e-05,
      "loss": 0.1488,
      "step": 100
    },
    {
      "epoch": 0.3048780487804878,
      "grad_norm": 1.42342209815979,
      "learning_rate": 3.8644067796610175e-05,
      "loss": 0.0939,
      "step": 200
    },
    {
      "epoch": 0.4573170731707317,
      "grad_norm": 7.705954074859619,
      "learning_rate": 3.016949152542373e-05,
      "loss": 0.0744,
      "step": 300
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 5.876913070678711,
      "learning_rate": 2.1694915254237287e-05,
      "loss": 0.1175,
      "step": 400
    },
    {
      "epoch": 0.7621951219512195,
      "grad_norm": 4.6725382804870605,
      "learning_rate": 1.3220338983050848e-05,
      "loss": 0.0954,
      "step": 500
    },
    {
      "epoch": 0.9146341463414634,
      "grad_norm": 3.6604549884796143,
      "learning_rate": 4.745762711864407e-06,
      "loss": 0.0813,
      "step": 600
    }
  ],
  "logging_steps": 100,
  "max_steps": 656,
  "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": 0.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}