trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.8734296560287476,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.3671,
      "step": 33
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7665506601333618,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.5592,
      "step": 66
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7064546942710876,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8033,
      "step": 99
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.7876946926116943,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.6101,
      "step": 132
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.7344518303871155,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.4754,
      "step": 165
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.986533522605896,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.3721,
      "step": 198
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.7859296798706055,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2771,
      "step": 231
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.0256364345550537,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.2164,
      "step": 264
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.610874354839325,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.1827,
      "step": 297
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.2651737630367279,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1653,
      "step": 330
    }
  ],
  "logging_steps": 500,
  "max_steps": 330,
  "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": 1494970592256000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}