| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "dq158/morbius/checkpoint-144", | |
| "epoch": 19.913569576490925, | |
| "eval_steps": 500, | |
| "global_step": 2880, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.4923, | |
| "eval_samples_per_second": 8.392, | |
| "eval_steps_per_second": 1.053, | |
| "eval_translation_length": 18771, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.6086, | |
| "eval_samples_per_second": 8.384, | |
| "eval_steps_per_second": 1.052, | |
| "eval_translation_length": 18771, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.4683, | |
| "eval_samples_per_second": 8.394, | |
| "eval_steps_per_second": 1.053, | |
| "eval_translation_length": 18771, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.621, | |
| "eval_samples_per_second": 8.384, | |
| "eval_steps_per_second": 1.052, | |
| "eval_translation_length": 18771, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.3833, | |
| "eval_samples_per_second": 8.4, | |
| "eval_steps_per_second": 1.054, | |
| "eval_translation_length": 18771, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.7364, | |
| "eval_samples_per_second": 8.376, | |
| "eval_steps_per_second": 1.051, | |
| "eval_translation_length": 18771, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.9033, | |
| "eval_samples_per_second": 8.364, | |
| "eval_steps_per_second": 1.05, | |
| "eval_translation_length": 18771, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 123.0241, | |
| "eval_samples_per_second": 8.356, | |
| "eval_steps_per_second": 1.049, | |
| "eval_translation_length": 18771, | |
| "step": 1157 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.4135, | |
| "eval_samples_per_second": 8.398, | |
| "eval_steps_per_second": 1.054, | |
| "eval_translation_length": 18771, | |
| "step": 1301 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.6454, | |
| "eval_samples_per_second": 8.382, | |
| "eval_steps_per_second": 1.052, | |
| "eval_translation_length": 18771, | |
| "step": 1446 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.2623, | |
| "eval_samples_per_second": 8.408, | |
| "eval_steps_per_second": 1.055, | |
| "eval_translation_length": 18771, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.4484, | |
| "eval_samples_per_second": 8.395, | |
| "eval_steps_per_second": 1.054, | |
| "eval_translation_length": 18771, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.9159, | |
| "eval_samples_per_second": 8.363, | |
| "eval_steps_per_second": 1.049, | |
| "eval_translation_length": 18771, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 13.83, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 13.99, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.5545, | |
| "eval_samples_per_second": 8.388, | |
| "eval_steps_per_second": 1.053, | |
| "eval_translation_length": 18771, | |
| "step": 2024 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.6122, | |
| "eval_samples_per_second": 8.384, | |
| "eval_steps_per_second": 1.052, | |
| "eval_translation_length": 18771, | |
| "step": 2169 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.6643, | |
| "eval_samples_per_second": 8.381, | |
| "eval_steps_per_second": 1.052, | |
| "eval_translation_length": 18771, | |
| "step": 2314 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.6275, | |
| "eval_samples_per_second": 8.383, | |
| "eval_steps_per_second": 1.052, | |
| "eval_translation_length": 18771, | |
| "step": 2458 | |
| }, | |
| { | |
| "epoch": 17.29, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.8755, | |
| "eval_samples_per_second": 8.366, | |
| "eval_steps_per_second": 1.05, | |
| "eval_translation_length": 18771, | |
| "step": 2603 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.518, | |
| "eval_samples_per_second": 8.391, | |
| "eval_steps_per_second": 1.053, | |
| "eval_translation_length": 18771, | |
| "step": 2747 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "eval_bleu": 1.0, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0, | |
| "eval_loss": NaN, | |
| "eval_precisions": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_reference_length": 18771, | |
| "eval_runtime": 122.5437, | |
| "eval_samples_per_second": 8.389, | |
| "eval_steps_per_second": 1.053, | |
| "eval_translation_length": 18771, | |
| "step": 2880 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2880, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 1.2616243364442931e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |