|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 9.6, |
|
"global_step": 30000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.92e-05, |
|
"loss": 6.308, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.8400000000000004e-05, |
|
"loss": 5.437, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.76e-05, |
|
"loss": 4.9197, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 4.6800000000000006e-05, |
|
"loss": 4.2132, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.600000000000001e-05, |
|
"loss": 3.5741, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 4.52e-05, |
|
"loss": 3.1896, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 4.44e-05, |
|
"loss": 2.9179, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 4.36e-05, |
|
"loss": 2.689, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 4.2800000000000004e-05, |
|
"loss": 2.5473, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 4.2e-05, |
|
"loss": 2.414, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 4.12e-05, |
|
"loss": 2.3057, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 4.0400000000000006e-05, |
|
"loss": 2.2348, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 3.960000000000001e-05, |
|
"loss": 2.1517, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 3.88e-05, |
|
"loss": 2.0636, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 3.8e-05, |
|
"loss": 2.0165, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 3.72e-05, |
|
"loss": 1.952, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 3.6400000000000004e-05, |
|
"loss": 1.9072, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 3.56e-05, |
|
"loss": 1.8658, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 3.48e-05, |
|
"loss": 1.8263, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 3.4000000000000007e-05, |
|
"loss": 1.7846, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 3.32e-05, |
|
"loss": 1.7591, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 3.24e-05, |
|
"loss": 1.7168, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 3.16e-05, |
|
"loss": 1.6956, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 3.08e-05, |
|
"loss": 1.6747, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 3e-05, |
|
"loss": 1.6421, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 4.16, |
|
"learning_rate": 2.9199999999999998e-05, |
|
"loss": 1.6169, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 4.32, |
|
"learning_rate": 2.84e-05, |
|
"loss": 1.5991, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 4.48, |
|
"learning_rate": 2.7600000000000003e-05, |
|
"loss": 1.5645, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 4.64, |
|
"learning_rate": 2.6800000000000004e-05, |
|
"loss": 1.5588, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 4.8, |
|
"learning_rate": 2.6000000000000002e-05, |
|
"loss": 1.5424, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 4.96, |
|
"learning_rate": 2.5200000000000003e-05, |
|
"loss": 1.532, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 5.12, |
|
"learning_rate": 2.44e-05, |
|
"loss": 1.5137, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 5.28, |
|
"learning_rate": 2.36e-05, |
|
"loss": 1.4885, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 5.44, |
|
"learning_rate": 2.2800000000000002e-05, |
|
"loss": 1.475, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 5.6, |
|
"learning_rate": 2.2000000000000003e-05, |
|
"loss": 1.4793, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 5.76, |
|
"learning_rate": 2.12e-05, |
|
"loss": 1.4521, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 5.92, |
|
"learning_rate": 2.04e-05, |
|
"loss": 1.4481, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 6.08, |
|
"learning_rate": 1.9600000000000002e-05, |
|
"loss": 1.4376, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 6.24, |
|
"learning_rate": 1.88e-05, |
|
"loss": 1.4147, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 6.4, |
|
"learning_rate": 1.8e-05, |
|
"loss": 1.4153, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 6.56, |
|
"learning_rate": 1.7199999999999998e-05, |
|
"loss": 1.4011, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 6.72, |
|
"learning_rate": 1.6400000000000002e-05, |
|
"loss": 1.3889, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 6.88, |
|
"learning_rate": 1.56e-05, |
|
"loss": 1.3834, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 7.04, |
|
"learning_rate": 1.48e-05, |
|
"loss": 1.3765, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 7.2, |
|
"learning_rate": 1.4000000000000001e-05, |
|
"loss": 1.3716, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 7.36, |
|
"learning_rate": 1.32e-05, |
|
"loss": 1.3623, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 7.52, |
|
"learning_rate": 1.24e-05, |
|
"loss": 1.3495, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 7.68, |
|
"learning_rate": 1.16e-05, |
|
"loss": 1.3539, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 7.84, |
|
"learning_rate": 1.08e-05, |
|
"loss": 1.3432, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"learning_rate": 1e-05, |
|
"loss": 1.3416, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 8.16, |
|
"learning_rate": 9.2e-06, |
|
"loss": 1.3253, |
|
"step": 25500 |
|
}, |
|
{ |
|
"epoch": 8.32, |
|
"learning_rate": 8.400000000000001e-06, |
|
"loss": 1.3203, |
|
"step": 26000 |
|
}, |
|
{ |
|
"epoch": 8.48, |
|
"learning_rate": 7.6e-06, |
|
"loss": 1.319, |
|
"step": 26500 |
|
}, |
|
{ |
|
"epoch": 8.64, |
|
"learning_rate": 6.800000000000001e-06, |
|
"loss": 1.3196, |
|
"step": 27000 |
|
}, |
|
{ |
|
"epoch": 8.8, |
|
"learning_rate": 6e-06, |
|
"loss": 1.3185, |
|
"step": 27500 |
|
}, |
|
{ |
|
"epoch": 8.96, |
|
"learning_rate": 5.2e-06, |
|
"loss": 1.3155, |
|
"step": 28000 |
|
}, |
|
{ |
|
"epoch": 9.12, |
|
"learning_rate": 4.4e-06, |
|
"loss": 1.3083, |
|
"step": 28500 |
|
}, |
|
{ |
|
"epoch": 9.28, |
|
"learning_rate": 3.6e-06, |
|
"loss": 1.2983, |
|
"step": 29000 |
|
}, |
|
{ |
|
"epoch": 9.44, |
|
"learning_rate": 2.8000000000000003e-06, |
|
"loss": 1.2991, |
|
"step": 29500 |
|
}, |
|
{ |
|
"epoch": 9.6, |
|
"learning_rate": 2.0000000000000003e-06, |
|
"loss": 1.3022, |
|
"step": 30000 |
|
} |
|
], |
|
"max_steps": 31250, |
|
"num_train_epochs": 10, |
|
"total_flos": 4.028813279232e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|