{
  "best_metric": 0.6763165593147278,
  "best_model_checkpoint": "../outputs/phi35/amazon_esci_jp/Phi-3.5_CPT_AmazonESCI-v0.2.2/checkpoint-100",
  "epoch": 0.18867924528301888,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 2.3407922010201876,
      "learning_rate": 9.931994653268037e-07,
      "loss": 5.5516,
      "step": 100
    },
    {
      "epoch": 0.18867924528301888,
      "eval_loss": 0.6763165593147278,
      "eval_runtime": 368.4518,
      "eval_samples_per_second": 184.046,
      "eval_steps_per_second": 0.361,
      "step": 100
    }
  ],
  "logging_steps": 100,
  "max_steps": 1590,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 62813896704000.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}