checkpoint-36/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9142857142857143,
  "eval_steps": 500,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 0.030378561466932297,
      "learning_rate": 5e-05,
      "loss": 0.5952,
      "step": 5
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 0.05285210907459259,
      "learning_rate": 4.752422169756048e-05,
      "loss": 0.583,
      "step": 10
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.04900702089071274,
      "learning_rate": 4.058724504646834e-05,
      "loss": 0.5784,
      "step": 15
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 0.041186440736055374,
      "learning_rate": 3.056302334890786e-05,
      "loss": 0.5345,
      "step": 20
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.04592454433441162,
      "learning_rate": 1.9436976651092144e-05,
      "loss": 0.4879,
      "step": 25
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.051714979112148285,
      "learning_rate": 9.412754953531663e-06,
      "loss": 0.5065,
      "step": 30
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.041197337210178375,
      "learning_rate": 2.475778302439524e-06,
      "loss": 0.5044,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.091950490859602e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}