| { | |
| "best_metric": 2.233154535293579, | |
| "best_model_checkpoint": "output/dua-lipa/checkpoint-78", | |
| "epoch": 1.0, | |
| "global_step": 78, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00013581363873009956, | |
| "loss": 2.703, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00013171058983499535, | |
| "loss": 2.5698, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012505669320030482, | |
| "loss": 2.5811, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00011612089065075853, | |
| "loss": 2.4028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00010526435567236716, | |
| "loss": 2.5128, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.292589525111794e-05, | |
| "loss": 2.5631, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.960421386684236e-05, | |
| "loss": 2.1617, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 6.583775650849414e-05, | |
| "loss": 2.2314, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.218294542987356e-05, | |
| "loss": 2.2731, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.9191690287750474e-05, | |
| "loss": 2.0647, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.7389080673274638e-05, | |
| "loss": 2.2795, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.725216267546246e-05, | |
| "loss": 2.1056, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 2.2411, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.53040008242582e-06, | |
| "loss": 2.0633, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.001712368734975e-07, | |
| "loss": 2.0317, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.233154535293579, | |
| "eval_runtime": 5.2149, | |
| "eval_samples_per_second": 22.436, | |
| "eval_steps_per_second": 2.876, | |
| "step": 78 | |
| } | |
| ], | |
| "max_steps": 78, | |
| "num_train_epochs": 1, | |
| "total_flos": 81392467968000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |