| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.0, | |
| "eval_steps": 500, | |
| "global_step": 323078, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.1666594444685182e-09, | |
| "loss": 0.0003, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.000649997833341e-06, | |
| "loss": 0.0017, | |
| "step": 2308 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.0001299995666681e-05, | |
| "loss": 0.0017, | |
| "step": 4616 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5001949993500023e-05, | |
| "loss": 0.0016, | |
| "step": 6924 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.0002599991333363e-05, | |
| "loss": 0.0016, | |
| "step": 9232 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5003249989166704e-05, | |
| "loss": 0.0016, | |
| "step": 11540 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.0003899987000046e-05, | |
| "loss": 0.0015, | |
| "step": 13848 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.5004549984833384e-05, | |
| "loss": 0.0016, | |
| "step": 16156 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.0005199982666725e-05, | |
| "loss": 0.0017, | |
| "step": 18464 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.500584998050007e-05, | |
| "loss": 0.0017, | |
| "step": 20772 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.00893497932702303, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 18.8658, | |
| "eval_samples_per_second": 13.676, | |
| "eval_steps_per_second": 0.954, | |
| "step": 23077 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.000649997833341e-05, | |
| "loss": 0.0018, | |
| "step": 23080 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.500714997616675e-05, | |
| "loss": 0.0017, | |
| "step": 25388 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.000779997400009e-05, | |
| "loss": 0.0017, | |
| "step": 27696 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.500844997183343e-05, | |
| "loss": 0.0017, | |
| "step": 30004 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.000909996966677e-05, | |
| "loss": 0.0017, | |
| "step": 32312 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.50097499675001e-05, | |
| "loss": 0.0017, | |
| "step": 34620 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.001039996533345e-05, | |
| "loss": 0.0018, | |
| "step": 36928 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.501104996316679e-05, | |
| "loss": 0.0017, | |
| "step": 39236 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.001169996100013e-05, | |
| "loss": 0.0018, | |
| "step": 41544 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 9.501234995883348e-05, | |
| "loss": 0.0019, | |
| "step": 43852 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.008421082980930805, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 18.622, | |
| "eval_samples_per_second": 13.855, | |
| "eval_steps_per_second": 0.967, | |
| "step": 46154 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.999855556037036e-05, | |
| "loss": 0.0018, | |
| "step": 46160 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.944292778283332e-05, | |
| "loss": 0.0019, | |
| "step": 48468 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.888730000529628e-05, | |
| "loss": 0.0018, | |
| "step": 50776 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 9.833167222775925e-05, | |
| "loss": 0.0019, | |
| "step": 53084 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.777604445022221e-05, | |
| "loss": 0.0021, | |
| "step": 55392 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.722041667268516e-05, | |
| "loss": 0.0021, | |
| "step": 57700 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.666478889514812e-05, | |
| "loss": 0.0021, | |
| "step": 60008 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.610916111761109e-05, | |
| "loss": 0.002, | |
| "step": 62316 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.555353334007405e-05, | |
| "loss": 0.0022, | |
| "step": 64624 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.499790556253701e-05, | |
| "loss": 0.002, | |
| "step": 66932 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.008709550835192204, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 17.0366, | |
| "eval_samples_per_second": 15.144, | |
| "eval_steps_per_second": 1.057, | |
| "step": 69231 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.444227778499997e-05, | |
| "loss": 0.0022, | |
| "step": 69240 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 9.388665000746294e-05, | |
| "loss": 0.0018, | |
| "step": 71548 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.33310222299259e-05, | |
| "loss": 0.0019, | |
| "step": 73856 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 9.277539445238886e-05, | |
| "loss": 0.0019, | |
| "step": 76164 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.221976667485182e-05, | |
| "loss": 0.0019, | |
| "step": 78472 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 9.166413889731479e-05, | |
| "loss": 0.0018, | |
| "step": 80780 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 9.110851111977775e-05, | |
| "loss": 0.002, | |
| "step": 83088 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 9.055288334224071e-05, | |
| "loss": 0.0019, | |
| "step": 85396 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 8.999725556470368e-05, | |
| "loss": 0.002, | |
| "step": 87704 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 8.944162778716664e-05, | |
| "loss": 0.0021, | |
| "step": 90012 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.011967115104198456, | |
| "eval_max_distance": 4, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 18.1135, | |
| "eval_samples_per_second": 14.243, | |
| "eval_steps_per_second": 0.994, | |
| "step": 92308 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.88860000096296e-05, | |
| "loss": 0.0021, | |
| "step": 92320 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 8.833037223209256e-05, | |
| "loss": 0.0018, | |
| "step": 94628 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 8.777474445455553e-05, | |
| "loss": 0.0018, | |
| "step": 96936 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 8.721911667701849e-05, | |
| "loss": 0.0018, | |
| "step": 99244 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 8.666348889948145e-05, | |
| "loss": 0.0018, | |
| "step": 101552 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 8.610786112194442e-05, | |
| "loss": 0.0017, | |
| "step": 103860 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 8.555223334440738e-05, | |
| "loss": 0.0019, | |
| "step": 106168 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 8.499660556687034e-05, | |
| "loss": 0.0019, | |
| "step": 108476 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 8.44409777893333e-05, | |
| "loss": 0.002, | |
| "step": 110784 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 8.388535001179625e-05, | |
| "loss": 0.0019, | |
| "step": 113092 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.010002830997109413, | |
| "eval_max_distance": 4, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 17.3823, | |
| "eval_samples_per_second": 14.843, | |
| "eval_steps_per_second": 1.036, | |
| "step": 115385 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.332972223425922e-05, | |
| "loss": 0.0019, | |
| "step": 115400 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 8.277409445672218e-05, | |
| "loss": 0.0017, | |
| "step": 117708 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 8.221846667918514e-05, | |
| "loss": 0.0017, | |
| "step": 120016 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 8.16628389016481e-05, | |
| "loss": 0.0017, | |
| "step": 122324 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 8.110721112411107e-05, | |
| "loss": 0.0017, | |
| "step": 124632 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 8.055158334657403e-05, | |
| "loss": 0.0018, | |
| "step": 126940 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 7.999595556903699e-05, | |
| "loss": 0.0017, | |
| "step": 129248 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 7.944032779149996e-05, | |
| "loss": 0.0017, | |
| "step": 131556 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 7.888470001396292e-05, | |
| "loss": 0.0017, | |
| "step": 133864 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 7.832907223642588e-05, | |
| "loss": 0.0018, | |
| "step": 136172 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.011129369959235191, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 17.0083, | |
| "eval_samples_per_second": 15.169, | |
| "eval_steps_per_second": 1.058, | |
| "step": 138462 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.777344445888884e-05, | |
| "loss": 0.0018, | |
| "step": 138480 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 7.721781668135181e-05, | |
| "loss": 0.0016, | |
| "step": 140788 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 7.666218890381477e-05, | |
| "loss": 0.0016, | |
| "step": 143096 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 7.610656112627773e-05, | |
| "loss": 0.0017, | |
| "step": 145404 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 7.55509333487407e-05, | |
| "loss": 0.0017, | |
| "step": 147712 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 7.499530557120366e-05, | |
| "loss": 0.0017, | |
| "step": 150020 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 7.443967779366662e-05, | |
| "loss": 0.0016, | |
| "step": 152328 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 7.388405001612958e-05, | |
| "loss": 0.0016, | |
| "step": 154636 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 7.332842223859255e-05, | |
| "loss": 0.0017, | |
| "step": 156944 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 7.277279446105551e-05, | |
| "loss": 0.0017, | |
| "step": 159252 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.007010257337242365, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 16.7205, | |
| "eval_samples_per_second": 15.43, | |
| "eval_steps_per_second": 1.077, | |
| "step": 161539 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.221716668351847e-05, | |
| "loss": 0.0017, | |
| "step": 161560 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 7.166153890598143e-05, | |
| "loss": 0.0015, | |
| "step": 163868 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 7.11059111284444e-05, | |
| "loss": 0.0015, | |
| "step": 166176 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 7.055028335090735e-05, | |
| "loss": 0.0015, | |
| "step": 168484 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 6.999465557337031e-05, | |
| "loss": 0.0015, | |
| "step": 170792 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 6.943902779583327e-05, | |
| "loss": 0.0015, | |
| "step": 173100 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 6.888340001829624e-05, | |
| "loss": 0.0016, | |
| "step": 175408 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 6.83277722407592e-05, | |
| "loss": 0.0015, | |
| "step": 177716 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 6.777214446322216e-05, | |
| "loss": 0.0016, | |
| "step": 180024 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 6.721651668568512e-05, | |
| "loss": 0.0017, | |
| "step": 182332 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.01417616382241249, | |
| "eval_max_distance": 4, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 17.4179, | |
| "eval_samples_per_second": 14.812, | |
| "eval_steps_per_second": 1.033, | |
| "step": 184616 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.666088890814809e-05, | |
| "loss": 0.0016, | |
| "step": 184640 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 6.610526113061105e-05, | |
| "loss": 0.0014, | |
| "step": 186948 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 6.554963335307401e-05, | |
| "loss": 0.0014, | |
| "step": 189256 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 6.499400557553698e-05, | |
| "loss": 0.0014, | |
| "step": 191564 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 6.443837779799994e-05, | |
| "loss": 0.0015, | |
| "step": 193872 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 6.38827500204629e-05, | |
| "loss": 0.0014, | |
| "step": 196180 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 6.332712224292586e-05, | |
| "loss": 0.0014, | |
| "step": 198488 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 6.277149446538883e-05, | |
| "loss": 0.0015, | |
| "step": 200796 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.221586668785179e-05, | |
| "loss": 0.0015, | |
| "step": 203104 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 6.166023891031475e-05, | |
| "loss": 0.0014, | |
| "step": 205412 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.011828480288386345, | |
| "eval_max_distance": 4, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 17.0049, | |
| "eval_samples_per_second": 15.172, | |
| "eval_steps_per_second": 1.059, | |
| "step": 207693 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.110461113277771e-05, | |
| "loss": 0.0015, | |
| "step": 207720 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 6.054898335524067e-05, | |
| "loss": 0.0014, | |
| "step": 210028 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 5.9993355577703634e-05, | |
| "loss": 0.0013, | |
| "step": 212336 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 5.9437727800166596e-05, | |
| "loss": 0.0014, | |
| "step": 214644 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 5.888210002262956e-05, | |
| "loss": 0.0014, | |
| "step": 216952 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 5.832647224509252e-05, | |
| "loss": 0.0013, | |
| "step": 219260 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 5.7770844467555485e-05, | |
| "loss": 0.0013, | |
| "step": 221568 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 5.721521669001845e-05, | |
| "loss": 0.0013, | |
| "step": 223876 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 5.665958891248141e-05, | |
| "loss": 0.0014, | |
| "step": 226184 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 5.610396113494437e-05, | |
| "loss": 0.0014, | |
| "step": 228492 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.011539922095835209, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 17.0363, | |
| "eval_samples_per_second": 15.144, | |
| "eval_steps_per_second": 1.057, | |
| "step": 230770 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.5548333357407336e-05, | |
| "loss": 0.0015, | |
| "step": 230800 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 5.49927055798703e-05, | |
| "loss": 0.0013, | |
| "step": 233108 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 5.443707780233326e-05, | |
| "loss": 0.0012, | |
| "step": 235416 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 5.388145002479622e-05, | |
| "loss": 0.0013, | |
| "step": 237724 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 5.332582224725918e-05, | |
| "loss": 0.0013, | |
| "step": 240032 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 5.277019446972214e-05, | |
| "loss": 0.0014, | |
| "step": 242340 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 5.2214566692185106e-05, | |
| "loss": 0.0013, | |
| "step": 244648 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 5.165893891464807e-05, | |
| "loss": 0.0013, | |
| "step": 246956 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 5.110331113711103e-05, | |
| "loss": 0.0013, | |
| "step": 249264 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 5.0547683359573994e-05, | |
| "loss": 0.0013, | |
| "step": 251572 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.011254764162003994, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 16.9212, | |
| "eval_samples_per_second": 15.247, | |
| "eval_steps_per_second": 1.064, | |
| "step": 253847 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.999205558203695e-05, | |
| "loss": 0.0012, | |
| "step": 253880 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 4.943642780449991e-05, | |
| "loss": 0.0012, | |
| "step": 256188 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 4.8880800026962876e-05, | |
| "loss": 0.0012, | |
| "step": 258496 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 4.832517224942584e-05, | |
| "loss": 0.0013, | |
| "step": 260804 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 4.77695444718888e-05, | |
| "loss": 0.0012, | |
| "step": 263112 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 4.7213916694351764e-05, | |
| "loss": 0.0012, | |
| "step": 265420 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 4.665828891681473e-05, | |
| "loss": 0.0012, | |
| "step": 267728 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 4.610266113927768e-05, | |
| "loss": 0.0013, | |
| "step": 270036 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 4.5547033361740646e-05, | |
| "loss": 0.0012, | |
| "step": 272344 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 4.499140558420361e-05, | |
| "loss": 0.0012, | |
| "step": 274652 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.012018387205898762, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 16.9292, | |
| "eval_samples_per_second": 15.24, | |
| "eval_steps_per_second": 1.063, | |
| "step": 276924 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.443577780666657e-05, | |
| "loss": 0.0013, | |
| "step": 276960 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 4.3880150029129535e-05, | |
| "loss": 0.0012, | |
| "step": 279268 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 4.33245222515925e-05, | |
| "loss": 0.0011, | |
| "step": 281576 | |
| }, | |
| { | |
| "epoch": 12.3, | |
| "learning_rate": 4.276889447405546e-05, | |
| "loss": 0.0012, | |
| "step": 283884 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 4.221326669651842e-05, | |
| "loss": 0.0012, | |
| "step": 286192 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 4.1657638918981386e-05, | |
| "loss": 0.0012, | |
| "step": 288500 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 4.110201114144435e-05, | |
| "loss": 0.0011, | |
| "step": 290808 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 4.054638336390731e-05, | |
| "loss": 0.0011, | |
| "step": 293116 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.9990755586370274e-05, | |
| "loss": 0.0012, | |
| "step": 295424 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 3.943512780883323e-05, | |
| "loss": 0.0012, | |
| "step": 297732 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.013248566538095474, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 16.6859, | |
| "eval_samples_per_second": 15.462, | |
| "eval_steps_per_second": 1.079, | |
| "step": 300001 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.887950003129619e-05, | |
| "loss": 0.0012, | |
| "step": 300040 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 3.8323872253759156e-05, | |
| "loss": 0.0011, | |
| "step": 302348 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 3.776824447622212e-05, | |
| "loss": 0.0011, | |
| "step": 304656 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 3.721261669868508e-05, | |
| "loss": 0.0011, | |
| "step": 306964 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 3.6656988921148044e-05, | |
| "loss": 0.0012, | |
| "step": 309272 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 3.954328163153008e-06, | |
| "loss": 0.0012, | |
| "step": 311580 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3.16057364927606e-06, | |
| "loss": 0.0011, | |
| "step": 313888 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 2.3668191353991126e-06, | |
| "loss": 0.0011, | |
| "step": 316196 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 1.5730646215221654e-06, | |
| "loss": 0.001, | |
| "step": 318504 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "learning_rate": 7.79310107645218e-07, | |
| "loss": 0.001, | |
| "step": 320812 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.011406470090150833, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 18.3924, | |
| "eval_samples_per_second": 14.028, | |
| "eval_steps_per_second": 0.979, | |
| "step": 323078 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "step": 323078, | |
| "total_flos": 8.183655700394803e+16, | |
| "train_loss": 4.6522844528394624e-05, | |
| "train_runtime": 1031.7354, | |
| "train_samples_per_second": 4696.956, | |
| "train_steps_per_second": 313.14 | |
| } | |
| ], | |
| "logging_steps": 2308, | |
| "max_steps": 323078, | |
| "num_train_epochs": 14, | |
| "save_steps": 4616, | |
| "total_flos": 8.183655700394803e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |