| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5, |
| "eval_steps": 3, |
| "global_step": 57, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.008771929824561403, |
| "grad_norm": 0.0, |
| "learning_rate": 0.0, |
| "loss": 2.0802, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.02631578947368421, |
| "grad_norm": 0.0, |
| "learning_rate": 0.0, |
| "loss": 2.0494, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.05263157894736842, |
| "grad_norm": 2.4723047601512564, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 2.0771, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.07894736842105263, |
| "grad_norm": 2.106898891910819, |
| "learning_rate": 1.8e-06, |
| "loss": 2.0245, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.10526315789473684, |
| "grad_norm": 0.8386924455230856, |
| "learning_rate": 2.9432692307692307e-06, |
| "loss": 2.0568, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.13157894736842105, |
| "grad_norm": 1.1653346026055935, |
| "learning_rate": 2.7730769230769233e-06, |
| "loss": 2.0326, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.15789473684210525, |
| "grad_norm": 1.5574035133942843, |
| "learning_rate": 2.6028846153846155e-06, |
| "loss": 2.0396, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.18421052631578946, |
| "grad_norm": 0.9621595083981531, |
| "learning_rate": 2.4326923076923077e-06, |
| "loss": 2.0336, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.21052631578947367, |
| "grad_norm": 0.9955527535333841, |
| "learning_rate": 2.2625e-06, |
| "loss": 1.9571, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.23684210526315788, |
| "grad_norm": 0.7832834940985813, |
| "learning_rate": 2.092307692307692e-06, |
| "loss": 1.9792, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.2631578947368421, |
| "grad_norm": 0.7516778470264893, |
| "learning_rate": 1.9221153846153848e-06, |
| "loss": 2.015, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2894736842105263, |
| "grad_norm": 1.4307615046721256, |
| "learning_rate": 1.7519230769230768e-06, |
| "loss": 1.9845, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.3157894736842105, |
| "grad_norm": 0.7110172377205767, |
| "learning_rate": 1.581730769230769e-06, |
| "loss": 1.974, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.34210526315789475, |
| "grad_norm": 0.9472807779995442, |
| "learning_rate": 1.4115384615384616e-06, |
| "loss": 1.9848, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.3684210526315789, |
| "grad_norm": 0.6928271721519345, |
| "learning_rate": 1.2413461538461538e-06, |
| "loss": 1.9453, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.39473684210526316, |
| "grad_norm": 0.9136097540650397, |
| "learning_rate": 1.071153846153846e-06, |
| "loss": 1.9987, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.42105263157894735, |
| "grad_norm": 0.6671789202988747, |
| "learning_rate": 9.009615384615385e-07, |
| "loss": 2.0054, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.4473684210526316, |
| "grad_norm": 1.2888605208856772, |
| "learning_rate": 7.307692307692307e-07, |
| "loss": 1.9706, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.47368421052631576, |
| "grad_norm": 0.9597150120115726, |
| "learning_rate": 6.740384615384617e-07, |
| "loss": 1.9874, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.7428542672176522, |
| "learning_rate": 5.038461538461539e-07, |
| "loss": 2.0058, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.5, |
| "step": 57, |
| "total_flos": 227154377834496.0, |
| "train_loss": 2.006924344782244, |
| "train_runtime": 17818.5287, |
| "train_samples_per_second": 0.409, |
| "train_steps_per_second": 0.003 |
| } |
| ], |
| "logging_steps": 3, |
| "max_steps": 57, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 12, |
| "total_flos": 227154377834496.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
