checkpoint-128/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 128,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7858546168958742,
      "grad_norm": 0.12602689862251282,
      "learning_rate": 0.0001234375,
      "loss": 0.8758,
      "step": 50
    },
    {
      "epoch": 1.5658153241650294,
      "grad_norm": 0.1681228131055832,
      "learning_rate": 4.5312500000000004e-05,
      "loss": 0.8327,
      "step": 100
    }
  ],
  "logging_steps": 50,
  "max_steps": 128,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0479502172841574e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}