| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09592326139088729, | |
| "eval_steps": 500, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00013, | |
| "loss": 1.1241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00026, | |
| "loss": 1.0107, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00039, | |
| "loss": 1.1086, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00052, | |
| "loss": 1.0044, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00065, | |
| "loss": 1.0496, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0005933661039639299, | |
| "loss": 1.0199, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0005493502655735357, | |
| "loss": 1.0198, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0005138701197773616, | |
| "loss": 0.969, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0004844813951249544, | |
| "loss": 0.9383, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0004596194077712558, | |
| "loss": 0.8776, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0004382299106011073, | |
| "loss": 1.0173, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0004195731958391368, | |
| "loss": 1.1173, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0004031128874149274, | |
| "loss": 1.0876, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0003884492980336779, | |
| "loss": 1.0524, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003752776749732568, | |
| "loss": 0.8953, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00036336104634371584, | |
| "loss": 1.1335, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00035251199395531623, | |
| "loss": 0.9837, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00034258007985157445, | |
| "loss": 0.9707, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0003334429644276751, | |
| "loss": 0.9149, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.000325, | |
| "loss": 1.0043, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00031716752370827323, | |
| "loss": 1.001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00030987534150481746, | |
| "loss": 1.0395, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000303064062678102, | |
| "loss": 0.8718, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029668305198196496, | |
| "loss": 1.1114, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029068883707497264, | |
| "loss": 0.7765, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002850438562747845, | |
| "loss": 0.9522, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00027971546389275785, | |
| "loss": 0.9588, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00027467513278676785, | |
| "loss": 1.0313, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0002698978095246549, | |
| "loss": 0.9338, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000265361388801511, | |
| "loss": 0.892, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00026104628189331215, | |
| "loss": 0.893, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002569350598886808, | |
| "loss": 0.8983, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00025301215685249496, | |
| "loss": 0.9277, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00024926362137539537, | |
| "loss": 0.8962, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00024567690745599767, | |
| "loss": 0.9124, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002422406975624772, | |
| "loss": 0.9535, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00023894475218048754, | |
| "loss": 0.9019, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002357797812857538, | |
| "loss": 1.024, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00023273733406281566, | |
| "loss": 0.8549, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002298097038856279, | |
| "loss": 1.0489, | |
| "step": 40 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 417, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "total_flos": 1.2924943770845184e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |