checkpoint-1275/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1275,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 1.6640625,
      "learning_rate": 7.633188111698531e-05,
      "loss": 0.2758,
      "step": 500
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 0.0751953125,
      "learning_rate": 1.3619137675100801e-05,
      "loss": 0.0166,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.00428734440356493,
      "eval_runtime": 92.0757,
      "eval_samples_per_second": 3.16,
      "eval_steps_per_second": 0.402,
      "step": 1275
    }
  ],
  "logging_steps": 500,
  "max_steps": 1275,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.390704736207155e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}