|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 27741, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.909880682022999e-05, |
|
"loss": 1.5855, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.819761364045997e-05, |
|
"loss": 0.9642, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.7296420460689956e-05, |
|
"loss": 0.8671, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.639522728091994e-05, |
|
"loss": 0.8052, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.5494034101149925e-05, |
|
"loss": 0.765, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.459284092137991e-05, |
|
"loss": 0.7121, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 4.3691647741609894e-05, |
|
"loss": 0.6643, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.279045456183988e-05, |
|
"loss": 0.6489, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 4.188926138206986e-05, |
|
"loss": 0.6167, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 4.098806820229985e-05, |
|
"loss": 0.5922, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.008687502252983e-05, |
|
"loss": 0.5763, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 3.9185681842759816e-05, |
|
"loss": 0.5449, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 3.82844886629898e-05, |
|
"loss": 0.5321, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 3.7383295483219785e-05, |
|
"loss": 0.5141, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 3.648210230344977e-05, |
|
"loss": 0.4918, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 3.558090912367975e-05, |
|
"loss": 0.4764, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 3.467971594390974e-05, |
|
"loss": 0.4581, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 3.3778522764139723e-05, |
|
"loss": 0.4505, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 3.287732958436971e-05, |
|
"loss": 0.4065, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 3.197613640459969e-05, |
|
"loss": 0.3699, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 3.107494322482968e-05, |
|
"loss": 0.3601, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 3.017375004505966e-05, |
|
"loss": 0.3493, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 2.9272556865289646e-05, |
|
"loss": 0.3467, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 2.837136368551963e-05, |
|
"loss": 0.3401, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 1.35, |
|
"learning_rate": 2.7470170505749615e-05, |
|
"loss": 0.3317, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 1.41, |
|
"learning_rate": 2.65689773259796e-05, |
|
"loss": 0.3183, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 2.5667784146209584e-05, |
|
"loss": 0.3242, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 1.51, |
|
"learning_rate": 2.476659096643957e-05, |
|
"loss": 0.3167, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 2.3865397786669553e-05, |
|
"loss": 0.2991, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 2.2964204606899537e-05, |
|
"loss": 0.3037, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 2.2063011427129522e-05, |
|
"loss": 0.2938, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 1.73, |
|
"learning_rate": 2.1161818247359506e-05, |
|
"loss": 0.2826, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 2.026062506758949e-05, |
|
"loss": 0.2768, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 1.9359431887819472e-05, |
|
"loss": 0.2733, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 1.8458238708049457e-05, |
|
"loss": 0.273, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 1.755704552827944e-05, |
|
"loss": 0.2639, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 1.6655852348509426e-05, |
|
"loss": 0.2563, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 2.05, |
|
"learning_rate": 1.575465916873941e-05, |
|
"loss": 0.202, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 2.11, |
|
"learning_rate": 1.4853465988969395e-05, |
|
"loss": 0.1995, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 1.3952272809199379e-05, |
|
"loss": 0.1923, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"learning_rate": 1.3051079629429367e-05, |
|
"loss": 0.1955, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 2.27, |
|
"learning_rate": 1.214988644965935e-05, |
|
"loss": 0.1916, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 1.1248693269889334e-05, |
|
"loss": 0.1826, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 2.38, |
|
"learning_rate": 1.0347500090119317e-05, |
|
"loss": 0.1863, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 2.43, |
|
"learning_rate": 9.446306910349303e-06, |
|
"loss": 0.1797, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 8.545113730579288e-06, |
|
"loss": 0.1755, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 7.643920550809272e-06, |
|
"loss": 0.1744, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 6.742727371039257e-06, |
|
"loss": 0.1737, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 5.84153419126924e-06, |
|
"loss": 0.1631, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 4.940341011499225e-06, |
|
"loss": 0.165, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 4.03914783172921e-06, |
|
"loss": 0.1648, |
|
"step": 25500 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 3.1379546519591943e-06, |
|
"loss": 0.1626, |
|
"step": 26000 |
|
}, |
|
{ |
|
"epoch": 2.87, |
|
"learning_rate": 2.2367614721891784e-06, |
|
"loss": 0.1551, |
|
"step": 26500 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 1.335568292419163e-06, |
|
"loss": 0.1577, |
|
"step": 27000 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 4.3437511264914753e-07, |
|
"loss": 0.1535, |
|
"step": 27500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 27741, |
|
"total_flos": 2.3702775297552e+17, |
|
"train_loss": 0.38746264250645196, |
|
"train_runtime": 16164.8093, |
|
"train_samples_per_second": 109.822, |
|
"train_steps_per_second": 1.716 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 27741, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 2.3702775297552e+17, |
|
"train_batch_size": 64, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|