checkpoint-750/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7001983895437041,
  "eval_steps": 250,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2333994631812347,
      "grad_norm": 3.692305564880371,
      "learning_rate": 8.996514402527381e-05,
      "loss": 0.4543,
      "step": 250
    },
    {
      "epoch": 0.2333994631812347,
      "eval_loss": 0.2949160635471344,
      "eval_runtime": 27.88,
      "eval_samples_per_second": 3.121,
      "eval_steps_per_second": 3.121,
      "step": 250
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 6.010829925537109,
      "learning_rate": 5.843391598090062e-05,
      "loss": 0.2489,
      "step": 500
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.24741260707378387,
      "eval_runtime": 27.9132,
      "eval_samples_per_second": 3.117,
      "eval_steps_per_second": 3.117,
      "step": 500
    },
    {
      "epoch": 0.7001983895437041,
      "grad_norm": 3.6985373497009277,
      "learning_rate": 2.2300178981718183e-05,
      "loss": 0.2205,
      "step": 750
    },
    {
      "epoch": 0.7001983895437041,
      "eval_loss": 0.2210255116224289,
      "eval_runtime": 27.8815,
      "eval_samples_per_second": 3.12,
      "eval_steps_per_second": 3.12,
      "step": 750
    }
  ],
  "logging_steps": 250,
  "max_steps": 1071,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.317360457912525e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}