trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "grad_norm": 6.996930122375488,
      "learning_rate": 5e-06,
      "loss": 1.214,
      "step": 1
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.919618606567383,
      "learning_rate": 1e-05,
      "loss": 1.2166,
      "step": 2
    },
    {
      "epoch": 0.75,
      "grad_norm": 4.8507866859436035,
      "learning_rate": 9.755282581475769e-06,
      "loss": 1.1411,
      "step": 3
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.6980366706848145,
      "learning_rate": 9.045084971874738e-06,
      "loss": 1.103,
      "step": 4
    },
    {
      "epoch": 1.25,
      "grad_norm": 6.26192569732666,
      "learning_rate": 7.938926261462366e-06,
      "loss": 1.101,
      "step": 5
    },
    {
      "epoch": 1.5,
      "grad_norm": 5.828583717346191,
      "learning_rate": 6.545084971874738e-06,
      "loss": 1.0338,
      "step": 6
    },
    {
      "epoch": 1.75,
      "grad_norm": 6.160283088684082,
      "learning_rate": 5e-06,
      "loss": 1.0253,
      "step": 7
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.712091445922852,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.9904,
      "step": 8
    },
    {
      "epoch": 2.25,
      "grad_norm": 3.2412965297698975,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.9406,
      "step": 9
    },
    {
      "epoch": 2.5,
      "grad_norm": 2.3865790367126465,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.9228,
      "step": 10
    },
    {
      "epoch": 2.75,
      "grad_norm": 2.0577757358551025,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.9353,
      "step": 11
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.9040799140930176,
      "learning_rate": 0.0,
      "loss": 0.9267,
      "step": 12
    },
    {
      "epoch": 3.0,
      "step": 12,
      "total_flos": 5675056554311680.0,
      "train_loss": 1.0458828210830688,
      "train_runtime": 216.8763,
      "train_samples_per_second": 5.187,
      "train_steps_per_second": 0.055
    }
  ],
  "logging_steps": 1,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 5675056554311680.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}