trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1792,
  "eval_steps": 500,
  "global_step": 14,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0128,
      "grad_norm": 12.99861295213489,
      "learning_rate": 6.25e-07,
      "loss": 0.7998,
      "step": 1
    },
    {
      "epoch": 0.0256,
      "grad_norm": 12.355498309634275,
      "learning_rate": 1.25e-06,
      "loss": 0.7667,
      "step": 2
    },
    {
      "epoch": 0.0384,
      "grad_norm": 13.377026375153603,
      "learning_rate": 1.8750000000000003e-06,
      "loss": 0.8004,
      "step": 3
    },
    {
      "epoch": 0.0512,
      "grad_norm": 13.4959625671783,
      "learning_rate": 2.5e-06,
      "loss": 0.7769,
      "step": 4
    },
    {
      "epoch": 0.064,
      "grad_norm": 10.482327280051456,
      "learning_rate": 3.125e-06,
      "loss": 0.7544,
      "step": 5
    },
    {
      "epoch": 0.0768,
      "grad_norm": 18.566810425661483,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.7639,
      "step": 6
    },
    {
      "epoch": 0.0896,
      "grad_norm": 22.961763121425445,
      "learning_rate": 4.3750000000000005e-06,
      "loss": 0.6802,
      "step": 7
    },
    {
      "epoch": 0.1024,
      "grad_norm": 23.288202176933027,
      "learning_rate": 5e-06,
      "loss": 0.6742,
      "step": 8
    },
    {
      "epoch": 0.1152,
      "grad_norm": 5.353762222622938,
      "learning_rate": 4.997482666353287e-06,
      "loss": 0.5583,
      "step": 9
    },
    {
      "epoch": 0.128,
      "grad_norm": 29.528240817452634,
      "learning_rate": 4.989935734988098e-06,
      "loss": 0.554,
      "step": 10
    },
    {
      "epoch": 0.1408,
      "grad_norm": 6.270913357192842,
      "learning_rate": 4.977374404419838e-06,
      "loss": 0.5101,
      "step": 11
    },
    {
      "epoch": 0.1536,
      "grad_norm": 6.437334442280678,
      "learning_rate": 4.959823971496575e-06,
      "loss": 0.4621,
      "step": 12
    },
    {
      "epoch": 0.1664,
      "grad_norm": 4.101541939034336,
      "learning_rate": 4.937319780454559e-06,
      "loss": 0.4742,
      "step": 13
    },
    {
      "epoch": 0.1792,
      "grad_norm": 2.038050058538055,
      "learning_rate": 4.909907151739634e-06,
      "loss": 0.4091,
      "step": 14
    }
  ],
  "logging_steps": 1,
  "max_steps": 78,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 17358889091072.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}