trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 5970,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8375209380234506,
      "grad_norm": 0.8667312860488892,
      "learning_rate": 4.581239530988275e-05,
      "loss": 7.6874,
      "step": 500
    },
    {
      "epoch": 1.675041876046901,
      "grad_norm": 1.0515320301055908,
      "learning_rate": 4.16247906197655e-05,
      "loss": 7.1236,
      "step": 1000
    },
    {
      "epoch": 2.5125628140703515,
      "grad_norm": 0.9544970393180847,
      "learning_rate": 3.7437185929648245e-05,
      "loss": 6.9511,
      "step": 1500
    },
    {
      "epoch": 3.3500837520938025,
      "grad_norm": 1.0608201026916504,
      "learning_rate": 3.324958123953099e-05,
      "loss": 6.8374,
      "step": 2000
    },
    {
      "epoch": 4.187604690117253,
      "grad_norm": 1.3822133541107178,
      "learning_rate": 2.906197654941374e-05,
      "loss": 6.7455,
      "step": 2500
    },
    {
      "epoch": 5.025125628140704,
      "grad_norm": 1.3496253490447998,
      "learning_rate": 2.4874371859296484e-05,
      "loss": 6.6841,
      "step": 3000
    },
    {
      "epoch": 5.8626465661641545,
      "grad_norm": 1.0734386444091797,
      "learning_rate": 2.0686767169179232e-05,
      "loss": 6.6407,
      "step": 3500
    },
    {
      "epoch": 6.700167504187605,
      "grad_norm": 1.4356346130371094,
      "learning_rate": 1.6499162479061976e-05,
      "loss": 6.6059,
      "step": 4000
    },
    {
      "epoch": 7.5376884422110555,
      "grad_norm": 1.3260369300842285,
      "learning_rate": 1.2311557788944725e-05,
      "loss": 6.5782,
      "step": 4500
    },
    {
      "epoch": 8.375209380234505,
      "grad_norm": 1.589943528175354,
      "learning_rate": 8.123953098827471e-06,
      "loss": 6.5581,
      "step": 5000
    },
    {
      "epoch": 9.212730318257956,
      "grad_norm": 1.1932653188705444,
      "learning_rate": 3.936348408710218e-06,
      "loss": 6.5496,
      "step": 5500
    },
    {
      "epoch": 10.0,
      "step": 5970,
      "total_flos": 7568723438714880.0,
      "train_loss": 6.792878454773869,
      "train_runtime": 2074.686,
      "train_samples_per_second": 92.024,
      "train_steps_per_second": 2.878
    }
  ],
  "logging_steps": 500,
  "max_steps": 5970,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7568723438714880.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}