trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.3465218544006348,
      "learning_rate": 9.846798312018146e-05,
      "loss": 2.7328,
      "step": 100
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7282734513282776,
      "learning_rate": 9.230035528339211e-05,
      "loss": 1.6124,
      "step": 200
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.8552231788635254,
      "learning_rate": 8.199207394755893e-05,
      "loss": 1.2943,
      "step": 300
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.293209195137024,
      "learning_rate": 6.855218551185255e-05,
      "loss": 1.0132,
      "step": 400
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.836729049682617,
      "learning_rate": 5.32962798975689e-05,
      "loss": 0.7495,
      "step": 500
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.0586963891983032,
      "learning_rate": 3.7717711440378694e-05,
      "loss": 0.561,
      "step": 600
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.7043125629425049,
      "learning_rate": 2.334141896314057e-05,
      "loss": 0.4335,
      "step": 700
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.2614474296569824,
      "learning_rate": 1.1574654139046171e-05,
      "loss": 0.362,
      "step": 800
    },
    {
      "epoch": 9.0,
      "grad_norm": 1.796047329902649,
      "learning_rate": 3.569229892949133e-06,
      "loss": 0.3259,
      "step": 900
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.8333213925361633,
      "learning_rate": 1.0877292712792585e-07,
      "loss": 0.3123,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1919269665792000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}