trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 1.1875,
      "learning_rate": 1.827402135231317e-05,
      "loss": 0.4486,
      "step": 100
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 1.21875,
      "learning_rate": 1.6494661921708185e-05,
      "loss": 0.1052,
      "step": 200
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.90625,
      "learning_rate": 1.4715302491103204e-05,
      "loss": 0.0932,
      "step": 300
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 1.3984375,
      "learning_rate": 1.2935943060498222e-05,
      "loss": 0.0988,
      "step": 400
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.5703125,
      "learning_rate": 1.1156583629893238e-05,
      "loss": 0.0903,
      "step": 500
    },
    {
      "epoch": 1.0657777777777777,
      "grad_norm": 1.265625,
      "learning_rate": 9.377224199288258e-06,
      "loss": 0.0912,
      "step": 600
    },
    {
      "epoch": 1.2435555555555555,
      "grad_norm": 0.65234375,
      "learning_rate": 7.597864768683275e-06,
      "loss": 0.0798,
      "step": 700
    },
    {
      "epoch": 1.4213333333333333,
      "grad_norm": 1.890625,
      "learning_rate": 5.818505338078292e-06,
      "loss": 0.0835,
      "step": 800
    },
    {
      "epoch": 1.5991111111111111,
      "grad_norm": 2.015625,
      "learning_rate": 4.03914590747331e-06,
      "loss": 0.0785,
      "step": 900
    },
    {
      "epoch": 1.7768888888888887,
      "grad_norm": 1.546875,
      "learning_rate": 2.2597864768683274e-06,
      "loss": 0.0785,
      "step": 1000
    },
    {
      "epoch": 1.9546666666666668,
      "grad_norm": 2.15625,
      "learning_rate": 4.804270462633452e-07,
      "loss": 0.079,
      "step": 1100
    }
  ],
  "logging_steps": 100,
  "max_steps": 1126,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.1068310033650483e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}