trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 17600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 1.1378424167633057,
      "learning_rate": 9.755558302740203e-05,
      "loss": 0.4049,
      "step": 1760
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8847500085830688,
      "learning_rate": 9.045609504540433e-05,
      "loss": 0.1213,
      "step": 3520
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.5457971692085266,
      "learning_rate": 7.940370166109008e-05,
      "loss": 0.0897,
      "step": 5280
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9751428365707397,
      "learning_rate": 6.547631198087277e-05,
      "loss": 0.0791,
      "step": 7040
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.33531779050827026,
      "learning_rate": 5.00267749361089e-05,
      "loss": 0.0714,
      "step": 8800
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.21050383150577545,
      "learning_rate": 3.457461697404673e-05,
      "loss": 0.0662,
      "step": 10560
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.30969759821891785,
      "learning_rate": 2.0632402977528074e-05,
      "loss": 0.0624,
      "step": 12320
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.19539938867092133,
      "learning_rate": 9.570144474699145e-06,
      "loss": 0.0588,
      "step": 14080
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.2412504404783249,
      "learning_rate": 2.458218186269834e-06,
      "loss": 0.0557,
      "step": 15840
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.3456253409385681,
      "learning_rate": 1.9913811794003424e-11,
      "loss": 0.0533,
      "step": 17600
    }
  ],
  "logging_steps": 500,
  "max_steps": 17600,
  "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": 1.08706216562688e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}