| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 5476, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.086924762600438e-05, | |
| "loss": 1.4977, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 8.173849525200878e-05, | |
| "loss": 1.2444, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.260774287801315e-05, | |
| "loss": 1.1926, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 6.347699050401752e-05, | |
| "loss": 1.1644, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 5.434623813002192e-05, | |
| "loss": 1.1414, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.52154857560263e-05, | |
| "loss": 1.0927, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.6084733382030684e-05, | |
| "loss": 1.0721, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.695398100803506e-05, | |
| "loss": 1.0598, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 1.7823228634039447e-05, | |
| "loss": 1.0517, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 8.692476260043827e-06, | |
| "loss": 1.0524, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 5476, | |
| "total_flos": 8.001615338274816e+16, | |
| "train_loss": 1.1475538333198987, | |
| "train_runtime": 10232.2752, | |
| "train_samples_per_second": 17.122, | |
| "train_steps_per_second": 0.535 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5476, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 8.001615338274816e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |