trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9983579638752053,
  "eval_steps": 500,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.052545155993431854,
      "grad_norm": 16.077190802187676,
      "learning_rate": 0.0,
      "loss": 2.3057,
      "step": 1
    },
    {
      "epoch": 0.10509031198686371,
      "grad_norm": 17.39692052150077,
      "learning_rate": 5e-06,
      "loss": 2.39,
      "step": 2
    },
    {
      "epoch": 0.15763546798029557,
      "grad_norm": 12.305210679711815,
      "learning_rate": 1e-05,
      "loss": 2.2061,
      "step": 3
    },
    {
      "epoch": 0.21018062397372742,
      "grad_norm": 8.35782605169056,
      "learning_rate": 9.91486549841951e-06,
      "loss": 1.9225,
      "step": 4
    },
    {
      "epoch": 0.2627257799671593,
      "grad_norm": 11.34251016444334,
      "learning_rate": 9.66236114702178e-06,
      "loss": 1.667,
      "step": 5
    },
    {
      "epoch": 0.31527093596059114,
      "grad_norm": 15.501119915951904,
      "learning_rate": 9.251085678648072e-06,
      "loss": 1.5072,
      "step": 6
    },
    {
      "epoch": 0.367816091954023,
      "grad_norm": 6.363923937713399,
      "learning_rate": 8.695044586103297e-06,
      "loss": 1.2449,
      "step": 7
    },
    {
      "epoch": 0.42036124794745483,
      "grad_norm": 4.647071328375543,
      "learning_rate": 8.013173181896283e-06,
      "loss": 1.1704,
      "step": 8
    },
    {
      "epoch": 0.4729064039408867,
      "grad_norm": 3.465580340666149,
      "learning_rate": 7.2286917788826926e-06,
      "loss": 1.1505,
      "step": 9
    },
    {
      "epoch": 0.5254515599343186,
      "grad_norm": 2.7262505628699203,
      "learning_rate": 6.368314950360416e-06,
      "loss": 1.0885,
      "step": 10
    },
    {
      "epoch": 0.5779967159277504,
      "grad_norm": 2.7528743802546627,
      "learning_rate": 5.46134179731651e-06,
      "loss": 1.1462,
      "step": 11
    },
    {
      "epoch": 0.6305418719211823,
      "grad_norm": 2.4196115928746784,
      "learning_rate": 4.53865820268349e-06,
      "loss": 1.0478,
      "step": 12
    },
    {
      "epoch": 0.6830870279146142,
      "grad_norm": 2.2650596225267834,
      "learning_rate": 3.6316850496395863e-06,
      "loss": 1.0811,
      "step": 13
    },
    {
      "epoch": 0.735632183908046,
      "grad_norm": 2.344241062074149,
      "learning_rate": 2.771308221117309e-06,
      "loss": 1.0594,
      "step": 14
    },
    {
      "epoch": 0.7881773399014779,
      "grad_norm": 2.3269744895106927,
      "learning_rate": 1.9868268181037186e-06,
      "loss": 1.0291,
      "step": 15
    },
    {
      "epoch": 0.8407224958949097,
      "grad_norm": 2.140419827300594,
      "learning_rate": 1.3049554138967052e-06,
      "loss": 0.931,
      "step": 16
    },
    {
      "epoch": 0.8932676518883416,
      "grad_norm": 2.062028584753248,
      "learning_rate": 7.489143213519301e-07,
      "loss": 1.0292,
      "step": 17
    },
    {
      "epoch": 0.9458128078817734,
      "grad_norm": 2.0801310407367026,
      "learning_rate": 3.3763885297822153e-07,
      "loss": 1.0591,
      "step": 18
    },
    {
      "epoch": 0.9983579638752053,
      "grad_norm": 2.1425834658879146,
      "learning_rate": 8.513450158049109e-08,
      "loss": 1.0019,
      "step": 19
    }
  ],
  "logging_steps": 1,
  "max_steps": 19,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3084490588160.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}