|
{ |
|
"best_metric": 0.7258342522680835, |
|
"best_model_checkpoint": "./checkpoints/clip-stage1-10240/checkpoint-100", |
|
"epoch": 0.4985044865403789, |
|
"global_step": 3000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 2e-06, |
|
"loss": 3.6467, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4e-06, |
|
"loss": 2.3745, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 6e-06, |
|
"loss": 1.9228, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 8e-06, |
|
"loss": 1.6728, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 9.999999999999999e-06, |
|
"loss": 1.5235, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.2e-05, |
|
"loss": 1.4338, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 1.4e-05, |
|
"loss": 1.3564, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.6e-05, |
|
"loss": 1.2923, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.8e-05, |
|
"loss": 1.2428, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 1.9999999999999998e-05, |
|
"loss": 1.2069, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.2e-05, |
|
"loss": 1.1654, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.4e-05, |
|
"loss": 1.129, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 2.6000000000000002e-05, |
|
"loss": 1.095, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.8e-05, |
|
"loss": 1.0813, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 3e-05, |
|
"loss": 1.0522, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 2.9894736842105264e-05, |
|
"loss": 1.0212, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 2.9789473684210527e-05, |
|
"loss": 0.9983, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 2.968421052631579e-05, |
|
"loss": 0.9816, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 2.957894736842105e-05, |
|
"loss": 0.9694, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 2.9473684210526314e-05, |
|
"loss": 0.9517, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 2.936842105263158e-05, |
|
"loss": 0.9385, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 2.9263157894736844e-05, |
|
"loss": 0.9146, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.9157894736842107e-05, |
|
"loss": 0.9091, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.905263157894737e-05, |
|
"loss": 0.8921, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.8947368421052634e-05, |
|
"loss": 0.8871, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 2.8842105263157897e-05, |
|
"loss": 0.8704, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 2.8736842105263157e-05, |
|
"loss": 0.8601, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 2.863157894736842e-05, |
|
"loss": 0.8561, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 2.8526315789473683e-05, |
|
"loss": 0.8481, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 2.8421052631578946e-05, |
|
"loss": 0.8323, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 2.8315789473684213e-05, |
|
"loss": 0.8285, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 2.8210526315789476e-05, |
|
"loss": 0.8279, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 2.810526315789474e-05, |
|
"loss": 0.8166, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 2.8e-05, |
|
"loss": 0.8072, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2.7894736842105263e-05, |
|
"loss": 0.7981, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2.7789473684210526e-05, |
|
"loss": 0.8, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 2.768421052631579e-05, |
|
"loss": 0.7873, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 2.7578947368421053e-05, |
|
"loss": 0.7805, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 2.7473684210526316e-05, |
|
"loss": 0.7772, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 2.736842105263158e-05, |
|
"loss": 0.7683, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 2.7263157894736846e-05, |
|
"loss": 0.7711, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 2.7157894736842106e-05, |
|
"loss": 0.7627, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 2.705263157894737e-05, |
|
"loss": 0.7543, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 2.6947368421052632e-05, |
|
"loss": 0.7538, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 2.6842105263157896e-05, |
|
"loss": 0.7468, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 2.673684210526316e-05, |
|
"loss": 0.7376, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 2.6631578947368422e-05, |
|
"loss": 0.7427, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 2.6526315789473685e-05, |
|
"loss": 0.7305, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 2.6421052631578945e-05, |
|
"loss": 0.727, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 2.631578947368421e-05, |
|
"loss": 0.7305, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 2.6210526315789475e-05, |
|
"loss": 0.7243, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 2.610526315789474e-05, |
|
"loss": 0.7189, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 2.6000000000000002e-05, |
|
"loss": 0.721, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 2.5894736842105265e-05, |
|
"loss": 0.7164, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 2.578947368421053e-05, |
|
"loss": 0.7171, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 2.568421052631579e-05, |
|
"loss": 0.7082, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 2.557894736842105e-05, |
|
"loss": 0.6998, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 2.5473684210526315e-05, |
|
"loss": 0.7025, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 2.5368421052631578e-05, |
|
"loss": 0.6959, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 2.526315789473684e-05, |
|
"loss": 0.6996, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 2.5157894736842108e-05, |
|
"loss": 0.6923, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 2.505263157894737e-05, |
|
"loss": 0.6906, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 2.4947368421052635e-05, |
|
"loss": 0.6894, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 2.4842105263157894e-05, |
|
"loss": 0.6838, |
|
"step": 1280 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 2.4736842105263158e-05, |
|
"loss": 0.6803, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 2.463157894736842e-05, |
|
"loss": 0.68, |
|
"step": 1320 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 2.4526315789473684e-05, |
|
"loss": 0.6734, |
|
"step": 1340 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 2.4421052631578948e-05, |
|
"loss": 0.6732, |
|
"step": 1360 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 2.431578947368421e-05, |
|
"loss": 0.673, |
|
"step": 1380 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 2.4210526315789474e-05, |
|
"loss": 0.6675, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 2.410526315789474e-05, |
|
"loss": 0.6689, |
|
"step": 1420 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 2.4e-05, |
|
"loss": 0.6671, |
|
"step": 1440 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 2.3894736842105264e-05, |
|
"loss": 0.6666, |
|
"step": 1460 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 2.3789473684210527e-05, |
|
"loss": 0.6582, |
|
"step": 1480 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 2.368421052631579e-05, |
|
"loss": 0.6541, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 2.3578947368421054e-05, |
|
"loss": 0.6621, |
|
"step": 1520 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 2.3473684210526317e-05, |
|
"loss": 0.6549, |
|
"step": 1540 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 2.336842105263158e-05, |
|
"loss": 0.6503, |
|
"step": 1560 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 2.326315789473684e-05, |
|
"loss": 0.6492, |
|
"step": 1580 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 2.3157894736842103e-05, |
|
"loss": 0.6498, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 2.3052631578947367e-05, |
|
"loss": 0.6523, |
|
"step": 1620 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 2.2947368421052633e-05, |
|
"loss": 0.6443, |
|
"step": 1640 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 2.2842105263157897e-05, |
|
"loss": 0.6442, |
|
"step": 1660 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 2.273684210526316e-05, |
|
"loss": 0.6459, |
|
"step": 1680 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 2.2631578947368423e-05, |
|
"loss": 0.6426, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 2.2526315789473686e-05, |
|
"loss": 0.636, |
|
"step": 1720 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 2.2421052631578946e-05, |
|
"loss": 0.6365, |
|
"step": 1740 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 2.231578947368421e-05, |
|
"loss": 0.636, |
|
"step": 1760 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 2.2210526315789473e-05, |
|
"loss": 0.6381, |
|
"step": 1780 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 2.2105263157894736e-05, |
|
"loss": 0.6346, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 2.2e-05, |
|
"loss": 0.6291, |
|
"step": 1820 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 2.1894736842105266e-05, |
|
"loss": 0.63, |
|
"step": 1840 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 2.178947368421053e-05, |
|
"loss": 0.6296, |
|
"step": 1860 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 2.168421052631579e-05, |
|
"loss": 0.6278, |
|
"step": 1880 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 2.1578947368421053e-05, |
|
"loss": 0.6261, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 2.1473684210526316e-05, |
|
"loss": 0.6234, |
|
"step": 1920 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 2.136842105263158e-05, |
|
"loss": 0.6201, |
|
"step": 1940 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 2.1263157894736842e-05, |
|
"loss": 0.6187, |
|
"step": 1960 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 2.1157894736842106e-05, |
|
"loss": 0.6201, |
|
"step": 1980 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 2.105263157894737e-05, |
|
"loss": 0.6165, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 2.0947368421052632e-05, |
|
"loss": 0.6181, |
|
"step": 2020 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 2.0842105263157895e-05, |
|
"loss": 0.6129, |
|
"step": 2040 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 2.073684210526316e-05, |
|
"loss": 0.6158, |
|
"step": 2060 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 2.0631578947368422e-05, |
|
"loss": 0.6141, |
|
"step": 2080 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 2.0526315789473685e-05, |
|
"loss": 0.608, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 2.042105263157895e-05, |
|
"loss": 0.6077, |
|
"step": 2120 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 2.0315789473684212e-05, |
|
"loss": 0.6087, |
|
"step": 2140 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 2.0210526315789475e-05, |
|
"loss": 0.6066, |
|
"step": 2160 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 2.0105263157894735e-05, |
|
"loss": 0.6035, |
|
"step": 2180 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.9999999999999998e-05, |
|
"loss": 0.6006, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.989473684210526e-05, |
|
"loss": 0.6061, |
|
"step": 2220 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 1.9789473684210528e-05, |
|
"loss": 0.6025, |
|
"step": 2240 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.968421052631579e-05, |
|
"loss": 0.6021, |
|
"step": 2260 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.9578947368421055e-05, |
|
"loss": 0.5989, |
|
"step": 2280 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 1.9473684210526318e-05, |
|
"loss": 0.5998, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.936842105263158e-05, |
|
"loss": 0.597, |
|
"step": 2320 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.926315789473684e-05, |
|
"loss": 0.5995, |
|
"step": 2340 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 1.9157894736842104e-05, |
|
"loss": 0.5965, |
|
"step": 2360 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.9052631578947368e-05, |
|
"loss": 0.5922, |
|
"step": 2380 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.894736842105263e-05, |
|
"loss": 0.5922, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 1.8842105263157894e-05, |
|
"loss": 0.5964, |
|
"step": 2420 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.873684210526316e-05, |
|
"loss": 0.5898, |
|
"step": 2440 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.8631578947368424e-05, |
|
"loss": 0.5897, |
|
"step": 2460 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 1.8526315789473684e-05, |
|
"loss": 0.5818, |
|
"step": 2480 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.8421052631578947e-05, |
|
"loss": 0.5876, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.831578947368421e-05, |
|
"loss": 0.5868, |
|
"step": 2520 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 1.8210526315789474e-05, |
|
"loss": 0.5864, |
|
"step": 2540 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.8105263157894737e-05, |
|
"loss": 0.5851, |
|
"step": 2560 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.8e-05, |
|
"loss": 0.5835, |
|
"step": 2580 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 1.7894736842105264e-05, |
|
"loss": 0.5777, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.7789473684210527e-05, |
|
"loss": 0.5832, |
|
"step": 2620 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.7684210526315787e-05, |
|
"loss": 0.579, |
|
"step": 2640 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 1.7578947368421054e-05, |
|
"loss": 0.5833, |
|
"step": 2660 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.7473684210526317e-05, |
|
"loss": 0.585, |
|
"step": 2680 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.736842105263158e-05, |
|
"loss": 0.5819, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 1.7263157894736843e-05, |
|
"loss": 0.5744, |
|
"step": 2720 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.7157894736842107e-05, |
|
"loss": 0.5743, |
|
"step": 2740 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.705263157894737e-05, |
|
"loss": 0.5787, |
|
"step": 2760 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 1.694736842105263e-05, |
|
"loss": 0.5737, |
|
"step": 2780 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.6842105263157893e-05, |
|
"loss": 0.5733, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.6736842105263156e-05, |
|
"loss": 0.5711, |
|
"step": 2820 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 1.663157894736842e-05, |
|
"loss": 0.5667, |
|
"step": 2840 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.6526315789473686e-05, |
|
"loss": 0.5659, |
|
"step": 2860 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.642105263157895e-05, |
|
"loss": 0.5685, |
|
"step": 2880 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 1.6315789473684213e-05, |
|
"loss": 0.5664, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.6210526315789476e-05, |
|
"loss": 0.5691, |
|
"step": 2920 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.6105263157894736e-05, |
|
"loss": 0.5645, |
|
"step": 2940 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 1.6e-05, |
|
"loss": 0.568, |
|
"step": 2960 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.5894736842105263e-05, |
|
"loss": 0.5614, |
|
"step": 2980 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 1.5789473684210526e-05, |
|
"loss": 0.5648, |
|
"step": 3000 |
|
} |
|
], |
|
"max_steps": 6000, |
|
"num_train_epochs": 1, |
|
"total_flos": 0.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|