pradachan's picture
Upload folder using huggingface_hub
f71c233 verified
{"shakespeare_char": {"means": {"final_train_loss_mean": 0.7984780073165894, "best_val_loss_mean": 1.463551680246989, "total_train_time_mean": 79.24612506230672, "avg_inference_tokens_per_second_mean": 617.9132836431749}, "stderrs": {"final_train_loss_stderr": 0.002017979354479217, "best_val_loss_stderr": 0.0007040510436544415, "total_train_time_stderr": 0.44941569393348185, "avg_inference_tokens_per_second_stderr": 1.9699288733866238}, "final_info_dict": {"final_train_loss": [0.8041762113571167, 0.7900950908660889, 0.8011627197265625], "best_val_loss": [1.4658539295196533, 1.4607523679733276, 1.4640487432479858], "total_train_time": [80.82218813896179, 77.52875280380249, 79.38743424415588], "avg_inference_tokens_per_second": [609.8204108206697, 623.7673217674162, 620.1521183414384]}}, "enwik8": {"means": {"final_train_loss_mean": 0.925983190536499, "best_val_loss_mean": 0.9917866587638855, "total_train_time_mean": 852.1484353542328, "avg_inference_tokens_per_second_mean": 605.0617699125265}, "stderrs": {"final_train_loss_stderr": 0.0, "best_val_loss_stderr": 0.0, "total_train_time_stderr": 0.0, "avg_inference_tokens_per_second_stderr": 0.0}, "final_info_dict": {"final_train_loss": [0.925983190536499], "best_val_loss": [0.9917866587638855], "total_train_time": [852.1484353542328], "avg_inference_tokens_per_second": [605.0617699125265]}}, "text8": {"means": {"final_train_loss_mean": 0.9827583432197571, "best_val_loss_mean": 0.9615200161933899, "total_train_time_mean": 846.4471461772919, "avg_inference_tokens_per_second_mean": 613.2623906747798}, "stderrs": {"final_train_loss_stderr": 0.0, "best_val_loss_stderr": 0.0, "total_train_time_stderr": 0.0, "avg_inference_tokens_per_second_stderr": 0.0}, "final_info_dict": {"final_train_loss": [0.9827583432197571], "best_val_loss": [0.9615200161933899], "total_train_time": [846.4471461772919], "avg_inference_tokens_per_second": [613.2623906747798]}}}