| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6650630231886847, | |
| "eval_steps": 500, | |
| "global_step": 108, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.9998119704485016e-05, | |
| "loss": 1.1733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9953027957931658e-05, | |
| "loss": 1.1282, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 1.9812553106273848e-05, | |
| "loss": 1.1452, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.957989512315489e-05, | |
| "loss": 1.1346, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.9257239692688907e-05, | |
| "loss": 1.1056, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.8847617971766577e-05, | |
| "loss": 1.0978, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.8354878114129368e-05, | |
| "loss": 1.067, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 1.7783649119241603e-05, | |
| "loss": 1.0392, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.7139297345578992e-05, | |
| "loss": 1.0536, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.6427876096865394e-05, | |
| "loss": 1.0547, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.5656068754865388e-05, | |
| "loss": 1.0304, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.4831125992966386e-05, | |
| "loss": 1.0428, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.396079766039157e-05, | |
| "loss": 1.0502, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 1.3053259976951134e-05, | |
| "loss": 1.0294, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.211703872229411e-05, | |
| "loss": 1.0313, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.1160929141252303e-05, | |
| "loss": 1.0468, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.0193913317718245e-05, | |
| "loss": 1.0264, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.225075793280693e-06, | |
| "loss": 1.0222, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 1.0264, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 7.3182738723936255e-06, | |
| "loss": 1.0263, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.3982227519528986e-06, | |
| "loss": 1.051, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 5.512008197995379e-06, | |
| "loss": 1.0313, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.025382399559021, | |
| "eval_runtime": 12686.0816, | |
| "eval_samples_per_second": 1.822, | |
| "eval_steps_per_second": 0.911, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "step": 108, | |
| "total_flos": 1.227710764417024e+18, | |
| "train_loss": 1.0669225134231426, | |
| "train_runtime": 50855.7644, | |
| "train_samples_per_second": 0.409, | |
| "train_steps_per_second": 0.003 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 162, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 1.227710764417024e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |