trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9832402234636871,
  "eval_steps": 500,
  "global_step": 22,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 0.4495355188846588,
      "learning_rate": 2.5e-06,
      "loss": 0.8615,
      "step": 5
    },
    {
      "epoch": 0.44692737430167595,
      "grad_norm": 0.49592095613479614,
      "learning_rate": 5e-06,
      "loss": 0.894,
      "step": 10
    },
    {
      "epoch": 0.6703910614525139,
      "grad_norm": 0.47344380617141724,
      "learning_rate": 7.5e-06,
      "loss": 0.8808,
      "step": 15
    },
    {
      "epoch": 0.8938547486033519,
      "grad_norm": 0.5614600777626038,
      "learning_rate": 1e-05,
      "loss": 0.8746,
      "step": 20
    }
  ],
  "logging_steps": 5,
  "max_steps": 22,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.043290589292134e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}