|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.4101963082332259, |
|
"global_step": 4200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 5e-05, |
|
"loss": 3.3163, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0001, |
|
"loss": 2.491, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 0.0001, |
|
"loss": 2.0415, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0001, |
|
"loss": 1.9681, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 0.0001, |
|
"loss": 1.8944, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0001, |
|
"loss": 1.8218, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.0001, |
|
"loss": 1.7536, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0001, |
|
"loss": 1.681, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6851, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6193, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6291, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6241, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5997, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5744, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6018, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0001, |
|
"loss": 1.6006, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5671, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5721, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5573, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5539, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.0001, |
|
"loss": 1.542, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5165, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5797, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5609, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5435, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5645, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5258, |
|
"step": 1350 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4773, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4825, |
|
"step": 1450 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5124, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4963, |
|
"step": 1550 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4861, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5275, |
|
"step": 1650 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0001, |
|
"loss": 1.484, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5349, |
|
"step": 1750 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4641, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4752, |
|
"step": 1850 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4475, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.0001, |
|
"loss": 1.5358, |
|
"step": 1950 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4652, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0001, |
|
"loss": 1.419, |
|
"step": 2050 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4588, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4593, |
|
"step": 2150 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4604, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4598, |
|
"step": 2250 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0001, |
|
"loss": 1.482, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4749, |
|
"step": 2350 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4718, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4343, |
|
"step": 2450 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4861, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4717, |
|
"step": 2550 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4599, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4746, |
|
"step": 2650 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4517, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4267, |
|
"step": 2750 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4303, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4146, |
|
"step": 2850 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4245, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4356, |
|
"step": 2950 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4183, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0001, |
|
"loss": 1.423, |
|
"step": 3050 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4854, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4552, |
|
"step": 3150 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0001, |
|
"loss": 1.456, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4202, |
|
"step": 3250 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4025, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4134, |
|
"step": 3350 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4282, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4256, |
|
"step": 3450 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4056, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.0001, |
|
"loss": 1.3779, |
|
"step": 3550 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.0001, |
|
"loss": 1.3857, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0001, |
|
"loss": 1.3819, |
|
"step": 3650 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4095, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4387, |
|
"step": 3750 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 0.0001, |
|
"loss": 1.3831, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.0001, |
|
"loss": 1.3913, |
|
"step": 3850 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4007, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4038, |
|
"step": 3950 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0001, |
|
"loss": 1.3926, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0001, |
|
"loss": 1.36, |
|
"step": 4050 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0001, |
|
"loss": 1.4146, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.0001, |
|
"loss": 1.3626, |
|
"step": 4150 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.0001, |
|
"loss": 1.3562, |
|
"step": 4200 |
|
} |
|
], |
|
"max_steps": 20478, |
|
"num_train_epochs": 2, |
|
"total_flos": 6.3352674125568e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|