| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 69180, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.4455044810638915e-08, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5.001445504481065e-06, | |
| "loss": 0.0054, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.000289100896213e-05, | |
| "loss": 0.0038, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5004336513443193e-05, | |
| "loss": 0.0027, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.000578201792426e-05, | |
| "loss": 0.0019, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5007227522405318e-05, | |
| "loss": 0.0012, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.0008673026886387e-05, | |
| "loss": 0.0011, | |
| "step": 2076 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.5010118531367445e-05, | |
| "loss": 0.0012, | |
| "step": 2422 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.001156403584852e-05, | |
| "loss": 0.0011, | |
| "step": 2768 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.5013009540329577e-05, | |
| "loss": 0.001, | |
| "step": 3114 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.0005217896541580558, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1674, | |
| "eval_samples_per_second": 23.069, | |
| "eval_steps_per_second": 0.923, | |
| "step": 3459 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.0014455044810635e-05, | |
| "loss": 0.001, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.501590054929171e-05, | |
| "loss": 0.001, | |
| "step": 3806 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6.001734605377277e-05, | |
| "loss": 0.0008, | |
| "step": 4152 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.501879155825383e-05, | |
| "loss": 0.0009, | |
| "step": 4498 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7.002023706273489e-05, | |
| "loss": 0.0011, | |
| "step": 4844 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.502168256721596e-05, | |
| "loss": 0.001, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8.002312807169704e-05, | |
| "loss": 0.0008, | |
| "step": 5536 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.50245735761781e-05, | |
| "loss": 0.0009, | |
| "step": 5882 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9.002601908065915e-05, | |
| "loss": 0.0011, | |
| "step": 6228 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 9.502746458514021e-05, | |
| "loss": 0.0007, | |
| "step": 6574 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.0005328759434632957, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1588, | |
| "eval_samples_per_second": 23.161, | |
| "eval_steps_per_second": 0.926, | |
| "step": 6918 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.999678776781987e-05, | |
| "loss": 0.001, | |
| "step": 6920 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.94410716006553e-05, | |
| "loss": 0.0007, | |
| "step": 7266 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.888535543349073e-05, | |
| "loss": 0.0009, | |
| "step": 7612 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 9.832963926632618e-05, | |
| "loss": 0.0008, | |
| "step": 7958 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.777392309916162e-05, | |
| "loss": 0.0009, | |
| "step": 8304 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.721820693199704e-05, | |
| "loss": 0.0008, | |
| "step": 8650 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.666249076483249e-05, | |
| "loss": 0.0008, | |
| "step": 8996 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.610677459766793e-05, | |
| "loss": 0.0009, | |
| "step": 9342 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.555105843050336e-05, | |
| "loss": 0.0008, | |
| "step": 9688 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.49953422633388e-05, | |
| "loss": 0.0008, | |
| "step": 10034 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.0005345833487808704, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1807, | |
| "eval_samples_per_second": 22.928, | |
| "eval_steps_per_second": 0.917, | |
| "step": 10377 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.443962609617424e-05, | |
| "loss": 0.0012, | |
| "step": 10380 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 9.388390992900967e-05, | |
| "loss": 0.0008, | |
| "step": 10726 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.332819376184511e-05, | |
| "loss": 0.0006, | |
| "step": 11072 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 9.277247759468054e-05, | |
| "loss": 0.0009, | |
| "step": 11418 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.221676142751598e-05, | |
| "loss": 0.0007, | |
| "step": 11764 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 9.166104526035142e-05, | |
| "loss": 0.0006, | |
| "step": 12110 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 9.110532909318687e-05, | |
| "loss": 0.0007, | |
| "step": 12456 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 9.05496129260223e-05, | |
| "loss": 0.0008, | |
| "step": 12802 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 8.999389675885773e-05, | |
| "loss": 0.0008, | |
| "step": 13148 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 8.943818059169318e-05, | |
| "loss": 0.0007, | |
| "step": 13494 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.0006046278867870569, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1455, | |
| "eval_samples_per_second": 23.305, | |
| "eval_steps_per_second": 0.932, | |
| "step": 13836 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.888246442452861e-05, | |
| "loss": 0.0008, | |
| "step": 13840 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 8.832674825736405e-05, | |
| "loss": 0.0005, | |
| "step": 14186 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 8.777103209019947e-05, | |
| "loss": 0.0006, | |
| "step": 14532 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 8.721531592303492e-05, | |
| "loss": 0.0009, | |
| "step": 14878 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 8.665959975587036e-05, | |
| "loss": 0.0005, | |
| "step": 15224 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 8.61038835887058e-05, | |
| "loss": 0.0006, | |
| "step": 15570 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 8.554816742154123e-05, | |
| "loss": 0.0007, | |
| "step": 15916 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 8.499245125437667e-05, | |
| "loss": 0.0006, | |
| "step": 16262 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 8.44367350872121e-05, | |
| "loss": 0.0008, | |
| "step": 16608 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 8.388101892004755e-05, | |
| "loss": 0.0006, | |
| "step": 16954 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.0002887483569793403, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1519, | |
| "eval_samples_per_second": 23.235, | |
| "eval_steps_per_second": 0.929, | |
| "step": 17295 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.332530275288298e-05, | |
| "loss": 0.0007, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 8.276958658571841e-05, | |
| "loss": 0.0006, | |
| "step": 17646 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 8.221387041855386e-05, | |
| "loss": 0.0006, | |
| "step": 17992 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 8.16581542513893e-05, | |
| "loss": 0.0006, | |
| "step": 18338 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 8.110243808422474e-05, | |
| "loss": 0.0006, | |
| "step": 18684 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 8.054672191706016e-05, | |
| "loss": 0.0007, | |
| "step": 19030 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 7.999100574989561e-05, | |
| "loss": 0.0007, | |
| "step": 19376 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 7.943528958273105e-05, | |
| "loss": 0.0005, | |
| "step": 19722 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 7.887957341556648e-05, | |
| "loss": 0.0007, | |
| "step": 20068 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 7.832385724840192e-05, | |
| "loss": 0.0006, | |
| "step": 20414 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.00028923238278366625, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.139, | |
| "eval_samples_per_second": 23.376, | |
| "eval_steps_per_second": 0.935, | |
| "step": 20754 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.776814108123735e-05, | |
| "loss": 0.0007, | |
| "step": 20760 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 7.721242491407279e-05, | |
| "loss": 0.0006, | |
| "step": 21106 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 7.665670874690823e-05, | |
| "loss": 0.0007, | |
| "step": 21452 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 7.610099257974366e-05, | |
| "loss": 0.0006, | |
| "step": 21798 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 7.55452764125791e-05, | |
| "loss": 0.0005, | |
| "step": 22144 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 7.498956024541455e-05, | |
| "loss": 0.0006, | |
| "step": 22490 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 7.443384407824999e-05, | |
| "loss": 0.0005, | |
| "step": 22836 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 7.387812791108541e-05, | |
| "loss": 0.0006, | |
| "step": 23182 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 7.332241174392085e-05, | |
| "loss": 0.0006, | |
| "step": 23528 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 7.27666955767563e-05, | |
| "loss": 0.0005, | |
| "step": 23874 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.00023660251463297755, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1425, | |
| "eval_samples_per_second": 23.338, | |
| "eval_steps_per_second": 0.934, | |
| "step": 24213 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.221097940959173e-05, | |
| "loss": 0.0006, | |
| "step": 24220 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 7.165526324242716e-05, | |
| "loss": 0.0005, | |
| "step": 24566 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 7.10995470752626e-05, | |
| "loss": 0.0006, | |
| "step": 24912 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 7.054383090809804e-05, | |
| "loss": 0.0006, | |
| "step": 25258 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 6.998811474093348e-05, | |
| "loss": 0.0005, | |
| "step": 25604 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 6.943239857376891e-05, | |
| "loss": 0.0006, | |
| "step": 25950 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 6.887668240660435e-05, | |
| "loss": 0.0004, | |
| "step": 26296 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 6.832096623943979e-05, | |
| "loss": 0.0007, | |
| "step": 26642 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 6.776525007227524e-05, | |
| "loss": 0.0007, | |
| "step": 26988 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 6.720953390511066e-05, | |
| "loss": 0.0006, | |
| "step": 27334 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.0004639440739993006, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1108, | |
| "eval_samples_per_second": 23.687, | |
| "eval_steps_per_second": 0.947, | |
| "step": 27672 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.66538177379461e-05, | |
| "loss": 0.0006, | |
| "step": 27680 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 6.609810157078153e-05, | |
| "loss": 0.0005, | |
| "step": 28026 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 6.554238540361698e-05, | |
| "loss": 0.0005, | |
| "step": 28372 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 6.498666923645242e-05, | |
| "loss": 0.0004, | |
| "step": 28718 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 6.443095306928784e-05, | |
| "loss": 0.0004, | |
| "step": 29064 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 6.387523690212329e-05, | |
| "loss": 0.0006, | |
| "step": 29410 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 6.331952073495873e-05, | |
| "loss": 0.0008, | |
| "step": 29756 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 6.276380456779417e-05, | |
| "loss": 0.0006, | |
| "step": 30102 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.22080884006296e-05, | |
| "loss": 0.0005, | |
| "step": 30448 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 6.165237223346504e-05, | |
| "loss": 0.0006, | |
| "step": 30794 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.0005358799826353788, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1129, | |
| "eval_samples_per_second": 23.664, | |
| "eval_steps_per_second": 0.947, | |
| "step": 31131 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.109665606630047e-05, | |
| "loss": 0.0004, | |
| "step": 31140 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 6.054093989913592e-05, | |
| "loss": 0.0005, | |
| "step": 31486 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 5.9985223731971354e-05, | |
| "loss": 0.0006, | |
| "step": 31832 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 5.9429507564806783e-05, | |
| "loss": 0.0004, | |
| "step": 32178 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 5.887379139764222e-05, | |
| "loss": 0.0007, | |
| "step": 32524 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 5.831807523047766e-05, | |
| "loss": 0.0005, | |
| "step": 32870 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 5.77623590633131e-05, | |
| "loss": 0.0004, | |
| "step": 33216 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 5.720664289614853e-05, | |
| "loss": 0.0006, | |
| "step": 33562 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 5.665092672898398e-05, | |
| "loss": 0.0005, | |
| "step": 33908 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 5.609521056181941e-05, | |
| "loss": 0.0005, | |
| "step": 34254 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.0005827790591865778, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.188, | |
| "eval_samples_per_second": 22.852, | |
| "eval_steps_per_second": 0.914, | |
| "step": 34590 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.5539494394654845e-05, | |
| "loss": 0.0005, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 5.498377822749029e-05, | |
| "loss": 0.0005, | |
| "step": 34946 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 5.4428062060325725e-05, | |
| "loss": 0.0004, | |
| "step": 35292 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 5.387234589316116e-05, | |
| "loss": 0.0004, | |
| "step": 35638 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 5.3316629725996604e-05, | |
| "loss": 0.0004, | |
| "step": 35984 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 5.2760913558832034e-05, | |
| "loss": 0.0005, | |
| "step": 36330 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 5.220519739166747e-05, | |
| "loss": 0.0006, | |
| "step": 36676 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 5.164948122450291e-05, | |
| "loss": 0.0005, | |
| "step": 37022 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 5.109376505733835e-05, | |
| "loss": 0.0004, | |
| "step": 37368 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 5.0538048890173786e-05, | |
| "loss": 0.0004, | |
| "step": 37714 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.0005017376388423145, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1154, | |
| "eval_samples_per_second": 23.636, | |
| "eval_steps_per_second": 0.945, | |
| "step": 38049 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.998233272300922e-05, | |
| "loss": 0.0005, | |
| "step": 38060 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 4.942661655584466e-05, | |
| "loss": 0.0004, | |
| "step": 38406 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 4.8870900388680096e-05, | |
| "loss": 0.0004, | |
| "step": 38752 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 4.831518422151554e-05, | |
| "loss": 0.0004, | |
| "step": 39098 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 4.775946805435097e-05, | |
| "loss": 0.0007, | |
| "step": 39444 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 4.720375188718641e-05, | |
| "loss": 0.0005, | |
| "step": 39790 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 4.664803572002184e-05, | |
| "loss": 0.0005, | |
| "step": 40136 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 4.6092319552857284e-05, | |
| "loss": 0.0007, | |
| "step": 40482 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 4.553660338569272e-05, | |
| "loss": 0.0006, | |
| "step": 40828 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 4.498088721852816e-05, | |
| "loss": 0.0005, | |
| "step": 41174 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.0003966529038734734, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1167, | |
| "eval_samples_per_second": 23.622, | |
| "eval_steps_per_second": 0.945, | |
| "step": 41508 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.4425171051363594e-05, | |
| "loss": 0.0005, | |
| "step": 41520 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 4.386945488419903e-05, | |
| "loss": 0.0005, | |
| "step": 41866 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 4.3313738717034466e-05, | |
| "loss": 0.0005, | |
| "step": 42212 | |
| }, | |
| { | |
| "epoch": 12.3, | |
| "learning_rate": 4.275802254986991e-05, | |
| "loss": 0.0004, | |
| "step": 42558 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 4.220230638270534e-05, | |
| "loss": 0.0004, | |
| "step": 42904 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 4.164659021554078e-05, | |
| "loss": 0.0005, | |
| "step": 43250 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 4.109087404837622e-05, | |
| "loss": 0.0005, | |
| "step": 43596 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 4.0535157881211655e-05, | |
| "loss": 0.0004, | |
| "step": 43942 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.997944171404709e-05, | |
| "loss": 0.0004, | |
| "step": 44288 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 3.942372554688253e-05, | |
| "loss": 0.0004, | |
| "step": 44634 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.0004018562030978501, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1157, | |
| "eval_samples_per_second": 23.633, | |
| "eval_steps_per_second": 0.945, | |
| "step": 44967 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.886800937971797e-05, | |
| "loss": 0.0005, | |
| "step": 44980 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 3.831229321255341e-05, | |
| "loss": 0.0006, | |
| "step": 45326 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 3.7756577045388844e-05, | |
| "loss": 0.0005, | |
| "step": 45672 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 3.720086087822428e-05, | |
| "loss": 0.0004, | |
| "step": 46018 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 3.664514471105972e-05, | |
| "loss": 0.0004, | |
| "step": 46364 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 3.608942854389515e-05, | |
| "loss": 0.0004, | |
| "step": 46710 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3.5533712376730596e-05, | |
| "loss": 0.0004, | |
| "step": 47056 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 3.4977996209566026e-05, | |
| "loss": 0.0003, | |
| "step": 47402 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 3.442228004240147e-05, | |
| "loss": 0.0006, | |
| "step": 47748 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "learning_rate": 3.3866563875236906e-05, | |
| "loss": 0.0004, | |
| "step": 48094 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.00045212701661512256, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.109, | |
| "eval_samples_per_second": 23.708, | |
| "eval_steps_per_second": 0.948, | |
| "step": 48426 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.331084770807234e-05, | |
| "loss": 0.0004, | |
| "step": 48440 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 3.275513154090778e-05, | |
| "loss": 0.0004, | |
| "step": 48786 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 3.2199415373743215e-05, | |
| "loss": 0.0005, | |
| "step": 49132 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 3.164369920657865e-05, | |
| "loss": 0.0004, | |
| "step": 49478 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 3.1087983039414094e-05, | |
| "loss": 0.0004, | |
| "step": 49824 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 3.0532266872249524e-05, | |
| "loss": 0.0004, | |
| "step": 50170 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "learning_rate": 2.9976550705084967e-05, | |
| "loss": 0.0005, | |
| "step": 50516 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 2.94208345379204e-05, | |
| "loss": 0.0003, | |
| "step": 50862 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 2.886511837075584e-05, | |
| "loss": 0.0004, | |
| "step": 51208 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 2.830940220359128e-05, | |
| "loss": 0.0004, | |
| "step": 51554 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.0004186382284387946, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1163, | |
| "eval_samples_per_second": 23.626, | |
| "eval_steps_per_second": 0.945, | |
| "step": 51885 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.7753686036426713e-05, | |
| "loss": 0.0004, | |
| "step": 51900 | |
| }, | |
| { | |
| "epoch": 15.1, | |
| "learning_rate": 2.7197969869262153e-05, | |
| "loss": 0.0004, | |
| "step": 52246 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.6642253702097592e-05, | |
| "loss": 0.0005, | |
| "step": 52592 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 2.6086537534933025e-05, | |
| "loss": 0.0004, | |
| "step": 52938 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 2.5530821367768465e-05, | |
| "loss": 0.0004, | |
| "step": 53284 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 2.49751052006039e-05, | |
| "loss": 0.0005, | |
| "step": 53630 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 2.4419389033439338e-05, | |
| "loss": 0.0004, | |
| "step": 53976 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 2.3863672866274774e-05, | |
| "loss": 0.0004, | |
| "step": 54322 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 2.330795669911021e-05, | |
| "loss": 0.0004, | |
| "step": 54668 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 2.275224053194565e-05, | |
| "loss": 0.0004, | |
| "step": 55014 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.00046242817188613117, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1198, | |
| "eval_samples_per_second": 23.587, | |
| "eval_steps_per_second": 0.943, | |
| "step": 55344 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.2196524364781087e-05, | |
| "loss": 0.0003, | |
| "step": 55360 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 2.1640808197616523e-05, | |
| "loss": 0.0004, | |
| "step": 55706 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 2.108509203045196e-05, | |
| "loss": 0.0004, | |
| "step": 56052 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 2.05293758632874e-05, | |
| "loss": 0.0003, | |
| "step": 56398 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 1.9973659696122836e-05, | |
| "loss": 0.0005, | |
| "step": 56744 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 1.9417943528958272e-05, | |
| "loss": 0.0003, | |
| "step": 57090 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "learning_rate": 1.8862227361793712e-05, | |
| "loss": 0.0003, | |
| "step": 57436 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 1.830651119462915e-05, | |
| "loss": 0.0003, | |
| "step": 57782 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 1.7750795027464585e-05, | |
| "loss": 0.0006, | |
| "step": 58128 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 1.7195078860300025e-05, | |
| "loss": 0.0004, | |
| "step": 58474 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.0004974314360879362, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1095, | |
| "eval_samples_per_second": 23.702, | |
| "eval_steps_per_second": 0.948, | |
| "step": 58803 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.663936269313546e-05, | |
| "loss": 0.0005, | |
| "step": 58820 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 1.6083646525970898e-05, | |
| "loss": 0.0004, | |
| "step": 59166 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 1.5527930358806337e-05, | |
| "loss": 0.0003, | |
| "step": 59512 | |
| }, | |
| { | |
| "epoch": 17.31, | |
| "learning_rate": 1.4972214191641772e-05, | |
| "loss": 0.0003, | |
| "step": 59858 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 1.441649802447721e-05, | |
| "loss": 0.0005, | |
| "step": 60204 | |
| }, | |
| { | |
| "epoch": 17.51, | |
| "learning_rate": 1.3860781857312647e-05, | |
| "loss": 0.0004, | |
| "step": 60550 | |
| }, | |
| { | |
| "epoch": 17.61, | |
| "learning_rate": 1.3305065690148087e-05, | |
| "loss": 0.0003, | |
| "step": 60896 | |
| }, | |
| { | |
| "epoch": 17.71, | |
| "learning_rate": 1.2749349522983523e-05, | |
| "loss": 0.0004, | |
| "step": 61242 | |
| }, | |
| { | |
| "epoch": 17.81, | |
| "learning_rate": 1.219363335581896e-05, | |
| "loss": 0.0005, | |
| "step": 61588 | |
| }, | |
| { | |
| "epoch": 17.91, | |
| "learning_rate": 1.1637917188654396e-05, | |
| "loss": 0.0004, | |
| "step": 61934 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.0004895007587037981, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1247, | |
| "eval_samples_per_second": 23.533, | |
| "eval_steps_per_second": 0.941, | |
| "step": 62262 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 1.1082201021489834e-05, | |
| "loss": 0.0003, | |
| "step": 62280 | |
| }, | |
| { | |
| "epoch": 18.11, | |
| "learning_rate": 1.052648485432527e-05, | |
| "loss": 0.0003, | |
| "step": 62626 | |
| }, | |
| { | |
| "epoch": 18.21, | |
| "learning_rate": 9.970768687160708e-06, | |
| "loss": 0.0005, | |
| "step": 62972 | |
| }, | |
| { | |
| "epoch": 18.31, | |
| "learning_rate": 9.415052519996145e-06, | |
| "loss": 0.0004, | |
| "step": 63318 | |
| }, | |
| { | |
| "epoch": 18.41, | |
| "learning_rate": 8.859336352831583e-06, | |
| "loss": 0.0004, | |
| "step": 63664 | |
| }, | |
| { | |
| "epoch": 18.51, | |
| "learning_rate": 8.303620185667021e-06, | |
| "loss": 0.0004, | |
| "step": 64010 | |
| }, | |
| { | |
| "epoch": 18.61, | |
| "learning_rate": 7.747904018502457e-06, | |
| "loss": 0.0005, | |
| "step": 64356 | |
| }, | |
| { | |
| "epoch": 18.71, | |
| "learning_rate": 7.192187851337895e-06, | |
| "loss": 0.0004, | |
| "step": 64702 | |
| }, | |
| { | |
| "epoch": 18.81, | |
| "learning_rate": 6.636471684173333e-06, | |
| "loss": 0.0004, | |
| "step": 65048 | |
| }, | |
| { | |
| "epoch": 18.91, | |
| "learning_rate": 6.08075551700877e-06, | |
| "loss": 0.0004, | |
| "step": 65394 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.00047712118248455226, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.1311, | |
| "eval_samples_per_second": 23.462, | |
| "eval_steps_per_second": 0.938, | |
| "step": 65721 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 5.525039349844207e-06, | |
| "loss": 0.0003, | |
| "step": 65740 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 4.9693231826796444e-06, | |
| "loss": 0.0003, | |
| "step": 66086 | |
| }, | |
| { | |
| "epoch": 19.21, | |
| "learning_rate": 4.413607015515082e-06, | |
| "loss": 0.0003, | |
| "step": 66432 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 3.857890848350519e-06, | |
| "loss": 0.0004, | |
| "step": 66778 | |
| }, | |
| { | |
| "epoch": 19.41, | |
| "learning_rate": 3.3021746811859566e-06, | |
| "loss": 0.0005, | |
| "step": 67124 | |
| }, | |
| { | |
| "epoch": 19.51, | |
| "learning_rate": 2.7464585140213935e-06, | |
| "loss": 0.0003, | |
| "step": 67470 | |
| }, | |
| { | |
| "epoch": 19.61, | |
| "learning_rate": 2.1907423468568307e-06, | |
| "loss": 0.0003, | |
| "step": 67816 | |
| }, | |
| { | |
| "epoch": 19.71, | |
| "learning_rate": 1.6350261796922682e-06, | |
| "loss": 0.0003, | |
| "step": 68162 | |
| }, | |
| { | |
| "epoch": 19.81, | |
| "learning_rate": 1.0793100125277054e-06, | |
| "loss": 0.0004, | |
| "step": 68508 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 5.235938453631429e-07, | |
| "loss": 0.0004, | |
| "step": 68854 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.00047323742182925344, | |
| "eval_max_distance": 3, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 2.107, | |
| "eval_samples_per_second": 23.73, | |
| "eval_steps_per_second": 0.949, | |
| "step": 69180 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 69180, | |
| "total_flos": 4.132028143466496e+16, | |
| "train_loss": 0.0006141960998232213, | |
| "train_runtime": 5700.2515, | |
| "train_samples_per_second": 364.026, | |
| "train_steps_per_second": 12.136 | |
| } | |
| ], | |
| "logging_steps": 346, | |
| "max_steps": 69180, | |
| "num_train_epochs": 20, | |
| "save_steps": 692, | |
| "total_flos": 4.132028143466496e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |