checkpoint-19/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9620253164556962,
  "eval_steps": 500,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 1.768328070640564,
      "learning_rate": 1.0825793454723325e-05,
      "loss": 1.4262,
      "memory/device_mem_reserved(gib)": 67.49,
      "memory/max_mem_active(gib)": 66.55,
      "memory/max_mem_allocated(gib)": 66.55,
      "step": 10
    }
  ],
  "logging_steps": 10,
  "max_steps": 19,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1607219054373765e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}