checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4667989263624694,
  "eval_steps": 250,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2333994631812347,
      "grad_norm": 1.2788289785385132,
      "learning_rate": 9.992757124875143e-05,
      "loss": 0.3573,
      "step": 250
    },
    {
      "epoch": 0.2333994631812347,
      "eval_loss": 0.18718622624874115,
      "eval_runtime": 18.4863,
      "eval_samples_per_second": 4.706,
      "eval_steps_per_second": 4.706,
      "step": 250
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 1.7301123142242432,
      "learning_rate": 9.895259863857224e-05,
      "loss": 0.1155,
      "step": 500
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.11222057044506073,
      "eval_runtime": 18.4689,
      "eval_samples_per_second": 4.711,
      "eval_steps_per_second": 4.711,
      "step": 500
    }
  ],
  "logging_steps": 250,
  "max_steps": 5355,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1.8122747112751104e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}