| { | |
| "best_metric": 2.331069231033325, | |
| "best_model_checkpoint": "dq158/morbius/checkpoint-13150", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 13150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.8098859315589354e-05, | |
| "loss": 2.6388, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.619771863117871e-05, | |
| "loss": 2.6102, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.4296577946768064e-05, | |
| "loss": 2.6153, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.2395437262357415e-05, | |
| "loss": 2.6423, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.0494296577946774e-05, | |
| "loss": 2.6085, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_bleu": 0.039845626314436104, | |
| "eval_brevity_penalty": 1.0, | |
| "eval_length_ratio": 1.0584780223326664, | |
| "eval_loss": 2.3793318271636963, | |
| "eval_precisions": [ | |
| 0.11484440108136675, | |
| 0.05086452177719413, | |
| 0.022402389588222743, | |
| 0.019262093750807972 | |
| ], | |
| "eval_reference_length": 46479, | |
| "eval_runtime": 201.6056, | |
| "eval_samples_per_second": 17.395, | |
| "eval_steps_per_second": 1.453, | |
| "eval_translation_length": 49197, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.8593155893536125e-05, | |
| "loss": 2.529, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 3.669201520912548e-05, | |
| "loss": 2.5228, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3.479087452471483e-05, | |
| "loss": 2.4726, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 3.288973384030418e-05, | |
| "loss": 2.5319, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.098859315589354e-05, | |
| "loss": 2.5537, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_bleu": 0.04511134441808281, | |
| "eval_brevity_penalty": 0.9857642100346898, | |
| "eval_length_ratio": 0.98586458400568, | |
| "eval_loss": 2.3537790775299072, | |
| "eval_precisions": [ | |
| 0.12435074854873206, | |
| 0.053338059789672695, | |
| 0.02736549165120594, | |
| 0.024163621427155037 | |
| ], | |
| "eval_reference_length": 46479, | |
| "eval_runtime": 200.2247, | |
| "eval_samples_per_second": 17.515, | |
| "eval_steps_per_second": 1.463, | |
| "eval_translation_length": 45822, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 2.908745247148289e-05, | |
| "loss": 2.4999, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 2.7186311787072245e-05, | |
| "loss": 2.4502, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 2.5285171102661596e-05, | |
| "loss": 2.4936, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 2.338403041825095e-05, | |
| "loss": 2.4053, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.1482889733840306e-05, | |
| "loss": 2.427, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_bleu": 0.047839363303602896, | |
| "eval_brevity_penalty": 0.9798114045807085, | |
| "eval_length_ratio": 0.9800124787538458, | |
| "eval_loss": 2.3411617279052734, | |
| "eval_precisions": [ | |
| 0.12566410537870473, | |
| 0.05610922151130985, | |
| 0.029971974257836827, | |
| 0.026891236083357122 | |
| ], | |
| "eval_reference_length": 46479, | |
| "eval_runtime": 200.7411, | |
| "eval_samples_per_second": 17.47, | |
| "eval_steps_per_second": 1.46, | |
| "eval_translation_length": 45550, | |
| "step": 7890 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 1.958174904942966e-05, | |
| "loss": 2.4461, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 1.7680608365019013e-05, | |
| "loss": 2.4042, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "learning_rate": 1.5779467680608364e-05, | |
| "loss": 2.4027, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.387832699619772e-05, | |
| "loss": 2.3927, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.1977186311787073e-05, | |
| "loss": 2.3733, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.0076045627376426e-05, | |
| "loss": 2.3716, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_bleu": 0.04869515928692814, | |
| "eval_brevity_penalty": 0.9823324657661657, | |
| "eval_length_ratio": 0.9824867144301728, | |
| "eval_loss": 2.3347413539886475, | |
| "eval_precisions": [ | |
| 0.12663965838169275, | |
| 0.0574505431946487, | |
| 0.030477866031926728, | |
| 0.027230821761893922 | |
| ], | |
| "eval_reference_length": 46479, | |
| "eval_runtime": 200.6451, | |
| "eval_samples_per_second": 17.479, | |
| "eval_steps_per_second": 1.46, | |
| "eval_translation_length": 45665, | |
| "step": 10520 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 8.17490494296578e-06, | |
| "loss": 2.3618, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 6.273764258555133e-06, | |
| "loss": 2.3667, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "learning_rate": 4.3726235741444865e-06, | |
| "loss": 2.377, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.4714828897338406e-06, | |
| "loss": 2.346, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 5.70342205323194e-07, | |
| "loss": 2.3494, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_bleu": 0.04900460577934908, | |
| "eval_brevity_penalty": 0.9780979152370445, | |
| "eval_length_ratio": 0.978334301512511, | |
| "eval_loss": 2.331069231033325, | |
| "eval_precisions": [ | |
| 0.12658339197748064, | |
| 0.058000714881448825, | |
| 0.031020853918560506, | |
| 0.0276665140764477 | |
| ], | |
| "eval_reference_length": 46479, | |
| "eval_runtime": 201.3997, | |
| "eval_samples_per_second": 17.413, | |
| "eval_steps_per_second": 1.455, | |
| "eval_translation_length": 45472, | |
| "step": 13150 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 13150, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 1.080547102162944e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |