| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.675, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.999999999999999e-07, | |
| "loss": 2.4017, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 6.505149978319905e-07, | |
| "loss": 2.0997, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.38560627359831e-07, | |
| "loss": 2.0895, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 8.01029995663981e-07, | |
| "loss": 1.8155, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 8.494850021680092e-07, | |
| "loss": 1.754, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 8.926649175053833e-07, | |
| "loss": 1.9317, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 9.256291743595375e-07, | |
| "loss": 1.7777, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 9.569069261918583e-07, | |
| "loss": 1.8519, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 9.818939136727774e-07, | |
| "loss": 1.706, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 9.991666666666667e-07, | |
| "loss": 1.7139, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "eval_oa_private_accuracy": 0.535490605427975, | |
| "eval_oa_private_loss": 2.12109375, | |
| "eval_oa_private_runtime": 1.2492, | |
| "eval_oa_private_samples_per_second": 13.608, | |
| "eval_oa_private_steps_per_second": 0.8, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 9.908333333333333e-07, | |
| "loss": 1.7749, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 9.825e-07, | |
| "loss": 1.6555, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.97, | |
| "learning_rate": 9.741666666666665e-07, | |
| "loss": 1.7188, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 9.649999999999999e-07, | |
| "loss": 1.7656, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 9.566666666666667e-07, | |
| "loss": 1.6343, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 9.474999999999999e-07, | |
| "loss": 1.6978, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 9.391666666666666e-07, | |
| "loss": 1.6376, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 9.308333333333332e-07, | |
| "loss": 1.6455, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 9.225e-07, | |
| "loss": 1.7388, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "learning_rate": 9.141666666666667e-07, | |
| "loss": 1.6082, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 7.67, | |
| "eval_oa_private_accuracy": 0.6682947547249947, | |
| "eval_oa_private_loss": 1.4609375, | |
| "eval_oa_private_runtime": 0.6912, | |
| "eval_oa_private_samples_per_second": 24.594, | |
| "eval_oa_private_steps_per_second": 1.447, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 1300, | |
| "num_train_epochs": 50, | |
| "total_flos": 4.539212744569651e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |