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": 0.8417201914367606,
      "learning_rate": 9.59731543624161e-06,
      "loss": 0.0085,
      "step": 7
    },
    {
      "epoch": 14.0,
      "grad_norm": 0.28669026236491124,
      "learning_rate": 9.12751677852349e-06,
      "loss": 0.0104,
      "step": 14
    },
    {
      "epoch": 21.0,
      "grad_norm": 1.0972848322055662,
      "learning_rate": 8.65771812080537e-06,
      "loss": 0.0014,
      "step": 21
    },
    {
      "epoch": 28.0,
      "grad_norm": 1.360934749216498,
      "learning_rate": 8.18791946308725e-06,
      "loss": -0.0028,
      "step": 28
    },
    {
      "epoch": 35.0,
      "grad_norm": 4.791222237242515,
      "learning_rate": 7.718120805369127e-06,
      "loss": -0.0199,
      "step": 35
    },
    {
      "epoch": 42.0,
      "grad_norm": 3.9478984078001704,
      "learning_rate": 7.248322147651007e-06,
      "loss": -0.0723,
      "step": 42
    },
    {
      "epoch": 49.0,
      "grad_norm": 3.6883480021071446,
      "learning_rate": 6.778523489932887e-06,
      "loss": -0.1495,
      "step": 49
    },
    {
      "epoch": 56.0,
      "grad_norm": 3.984289016263464,
      "learning_rate": 6.308724832214766e-06,
      "loss": -0.2205,
      "step": 56
    },
    {
      "epoch": 63.0,
      "grad_norm": 6.4532731848729945,
      "learning_rate": 5.8389261744966455e-06,
      "loss": -0.3157,
      "step": 63
    },
    {
      "epoch": 70.0,
      "grad_norm": 8.270747263807621,
      "learning_rate": 5.369127516778524e-06,
      "loss": -0.4443,
      "step": 70
    },
    {
      "epoch": 77.0,
      "grad_norm": 9.515366960172516,
      "learning_rate": 4.899328859060403e-06,
      "loss": -0.602,
      "step": 77
    },
    {
      "epoch": 84.0,
      "grad_norm": 9.4848621372966,
      "learning_rate": 4.429530201342283e-06,
      "loss": -0.7758,
      "step": 84
    },
    {
      "epoch": 91.0,
      "grad_norm": 9.365694828351332,
      "learning_rate": 3.959731543624161e-06,
      "loss": -0.9344,
      "step": 91
    },
    {
      "epoch": 98.0,
      "grad_norm": 9.576997151455942,
      "learning_rate": 3.4899328859060407e-06,
      "loss": -1.081,
      "step": 98
    },
    {
      "epoch": 105.0,
      "grad_norm": 11.473600533954098,
      "learning_rate": 3.02013422818792e-06,
      "loss": -1.2337,
      "step": 105
    },
    {
      "epoch": 112.0,
      "grad_norm": 12.562155969204415,
      "learning_rate": 2.5503355704697992e-06,
      "loss": -1.3785,
      "step": 112
    },
    {
      "epoch": 119.0,
      "grad_norm": 13.21657459700114,
      "learning_rate": 2.080536912751678e-06,
      "loss": -1.5255,
      "step": 119
    },
    {
      "epoch": 126.0,
      "grad_norm": 12.597297161290706,
      "learning_rate": 1.6107382550335572e-06,
      "loss": -1.6496,
      "step": 126
    },
    {
      "epoch": 133.0,
      "grad_norm": 13.992247540188092,
      "learning_rate": 1.1409395973154363e-06,
      "loss": -1.7682,
      "step": 133
    },
    {
      "epoch": 140.0,
      "grad_norm": 14.258604526810764,
      "learning_rate": 6.711409395973155e-07,
      "loss": -1.8505,
      "step": 140
    },
    {
      "epoch": 147.0,
      "grad_norm": 14.333372551681608,
      "learning_rate": 2.0134228187919465e-07,
      "loss": -1.8989,
      "step": 147
    }
  ],
  "logging_steps": 7,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 150,
  "save_steps": 0,
  "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
}