|
{ |
|
"best_metric": 0.2615379807814019, |
|
"best_model_checkpoint": "/opt/ml/final/summary/training/../summary_models/checkpoint-5000", |
|
"epoch": 2.3741690408357075, |
|
"global_step": 5000, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 9.333333333333334e-07, |
|
"loss": 12.8401, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 1.885714285714286e-06, |
|
"loss": 11.0877, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 2.838095238095238e-06, |
|
"loss": 7.1907, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 3.7904761904761907e-06, |
|
"loss": 3.1573, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.723809523809524e-06, |
|
"loss": 1.707, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 5.676190476190476e-06, |
|
"loss": 0.9049, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 6.628571428571428e-06, |
|
"loss": 0.6742, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 7.580952380952381e-06, |
|
"loss": 0.6116, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 8.533333333333335e-06, |
|
"loss": 0.5597, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 9.485714285714287e-06, |
|
"loss": 0.562, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"eval_loss": 0.5062821507453918, |
|
"eval_rouge1": 0.24465619036536226, |
|
"eval_rouge2": 0.05823001316422367, |
|
"eval_rougeL": 0.2441932274023993, |
|
"eval_runtime": 37.1079, |
|
"eval_samples_per_second": 24.577, |
|
"eval_steps_per_second": 6.144, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 9.951476793248946e-06, |
|
"loss": 0.5549, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 9.845991561181436e-06, |
|
"loss": 0.5342, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 9.740506329113924e-06, |
|
"loss": 0.5304, |
|
"step": 1300 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 9.635021097046414e-06, |
|
"loss": 0.524, |
|
"step": 1400 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 9.529535864978904e-06, |
|
"loss": 0.5235, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 9.424050632911394e-06, |
|
"loss": 0.5279, |
|
"step": 1600 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 9.318565400843884e-06, |
|
"loss": 0.5304, |
|
"step": 1700 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 9.213080168776372e-06, |
|
"loss": 0.5124, |
|
"step": 1800 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 9.107594936708862e-06, |
|
"loss": 0.5014, |
|
"step": 1900 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 9.002109704641352e-06, |
|
"loss": 0.4888, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"eval_loss": 0.47751283645629883, |
|
"eval_rouge1": 0.25892549839485435, |
|
"eval_rouge2": 0.06567851737773929, |
|
"eval_rougeL": 0.2580640243425909, |
|
"eval_runtime": 37.104, |
|
"eval_samples_per_second": 24.58, |
|
"eval_steps_per_second": 6.145, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 8.897679324894515e-06, |
|
"loss": 0.5153, |
|
"step": 2100 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 8.792194092827004e-06, |
|
"loss": 0.4908, |
|
"step": 2200 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 8.686708860759494e-06, |
|
"loss": 0.5025, |
|
"step": 2300 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 8.581223628691983e-06, |
|
"loss": 0.4811, |
|
"step": 2400 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 8.475738396624473e-06, |
|
"loss": 0.4832, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 8.371308016877637e-06, |
|
"loss": 0.483, |
|
"step": 2600 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 8.265822784810127e-06, |
|
"loss": 0.5024, |
|
"step": 2700 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 8.160337552742617e-06, |
|
"loss": 0.4867, |
|
"step": 2800 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 8.054852320675107e-06, |
|
"loss": 0.4941, |
|
"step": 2900 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 7.949367088607595e-06, |
|
"loss": 0.479, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"eval_loss": 0.46754053235054016, |
|
"eval_rouge1": 0.25667075818488366, |
|
"eval_rouge2": 0.06493933281502531, |
|
"eval_rougeL": 0.25610002044309327, |
|
"eval_runtime": 37.2336, |
|
"eval_samples_per_second": 24.494, |
|
"eval_steps_per_second": 6.123, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 7.843881856540085e-06, |
|
"loss": 0.486, |
|
"step": 3100 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 7.738396624472575e-06, |
|
"loss": 0.482, |
|
"step": 3200 |
|
}, |
|
{ |
|
"epoch": 1.57, |
|
"learning_rate": 7.632911392405063e-06, |
|
"loss": 0.4835, |
|
"step": 3300 |
|
}, |
|
{ |
|
"epoch": 1.61, |
|
"learning_rate": 7.528481012658229e-06, |
|
"loss": 0.4751, |
|
"step": 3400 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 7.4229957805907185e-06, |
|
"loss": 0.4689, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 7.3175105485232076e-06, |
|
"loss": 0.4885, |
|
"step": 3600 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 7.212025316455697e-06, |
|
"loss": 0.4845, |
|
"step": 3700 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 7.106540084388186e-06, |
|
"loss": 0.4868, |
|
"step": 3800 |
|
}, |
|
{ |
|
"epoch": 1.85, |
|
"learning_rate": 7.0010548523206756e-06, |
|
"loss": 0.4837, |
|
"step": 3900 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 6.8955696202531655e-06, |
|
"loss": 0.4883, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"eval_loss": 0.4646187722682953, |
|
"eval_rouge1": 0.26037312163956894, |
|
"eval_rouge2": 0.06617398820913363, |
|
"eval_rougeL": 0.259785770394323, |
|
"eval_runtime": 37.1142, |
|
"eval_samples_per_second": 24.573, |
|
"eval_steps_per_second": 6.143, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 6.7900843881856545e-06, |
|
"loss": 0.477, |
|
"step": 4100 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 6.684599156118144e-06, |
|
"loss": 0.4758, |
|
"step": 4200 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 6.579113924050633e-06, |
|
"loss": 0.4601, |
|
"step": 4300 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 6.4736286919831225e-06, |
|
"loss": 0.4536, |
|
"step": 4400 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 6.368143459915612e-06, |
|
"loss": 0.4747, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 2.18, |
|
"learning_rate": 6.2626582278481014e-06, |
|
"loss": 0.4501, |
|
"step": 4600 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 6.157172995780591e-06, |
|
"loss": 0.4679, |
|
"step": 4700 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 6.051687763713081e-06, |
|
"loss": 0.4581, |
|
"step": 4800 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 5.9462025316455694e-06, |
|
"loss": 0.459, |
|
"step": 4900 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 5.840717299578059e-06, |
|
"loss": 0.4514, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"eval_loss": 0.45936986804008484, |
|
"eval_rouge1": 0.26192596998518053, |
|
"eval_rouge2": 0.06934835885234081, |
|
"eval_rougeL": 0.2615379807814019, |
|
"eval_runtime": 37.1093, |
|
"eval_samples_per_second": 24.576, |
|
"eval_steps_per_second": 6.144, |
|
"step": 5000 |
|
} |
|
], |
|
"max_steps": 10530, |
|
"num_train_epochs": 5, |
|
"total_flos": 4.723756721661542e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|