| { | |
| "best_metric": 1.6192371845245361, | |
| "best_model_checkpoint": "output/gspd/checkpoint-102", | |
| "epoch": 1.0, | |
| "global_step": 102, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00013638815138477438, | |
| "loss": 1.4771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00013397182122930294, | |
| "loss": 1.6873, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0001300082017869573, | |
| "loss": 1.5944, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001245911081876368, | |
| "loss": 1.563, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001178487579222207, | |
| "loss": 1.5602, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00010994073605561706, | |
| "loss": 1.5302, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00010105421799895028, | |
| "loss": 1.5424, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.139953924430467e-05, | |
| "loss": 1.6088, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 8.120521692221671e-05, | |
| "loss": 1.6842, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.071254101695329e-05, | |
| "loss": 1.5729, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 6.0169863260400656e-05, | |
| "loss": 1.4031, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.9826718881055135e-05, | |
| "loss": 1.4452, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.992792034076664e-05, | |
| "loss": 1.6059, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.0707762854909365e-05, | |
| "loss": 1.4848, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.2384478845846205e-05, | |
| "loss": 1.531, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.515507258753902e-05, | |
| "loss": 1.4834, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387498e-06, | |
| "loss": 1.4458, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 4.6324050628612214e-06, | |
| "loss": 1.5666, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.588205401691401e-06, | |
| "loss": 1.5073, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.3011164863877445e-07, | |
| "loss": 1.4195, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.6192371845245361, | |
| "eval_runtime": 3.8612, | |
| "eval_samples_per_second": 44.287, | |
| "eval_steps_per_second": 5.698, | |
| "step": 102 | |
| } | |
| ], | |
| "max_steps": 204, | |
| "num_train_epochs": 2, | |
| "total_flos": 105823272960000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |