trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 150.0,
  "eval_steps": 0,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.0,
      "grad_norm": 28.77810173804074,
      "learning_rate": 9.59731543624161e-06,
      "loss": 0.2929,
      "step": 7
    },
    {
      "epoch": 14.0,
      "grad_norm": 32.94976630615273,
      "learning_rate": 9.12751677852349e-06,
      "loss": 0.5339,
      "step": 14
    },
    {
      "epoch": 21.0,
      "grad_norm": 22.659163629011367,
      "learning_rate": 8.65771812080537e-06,
      "loss": -0.647,
      "step": 21
    },
    {
      "epoch": 28.0,
      "grad_norm": 18.779812873036764,
      "learning_rate": 8.18791946308725e-06,
      "loss": 0.1258,
      "step": 28
    },
    {
      "epoch": 35.0,
      "grad_norm": 21.166285940199522,
      "learning_rate": 7.718120805369127e-06,
      "loss": -0.323,
      "step": 35
    },
    {
      "epoch": 42.0,
      "grad_norm": 20.674930310126193,
      "learning_rate": 7.248322147651007e-06,
      "loss": -1.1331,
      "step": 42
    },
    {
      "epoch": 49.0,
      "grad_norm": 21.082599745949626,
      "learning_rate": 6.778523489932887e-06,
      "loss": -1.7808,
      "step": 49
    },
    {
      "epoch": 56.0,
      "grad_norm": 25.42833996474451,
      "learning_rate": 6.308724832214766e-06,
      "loss": -1.4649,
      "step": 56
    },
    {
      "epoch": 63.0,
      "grad_norm": 33.421364334304904,
      "learning_rate": 5.8389261744966455e-06,
      "loss": -2.5893,
      "step": 63
    },
    {
      "epoch": 70.0,
      "grad_norm": 28.93650702747366,
      "learning_rate": 5.369127516778524e-06,
      "loss": -2.0502,
      "step": 70
    },
    {
      "epoch": 77.0,
      "grad_norm": 27.048390950623677,
      "learning_rate": 4.899328859060403e-06,
      "loss": -2.8393,
      "step": 77
    },
    {
      "epoch": 84.0,
      "grad_norm": 26.556589712856884,
      "learning_rate": 4.429530201342283e-06,
      "loss": -2.5302,
      "step": 84
    },
    {
      "epoch": 91.0,
      "grad_norm": 34.56822907000099,
      "learning_rate": 3.959731543624161e-06,
      "loss": -2.5762,
      "step": 91
    },
    {
      "epoch": 98.0,
      "grad_norm": 29.366343177007273,
      "learning_rate": 3.4899328859060407e-06,
      "loss": -3.1915,
      "step": 98
    },
    {
      "epoch": 105.0,
      "grad_norm": 28.06389071006964,
      "learning_rate": 3.02013422818792e-06,
      "loss": -4.004,
      "step": 105
    },
    {
      "epoch": 112.0,
      "grad_norm": 28.688787801519627,
      "learning_rate": 2.5503355704697992e-06,
      "loss": -4.0863,
      "step": 112
    },
    {
      "epoch": 119.0,
      "grad_norm": 27.75975517103016,
      "learning_rate": 2.080536912751678e-06,
      "loss": -4.0921,
      "step": 119
    },
    {
      "epoch": 126.0,
      "grad_norm": 40.330078675308606,
      "learning_rate": 1.6107382550335572e-06,
      "loss": -4.0217,
      "step": 126
    },
    {
      "epoch": 133.0,
      "grad_norm": 47.10430499215624,
      "learning_rate": 1.1409395973154363e-06,
      "loss": -4.0927,
      "step": 133
    },
    {
      "epoch": 140.0,
      "grad_norm": 39.42456464587504,
      "learning_rate": 6.711409395973155e-07,
      "loss": -4.2622,
      "step": 140
    },
    {
      "epoch": 147.0,
      "grad_norm": 35.58432307410929,
      "learning_rate": 2.0134228187919465e-07,
      "loss": -4.6801,
      "step": 147
    }
  ],
  "logging_steps": 7,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}