| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9991488731821041, | |
| "global_step": 27000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0019629944861784404, | |
| "loss": 0.0147, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0019259889723568812, | |
| "loss": 0.0187, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0018889834585353218, | |
| "loss": 0.0201, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.0018519779447137624, | |
| "loss": 0.0176, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.001814972430892203, | |
| "loss": 0.0177, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0017779669170706436, | |
| "loss": 0.0175, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0017409614032490842, | |
| "loss": 0.0177, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0017039558894275247, | |
| "loss": 0.0185, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0016669503756059653, | |
| "loss": 0.0179, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.001629944861784406, | |
| "loss": 0.0188, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0015929393479628465, | |
| "loss": 0.0181, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0015559338341412869, | |
| "loss": 0.0192, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0015189283203197277, | |
| "loss": 0.0172, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0014819228064981683, | |
| "loss": 0.0153, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0014449172926766088, | |
| "loss": 0.0154, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0014079117788550494, | |
| "loss": 0.0163, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00137090626503349, | |
| "loss": 0.0161, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0013339007512119306, | |
| "loss": 0.0149, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0012968952373903712, | |
| "loss": 0.016, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0012598897235688118, | |
| "loss": 0.015, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0012228842097472524, | |
| "loss": 0.0145, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.001185878695925693, | |
| "loss": 0.0145, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0011488731821041335, | |
| "loss": 0.0143, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0011118676682825741, | |
| "loss": 0.0136, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0010748621544610147, | |
| "loss": 0.0148, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0010378566406394553, | |
| "loss": 0.0141, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.001000851126817896, | |
| "loss": 0.0132, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0009638456129963365, | |
| "loss": 0.0128, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0009268400991747771, | |
| "loss": 0.0128, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0008898345853532175, | |
| "loss": 0.0128, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0008528290715316582, | |
| "loss": 0.0123, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.0008158235577100988, | |
| "loss": 0.0119, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.0007788180438885394, | |
| "loss": 0.0124, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00074181253006698, | |
| "loss": 0.0116, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0007048070162454206, | |
| "loss": 0.0118, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0006678015024238612, | |
| "loss": 0.0114, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0006307959886023018, | |
| "loss": 0.0114, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0005937904747807424, | |
| "loss": 0.0111, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0005567849609591829, | |
| "loss": 0.0105, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.0005197794471376235, | |
| "loss": 0.0107, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0004827739333160641, | |
| "loss": 0.0102, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.0004457684194945047, | |
| "loss": 0.0102, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0004087629056729453, | |
| "loss": 0.0099, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0003717573918513859, | |
| "loss": 0.0101, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0003347518780298264, | |
| "loss": 0.0095, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 0.00029774636420826705, | |
| "loss": 0.0097, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00026074085038670764, | |
| "loss": 0.0094, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.00022373533656514823, | |
| "loss": 0.0094, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0001867298227435888, | |
| "loss": 0.0095, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00014972430892202937, | |
| "loss": 0.0089, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.00011271879510046997, | |
| "loss": 0.0087, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 7.571328127891056e-05, | |
| "loss": 0.009, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.870776745735115e-05, | |
| "loss": 0.0088, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.702253635791733e-06, | |
| "loss": 0.0088, | |
| "step": 27000 | |
| } | |
| ], | |
| "max_steps": 27023, | |
| "num_train_epochs": 1, | |
| "total_flos": 8.7701487353856e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |