| { | |
| "best_metric": 2.574702262878418, | |
| "best_model_checkpoint": "output/ariana-grande/checkpoint-112", | |
| "epoch": 1.0, | |
| "global_step": 112, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00013652642519808018, | |
| "loss": 3.1432, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00013451892828543385, | |
| "loss": 3.0156, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00013121693198320648, | |
| "loss": 3.0148, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00012668528006706028, | |
| "loss": 2.7633, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00012101296398136228, | |
| "loss": 2.7487, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011431137524750748, | |
| "loss": 2.8109, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010671211798514472, | |
| "loss": 2.7869, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.836442450346448e-05, | |
| "loss": 2.7909, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.943222471451957e-05, | |
| "loss": 2.7036, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 8.009092691870492e-05, | |
| "loss": 2.6624, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.052397318052461e-05, | |
| "loss": 2.4311, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 6.0919236939313083e-05, | |
| "loss": 2.8251, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.146533359772823e-05, | |
| "loss": 2.6649, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 2.6419, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.3746031316088095e-05, | |
| "loss": 2.6433, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.5828599592490882e-05, | |
| "loss": 2.9171, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8751101908465757e-05, | |
| "loss": 2.5503, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2652524389394753e-05, | |
| "loss": 2.6036, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.65262937184937e-06, | |
| "loss": 2.6237, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.849603540845984e-06, | |
| "loss": 2.4549, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.3181297643383925e-06, | |
| "loss": 2.6479, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.0792048977778093e-07, | |
| "loss": 2.6504, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.574702262878418, | |
| "eval_runtime": 7.2482, | |
| "eval_samples_per_second": 22.488, | |
| "eval_steps_per_second": 2.897, | |
| "step": 112 | |
| } | |
| ], | |
| "max_steps": 112, | |
| "num_train_epochs": 1, | |
| "total_flos": 117058830336000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |