| { | |
| "best_metric": 1.6143786907196045, | |
| "best_model_checkpoint": "output/gspd/checkpoint-104", | |
| "epoch": 1.0, | |
| "global_step": 104, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00013641901727743684, | |
| "loss": 2.3995, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013409385144248624, | |
| "loss": 2.0772, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00013027744460430822, | |
| "loss": 1.9236, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012505669320030482, | |
| "loss": 1.9836, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00011855046943587908, | |
| "loss": 1.876, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00011090691466231807, | |
| "loss": 1.9239, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00010230006632035399, | |
| "loss": 1.8628, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.292589525111794e-05, | |
| "loss": 1.6981, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.299784360164853e-05, | |
| "loss": 1.7632, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.274196492316882e-05, | |
| "loss": 1.8217, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.239177711808685e-05, | |
| "loss": 1.7681, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.218294542987356e-05, | |
| "loss": 1.7394, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2347916539754844e-05, | |
| "loss": 1.8022, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.311062594741274e-05, | |
| "loss": 1.7416, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.4681399144273327e-05, | |
| "loss": 1.7103, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.725216267546246e-05, | |
| "loss": 1.7463, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.0992074130600507e-05, | |
| "loss": 1.6627, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.043670564942622e-06, | |
| "loss": 1.7961, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.519623048140383e-06, | |
| "loss": 1.7855, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 5.001712368734975e-07, | |
| "loss": 1.7266, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6143786907196045, | |
| "eval_runtime": 6.5105, | |
| "eval_samples_per_second": 23.04, | |
| "eval_steps_per_second": 2.918, | |
| "step": 104 | |
| } | |
| ], | |
| "max_steps": 104, | |
| "num_train_epochs": 1, | |
| "total_flos": 108566839296000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |