|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"global_step": 1885630, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.9734863149186215e-05, |
|
"loss": 5.3726, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.946977933104586e-05, |
|
"loss": 3.517, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.920472202924222e-05, |
|
"loss": 2.957, |
|
"step": 30000 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.893963821110186e-05, |
|
"loss": 2.7004, |
|
"step": 40000 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.867460742563494e-05, |
|
"loss": 2.5453, |
|
"step": 50000 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.840955012383129e-05, |
|
"loss": 2.4342, |
|
"step": 60000 |
|
}, |
|
{ |
|
"epoch": 0.37, |
|
"learning_rate": 4.814446630569094e-05, |
|
"loss": 2.3507, |
|
"step": 70000 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 4.787943552022401e-05, |
|
"loss": 2.2903, |
|
"step": 80000 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.761437821842037e-05, |
|
"loss": 2.2356, |
|
"step": 90000 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 4.734934743295344e-05, |
|
"loss": 2.1933, |
|
"step": 100000 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 4.70842901311498e-05, |
|
"loss": 2.1565, |
|
"step": 110000 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 4.681923282934616e-05, |
|
"loss": 2.1247, |
|
"step": 120000 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 4.655417552754252e-05, |
|
"loss": 2.0947, |
|
"step": 130000 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 4.628909170940217e-05, |
|
"loss": 2.0742, |
|
"step": 140000 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.602403440759853e-05, |
|
"loss": 2.048, |
|
"step": 150000 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 4.575897710579488e-05, |
|
"loss": 2.0292, |
|
"step": 160000 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 4.5493893287654526e-05, |
|
"loss": 2.0091, |
|
"step": 170000 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 4.5228862502187606e-05, |
|
"loss": 1.9938, |
|
"step": 180000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_bleu": 27.6169, |
|
"eval_gen_len": 66.0246, |
|
"eval_loss": 2.0008087158203125, |
|
"eval_runtime": 2487.0668, |
|
"eval_samples_per_second": 6.902, |
|
"eval_steps_per_second": 0.431, |
|
"step": 188563 |
|
}, |
|
{ |
|
"epoch": 1.01, |
|
"learning_rate": 4.496380520038396e-05, |
|
"loss": 1.9756, |
|
"step": 190000 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 4.469874789858032e-05, |
|
"loss": 1.9481, |
|
"step": 200000 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 4.443369059677668e-05, |
|
"loss": 1.9385, |
|
"step": 210000 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 4.416865981130975e-05, |
|
"loss": 1.9268, |
|
"step": 220000 |
|
}, |
|
{ |
|
"epoch": 1.22, |
|
"learning_rate": 4.3903575993169396e-05, |
|
"loss": 1.9216, |
|
"step": 230000 |
|
}, |
|
{ |
|
"epoch": 1.27, |
|
"learning_rate": 4.363854520770247e-05, |
|
"loss": 1.9097, |
|
"step": 240000 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 4.337348790589882e-05, |
|
"loss": 1.8991, |
|
"step": 250000 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 4.31084571204319e-05, |
|
"loss": 1.8921, |
|
"step": 260000 |
|
}, |
|
{ |
|
"epoch": 1.43, |
|
"learning_rate": 4.284339981862826e-05, |
|
"loss": 1.8808, |
|
"step": 270000 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 4.2578342516824614e-05, |
|
"loss": 1.8733, |
|
"step": 280000 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 4.231331173135769e-05, |
|
"loss": 1.8671, |
|
"step": 290000 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 4.2048280945890766e-05, |
|
"loss": 1.8612, |
|
"step": 300000 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 4.178325016042384e-05, |
|
"loss": 1.8522, |
|
"step": 310000 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 4.151821937495691e-05, |
|
"loss": 1.8443, |
|
"step": 320000 |
|
}, |
|
{ |
|
"epoch": 1.75, |
|
"learning_rate": 4.125313555681656e-05, |
|
"loss": 1.8413, |
|
"step": 330000 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 4.098810477134963e-05, |
|
"loss": 1.8361, |
|
"step": 340000 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 4.0723073985882704e-05, |
|
"loss": 1.8276, |
|
"step": 350000 |
|
}, |
|
{ |
|
"epoch": 1.91, |
|
"learning_rate": 4.045801668407906e-05, |
|
"loss": 1.824, |
|
"step": 360000 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 4.0192985898612136e-05, |
|
"loss": 1.8171, |
|
"step": 370000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_bleu": 28.4709, |
|
"eval_gen_len": 65.8859, |
|
"eval_loss": 1.8752530813217163, |
|
"eval_runtime": 2537.4407, |
|
"eval_samples_per_second": 6.765, |
|
"eval_steps_per_second": 0.423, |
|
"step": 377126 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 3.9927928596808496e-05, |
|
"loss": 1.8061, |
|
"step": 380000 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 3.966289781134157e-05, |
|
"loss": 1.787, |
|
"step": 390000 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 3.939784050953793e-05, |
|
"loss": 1.7839, |
|
"step": 400000 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 3.9132809724071e-05, |
|
"loss": 1.7827, |
|
"step": 410000 |
|
}, |
|
{ |
|
"epoch": 2.23, |
|
"learning_rate": 3.886775242226736e-05, |
|
"loss": 1.7787, |
|
"step": 420000 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 3.860269512046372e-05, |
|
"loss": 1.776, |
|
"step": 430000 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 3.833763781866008e-05, |
|
"loss": 1.773, |
|
"step": 440000 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 3.807258051685644e-05, |
|
"loss": 1.7715, |
|
"step": 450000 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 3.78075232150528e-05, |
|
"loss": 1.7672, |
|
"step": 460000 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 3.754246591324915e-05, |
|
"loss": 1.764, |
|
"step": 470000 |
|
}, |
|
{ |
|
"epoch": 2.55, |
|
"learning_rate": 3.727740861144551e-05, |
|
"loss": 1.7602, |
|
"step": 480000 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 3.701235130964188e-05, |
|
"loss": 1.7608, |
|
"step": 490000 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 3.674729400783823e-05, |
|
"loss": 1.7564, |
|
"step": 500000 |
|
}, |
|
{ |
|
"epoch": 2.7, |
|
"learning_rate": 3.648223670603459e-05, |
|
"loss": 1.7532, |
|
"step": 510000 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 3.621720592056766e-05, |
|
"loss": 1.7479, |
|
"step": 520000 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 3.595214861876402e-05, |
|
"loss": 1.744, |
|
"step": 530000 |
|
}, |
|
{ |
|
"epoch": 2.86, |
|
"learning_rate": 3.568706480062367e-05, |
|
"loss": 1.744, |
|
"step": 540000 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 3.542203401515674e-05, |
|
"loss": 1.7409, |
|
"step": 550000 |
|
}, |
|
{ |
|
"epoch": 2.97, |
|
"learning_rate": 3.5156950197016386e-05, |
|
"loss": 1.7389, |
|
"step": 560000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_bleu": 28.9724, |
|
"eval_gen_len": 65.8601, |
|
"eval_loss": 1.8119513988494873, |
|
"eval_runtime": 2571.172, |
|
"eval_samples_per_second": 6.676, |
|
"eval_steps_per_second": 0.417, |
|
"step": 565689 |
|
}, |
|
{ |
|
"epoch": 3.02, |
|
"learning_rate": 3.489191941154946e-05, |
|
"loss": 1.7262, |
|
"step": 570000 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 3.462686210974582e-05, |
|
"loss": 1.711, |
|
"step": 580000 |
|
}, |
|
{ |
|
"epoch": 3.13, |
|
"learning_rate": 3.436183132427889e-05, |
|
"loss": 1.7129, |
|
"step": 590000 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 3.409674750613853e-05, |
|
"loss": 1.7137, |
|
"step": 600000 |
|
}, |
|
{ |
|
"epoch": 3.23, |
|
"learning_rate": 3.383166368799818e-05, |
|
"loss": 1.7105, |
|
"step": 610000 |
|
}, |
|
{ |
|
"epoch": 3.29, |
|
"learning_rate": 3.3566606386194536e-05, |
|
"loss": 1.7114, |
|
"step": 620000 |
|
}, |
|
{ |
|
"epoch": 3.34, |
|
"learning_rate": 3.3301549084390896e-05, |
|
"loss": 1.7078, |
|
"step": 630000 |
|
}, |
|
{ |
|
"epoch": 3.39, |
|
"learning_rate": 3.3036491782587255e-05, |
|
"loss": 1.7074, |
|
"step": 640000 |
|
}, |
|
{ |
|
"epoch": 3.45, |
|
"learning_rate": 3.2771434480783615e-05, |
|
"loss": 1.7052, |
|
"step": 650000 |
|
}, |
|
{ |
|
"epoch": 3.5, |
|
"learning_rate": 3.250637717897997e-05, |
|
"loss": 1.7038, |
|
"step": 660000 |
|
}, |
|
{ |
|
"epoch": 3.55, |
|
"learning_rate": 3.224131987717633e-05, |
|
"loss": 1.703, |
|
"step": 670000 |
|
}, |
|
{ |
|
"epoch": 3.61, |
|
"learning_rate": 3.1976262575372686e-05, |
|
"loss": 1.7015, |
|
"step": 680000 |
|
}, |
|
{ |
|
"epoch": 3.66, |
|
"learning_rate": 3.171120527356905e-05, |
|
"loss": 1.699, |
|
"step": 690000 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 3.144617448810212e-05, |
|
"loss": 1.6991, |
|
"step": 700000 |
|
}, |
|
{ |
|
"epoch": 3.77, |
|
"learning_rate": 3.1181090669961765e-05, |
|
"loss": 1.6956, |
|
"step": 710000 |
|
}, |
|
{ |
|
"epoch": 3.82, |
|
"learning_rate": 3.0916059884494844e-05, |
|
"loss": 1.6951, |
|
"step": 720000 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"learning_rate": 3.06510025826912e-05, |
|
"loss": 1.6925, |
|
"step": 730000 |
|
}, |
|
{ |
|
"epoch": 3.92, |
|
"learning_rate": 3.0385918764550843e-05, |
|
"loss": 1.6925, |
|
"step": 740000 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 3.0120887979083916e-05, |
|
"loss": 1.6893, |
|
"step": 750000 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_bleu": 29.5248, |
|
"eval_gen_len": 65.8846, |
|
"eval_loss": 1.7690072059631348, |
|
"eval_runtime": 2545.7813, |
|
"eval_samples_per_second": 6.743, |
|
"eval_steps_per_second": 0.421, |
|
"step": 754252 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 2.9855830677280272e-05, |
|
"loss": 1.6732, |
|
"step": 760000 |
|
}, |
|
{ |
|
"epoch": 4.08, |
|
"learning_rate": 2.959077337547663e-05, |
|
"loss": 1.6653, |
|
"step": 770000 |
|
}, |
|
{ |
|
"epoch": 4.14, |
|
"learning_rate": 2.9325716073672994e-05, |
|
"loss": 1.6672, |
|
"step": 780000 |
|
}, |
|
{ |
|
"epoch": 4.19, |
|
"learning_rate": 2.9060658771869347e-05, |
|
"loss": 1.667, |
|
"step": 790000 |
|
}, |
|
{ |
|
"epoch": 4.24, |
|
"learning_rate": 2.8795574953728993e-05, |
|
"loss": 1.6665, |
|
"step": 800000 |
|
}, |
|
{ |
|
"epoch": 4.3, |
|
"learning_rate": 2.8530517651925353e-05, |
|
"loss": 1.6661, |
|
"step": 810000 |
|
}, |
|
{ |
|
"epoch": 4.35, |
|
"learning_rate": 2.8265433833785e-05, |
|
"loss": 1.6656, |
|
"step": 820000 |
|
}, |
|
{ |
|
"epoch": 4.4, |
|
"learning_rate": 2.8000403048318068e-05, |
|
"loss": 1.666, |
|
"step": 830000 |
|
}, |
|
{ |
|
"epoch": 4.45, |
|
"learning_rate": 2.773534574651443e-05, |
|
"loss": 1.6629, |
|
"step": 840000 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 2.747028844471079e-05, |
|
"loss": 1.6648, |
|
"step": 850000 |
|
}, |
|
{ |
|
"epoch": 4.56, |
|
"learning_rate": 2.720520462657043e-05, |
|
"loss": 1.6633, |
|
"step": 860000 |
|
}, |
|
{ |
|
"epoch": 4.61, |
|
"learning_rate": 2.694014732476679e-05, |
|
"loss": 1.6631, |
|
"step": 870000 |
|
}, |
|
{ |
|
"epoch": 4.67, |
|
"learning_rate": 2.6675090022963152e-05, |
|
"loss": 1.6616, |
|
"step": 880000 |
|
}, |
|
{ |
|
"epoch": 4.72, |
|
"learning_rate": 2.641000620482279e-05, |
|
"loss": 1.6594, |
|
"step": 890000 |
|
}, |
|
{ |
|
"epoch": 4.77, |
|
"learning_rate": 2.614494890301915e-05, |
|
"loss": 1.6588, |
|
"step": 900000 |
|
}, |
|
{ |
|
"epoch": 4.83, |
|
"learning_rate": 2.5879865084878797e-05, |
|
"loss": 1.6582, |
|
"step": 910000 |
|
}, |
|
{ |
|
"epoch": 4.88, |
|
"learning_rate": 2.5614834299411866e-05, |
|
"loss": 1.6569, |
|
"step": 920000 |
|
}, |
|
{ |
|
"epoch": 4.93, |
|
"learning_rate": 2.5349750481271512e-05, |
|
"loss": 1.6539, |
|
"step": 930000 |
|
}, |
|
{ |
|
"epoch": 4.99, |
|
"learning_rate": 2.508471969580459e-05, |
|
"loss": 1.6559, |
|
"step": 940000 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_bleu": 29.5757, |
|
"eval_gen_len": 65.8046, |
|
"eval_loss": 1.7467188835144043, |
|
"eval_runtime": 2534.3035, |
|
"eval_samples_per_second": 6.773, |
|
"eval_steps_per_second": 0.423, |
|
"step": 942815 |
|
}, |
|
{ |
|
"epoch": 5.04, |
|
"learning_rate": 2.4819635877664228e-05, |
|
"loss": 1.6372, |
|
"step": 950000 |
|
}, |
|
{ |
|
"epoch": 5.09, |
|
"learning_rate": 2.455457857586059e-05, |
|
"loss": 1.6316, |
|
"step": 960000 |
|
}, |
|
{ |
|
"epoch": 5.14, |
|
"learning_rate": 2.4289494757720233e-05, |
|
"loss": 1.6343, |
|
"step": 970000 |
|
}, |
|
{ |
|
"epoch": 5.2, |
|
"learning_rate": 2.4024463972253306e-05, |
|
"loss": 1.6344, |
|
"step": 980000 |
|
}, |
|
{ |
|
"epoch": 5.25, |
|
"learning_rate": 2.3759406670449666e-05, |
|
"loss": 1.6345, |
|
"step": 990000 |
|
}, |
|
{ |
|
"epoch": 5.3, |
|
"learning_rate": 2.3494349368646025e-05, |
|
"loss": 1.6343, |
|
"step": 1000000 |
|
}, |
|
{ |
|
"epoch": 5.36, |
|
"learning_rate": 2.322929206684238e-05, |
|
"loss": 1.6353, |
|
"step": 1010000 |
|
}, |
|
{ |
|
"epoch": 5.41, |
|
"learning_rate": 2.296423476503874e-05, |
|
"loss": 1.6329, |
|
"step": 1020000 |
|
}, |
|
{ |
|
"epoch": 5.46, |
|
"learning_rate": 2.26991774632351e-05, |
|
"loss": 1.6338, |
|
"step": 1030000 |
|
}, |
|
{ |
|
"epoch": 5.52, |
|
"learning_rate": 2.2434093645094746e-05, |
|
"loss": 1.6341, |
|
"step": 1040000 |
|
}, |
|
{ |
|
"epoch": 5.57, |
|
"learning_rate": 2.216906285962782e-05, |
|
"loss": 1.633, |
|
"step": 1050000 |
|
}, |
|
{ |
|
"epoch": 5.62, |
|
"learning_rate": 2.1904005557824175e-05, |
|
"loss": 1.6322, |
|
"step": 1060000 |
|
}, |
|
{ |
|
"epoch": 5.67, |
|
"learning_rate": 2.163892173968382e-05, |
|
"loss": 1.6314, |
|
"step": 1070000 |
|
}, |
|
{ |
|
"epoch": 5.73, |
|
"learning_rate": 2.1373864437880177e-05, |
|
"loss": 1.6301, |
|
"step": 1080000 |
|
}, |
|
{ |
|
"epoch": 5.78, |
|
"learning_rate": 2.110880713607654e-05, |
|
"loss": 1.6313, |
|
"step": 1090000 |
|
}, |
|
{ |
|
"epoch": 5.83, |
|
"learning_rate": 2.0843749834272896e-05, |
|
"loss": 1.6313, |
|
"step": 1100000 |
|
}, |
|
{ |
|
"epoch": 5.89, |
|
"learning_rate": 2.057871904880597e-05, |
|
"loss": 1.6291, |
|
"step": 1110000 |
|
}, |
|
{ |
|
"epoch": 5.94, |
|
"learning_rate": 2.0313635230665615e-05, |
|
"loss": 1.627, |
|
"step": 1120000 |
|
}, |
|
{ |
|
"epoch": 5.99, |
|
"learning_rate": 2.0048604445198688e-05, |
|
"loss": 1.6279, |
|
"step": 1130000 |
|
}, |
|
{ |
|
"epoch": 6.0, |
|
"eval_bleu": 29.7512, |
|
"eval_gen_len": 66.0482, |
|
"eval_loss": 1.7236360311508179, |
|
"eval_runtime": 2786.837, |
|
"eval_samples_per_second": 6.159, |
|
"eval_steps_per_second": 0.385, |
|
"step": 1131378 |
|
}, |
|
{ |
|
"epoch": 6.05, |
|
"learning_rate": 1.9783520627058334e-05, |
|
"loss": 1.6085, |
|
"step": 1140000 |
|
}, |
|
{ |
|
"epoch": 6.1, |
|
"learning_rate": 1.9518489841591407e-05, |
|
"loss": 1.6066, |
|
"step": 1150000 |
|
}, |
|
{ |
|
"epoch": 6.15, |
|
"learning_rate": 1.9253432539787763e-05, |
|
"loss": 1.6079, |
|
"step": 1160000 |
|
}, |
|
{ |
|
"epoch": 6.2, |
|
"learning_rate": 1.8988375237984123e-05, |
|
"loss": 1.6108, |
|
"step": 1170000 |
|
}, |
|
{ |
|
"epoch": 6.26, |
|
"learning_rate": 1.8723317936180482e-05, |
|
"loss": 1.6083, |
|
"step": 1180000 |
|
}, |
|
{ |
|
"epoch": 6.31, |
|
"learning_rate": 1.8458234118040125e-05, |
|
"loss": 1.6082, |
|
"step": 1190000 |
|
}, |
|
{ |
|
"epoch": 6.36, |
|
"learning_rate": 1.8193176816236484e-05, |
|
"loss": 1.61, |
|
"step": 1200000 |
|
}, |
|
{ |
|
"epoch": 6.42, |
|
"learning_rate": 1.7928119514432844e-05, |
|
"loss": 1.6092, |
|
"step": 1210000 |
|
}, |
|
{ |
|
"epoch": 6.47, |
|
"learning_rate": 1.7663062212629203e-05, |
|
"loss": 1.6093, |
|
"step": 1220000 |
|
}, |
|
{ |
|
"epoch": 6.52, |
|
"learning_rate": 1.7397978394488846e-05, |
|
"loss": 1.6106, |
|
"step": 1230000 |
|
}, |
|
{ |
|
"epoch": 6.58, |
|
"learning_rate": 1.7132921092685202e-05, |
|
"loss": 1.6084, |
|
"step": 1240000 |
|
}, |
|
{ |
|
"epoch": 6.63, |
|
"learning_rate": 1.6867863790881565e-05, |
|
"loss": 1.6094, |
|
"step": 1250000 |
|
}, |
|
{ |
|
"epoch": 6.68, |
|
"learning_rate": 1.6602779972741207e-05, |
|
"loss": 1.6069, |
|
"step": 1260000 |
|
}, |
|
{ |
|
"epoch": 6.74, |
|
"learning_rate": 1.633774918727428e-05, |
|
"loss": 1.6069, |
|
"step": 1270000 |
|
}, |
|
{ |
|
"epoch": 6.79, |
|
"learning_rate": 1.6072665369133923e-05, |
|
"loss": 1.6075, |
|
"step": 1280000 |
|
}, |
|
{ |
|
"epoch": 6.84, |
|
"learning_rate": 1.5807608067330283e-05, |
|
"loss": 1.6051, |
|
"step": 1290000 |
|
}, |
|
{ |
|
"epoch": 6.89, |
|
"learning_rate": 1.5542550765526642e-05, |
|
"loss": 1.6044, |
|
"step": 1300000 |
|
}, |
|
{ |
|
"epoch": 6.95, |
|
"learning_rate": 1.5277493463723e-05, |
|
"loss": 1.6053, |
|
"step": 1310000 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"eval_bleu": 29.916, |
|
"eval_gen_len": 66.0031, |
|
"eval_loss": 1.7136626243591309, |
|
"eval_runtime": 2659.0199, |
|
"eval_samples_per_second": 6.455, |
|
"eval_steps_per_second": 0.404, |
|
"step": 1319941 |
|
}, |
|
{ |
|
"epoch": 7.0, |
|
"learning_rate": 1.5012436161919361e-05, |
|
"loss": 1.6068, |
|
"step": 1320000 |
|
}, |
|
{ |
|
"epoch": 7.05, |
|
"learning_rate": 1.4747378860115719e-05, |
|
"loss": 1.5851, |
|
"step": 1330000 |
|
}, |
|
{ |
|
"epoch": 7.11, |
|
"learning_rate": 1.4482321558312076e-05, |
|
"loss": 1.5864, |
|
"step": 1340000 |
|
}, |
|
{ |
|
"epoch": 7.16, |
|
"learning_rate": 1.4217264256508436e-05, |
|
"loss": 1.5865, |
|
"step": 1350000 |
|
}, |
|
{ |
|
"epoch": 7.21, |
|
"learning_rate": 1.3952206954704794e-05, |
|
"loss": 1.5866, |
|
"step": 1360000 |
|
}, |
|
{ |
|
"epoch": 7.27, |
|
"learning_rate": 1.3687149652901151e-05, |
|
"loss": 1.589, |
|
"step": 1370000 |
|
}, |
|
{ |
|
"epoch": 7.32, |
|
"learning_rate": 1.3422092351097513e-05, |
|
"loss": 1.5885, |
|
"step": 1380000 |
|
}, |
|
{ |
|
"epoch": 7.37, |
|
"learning_rate": 1.315703504929387e-05, |
|
"loss": 1.589, |
|
"step": 1390000 |
|
}, |
|
{ |
|
"epoch": 7.42, |
|
"learning_rate": 1.2891951231153515e-05, |
|
"loss": 1.5882, |
|
"step": 1400000 |
|
}, |
|
{ |
|
"epoch": 7.48, |
|
"learning_rate": 1.2626893929349873e-05, |
|
"loss": 1.5897, |
|
"step": 1410000 |
|
}, |
|
{ |
|
"epoch": 7.53, |
|
"learning_rate": 1.2361836627546232e-05, |
|
"loss": 1.5868, |
|
"step": 1420000 |
|
}, |
|
{ |
|
"epoch": 7.58, |
|
"learning_rate": 1.2096805842079307e-05, |
|
"loss": 1.5884, |
|
"step": 1430000 |
|
}, |
|
{ |
|
"epoch": 7.64, |
|
"learning_rate": 1.1831748540275664e-05, |
|
"loss": 1.5896, |
|
"step": 1440000 |
|
}, |
|
{ |
|
"epoch": 7.69, |
|
"learning_rate": 1.1566664722135307e-05, |
|
"loss": 1.5874, |
|
"step": 1450000 |
|
}, |
|
{ |
|
"epoch": 7.74, |
|
"learning_rate": 1.1301633936668382e-05, |
|
"loss": 1.5874, |
|
"step": 1460000 |
|
}, |
|
{ |
|
"epoch": 7.8, |
|
"learning_rate": 1.1036576634864741e-05, |
|
"loss": 1.5878, |
|
"step": 1470000 |
|
}, |
|
{ |
|
"epoch": 7.85, |
|
"learning_rate": 1.0771492816724385e-05, |
|
"loss": 1.5864, |
|
"step": 1480000 |
|
}, |
|
{ |
|
"epoch": 7.9, |
|
"learning_rate": 1.0506408998584028e-05, |
|
"loss": 1.5848, |
|
"step": 1490000 |
|
}, |
|
{ |
|
"epoch": 7.95, |
|
"learning_rate": 1.0241351696780386e-05, |
|
"loss": 1.5871, |
|
"step": 1500000 |
|
}, |
|
{ |
|
"epoch": 8.0, |
|
"eval_bleu": 30.1671, |
|
"eval_gen_len": 65.8853, |
|
"eval_loss": 1.7006529569625854, |
|
"eval_runtime": 2553.3513, |
|
"eval_samples_per_second": 6.723, |
|
"eval_steps_per_second": 0.42, |
|
"step": 1508504 |
|
}, |
|
{ |
|
"epoch": 8.01, |
|
"learning_rate": 9.97626787864003e-06, |
|
"loss": 1.582, |
|
"step": 1510000 |
|
}, |
|
{ |
|
"epoch": 8.06, |
|
"learning_rate": 9.711237093173105e-06, |
|
"loss": 1.5691, |
|
"step": 1520000 |
|
}, |
|
{ |
|
"epoch": 8.11, |
|
"learning_rate": 9.446153275032749e-06, |
|
"loss": 1.5695, |
|
"step": 1530000 |
|
}, |
|
{ |
|
"epoch": 8.17, |
|
"learning_rate": 9.181095973229107e-06, |
|
"loss": 1.5702, |
|
"step": 1540000 |
|
}, |
|
{ |
|
"epoch": 8.22, |
|
"learning_rate": 8.91601215508875e-06, |
|
"loss": 1.5701, |
|
"step": 1550000 |
|
}, |
|
{ |
|
"epoch": 8.27, |
|
"learning_rate": 8.650954853285109e-06, |
|
"loss": 1.5711, |
|
"step": 1560000 |
|
}, |
|
{ |
|
"epoch": 8.33, |
|
"learning_rate": 8.385897551481469e-06, |
|
"loss": 1.5693, |
|
"step": 1570000 |
|
}, |
|
{ |
|
"epoch": 8.38, |
|
"learning_rate": 8.120840249677828e-06, |
|
"loss": 1.5703, |
|
"step": 1580000 |
|
}, |
|
{ |
|
"epoch": 8.43, |
|
"learning_rate": 7.855809464210901e-06, |
|
"loss": 1.571, |
|
"step": 1590000 |
|
}, |
|
{ |
|
"epoch": 8.49, |
|
"learning_rate": 7.5907521624072595e-06, |
|
"loss": 1.5709, |
|
"step": 1600000 |
|
}, |
|
{ |
|
"epoch": 8.54, |
|
"learning_rate": 7.325694860603618e-06, |
|
"loss": 1.5698, |
|
"step": 1610000 |
|
}, |
|
{ |
|
"epoch": 8.59, |
|
"learning_rate": 7.0606110424632625e-06, |
|
"loss": 1.5716, |
|
"step": 1620000 |
|
}, |
|
{ |
|
"epoch": 8.64, |
|
"learning_rate": 6.79555374065962e-06, |
|
"loss": 1.5702, |
|
"step": 1630000 |
|
}, |
|
{ |
|
"epoch": 8.7, |
|
"learning_rate": 6.530496438855979e-06, |
|
"loss": 1.5698, |
|
"step": 1640000 |
|
}, |
|
{ |
|
"epoch": 8.75, |
|
"learning_rate": 6.265439137052338e-06, |
|
"loss": 1.5699, |
|
"step": 1650000 |
|
}, |
|
{ |
|
"epoch": 8.8, |
|
"learning_rate": 6.000381835248697e-06, |
|
"loss": 1.5683, |
|
"step": 1660000 |
|
}, |
|
{ |
|
"epoch": 8.86, |
|
"learning_rate": 5.735351049781771e-06, |
|
"loss": 1.5683, |
|
"step": 1670000 |
|
}, |
|
{ |
|
"epoch": 8.91, |
|
"learning_rate": 5.470267231641415e-06, |
|
"loss": 1.5701, |
|
"step": 1680000 |
|
}, |
|
{ |
|
"epoch": 8.96, |
|
"learning_rate": 5.205236446174489e-06, |
|
"loss": 1.5694, |
|
"step": 1690000 |
|
}, |
|
{ |
|
"epoch": 9.0, |
|
"eval_bleu": 30.3613, |
|
"eval_gen_len": 65.9506, |
|
"eval_loss": 1.692053198814392, |
|
"eval_runtime": 2749.5168, |
|
"eval_samples_per_second": 6.243, |
|
"eval_steps_per_second": 0.39, |
|
"step": 1697067 |
|
}, |
|
{ |
|
"epoch": 9.02, |
|
"learning_rate": 4.940126111697417e-06, |
|
"loss": 1.5631, |
|
"step": 1700000 |
|
}, |
|
{ |
|
"epoch": 9.07, |
|
"learning_rate": 4.675095326230491e-06, |
|
"loss": 1.5545, |
|
"step": 1710000 |
|
}, |
|
{ |
|
"epoch": 9.12, |
|
"learning_rate": 4.4100380244268495e-06, |
|
"loss": 1.554, |
|
"step": 1720000 |
|
}, |
|
{ |
|
"epoch": 9.17, |
|
"learning_rate": 4.144980722623208e-06, |
|
"loss": 1.5572, |
|
"step": 1730000 |
|
}, |
|
{ |
|
"epoch": 9.23, |
|
"learning_rate": 3.879896904482852e-06, |
|
"loss": 1.5576, |
|
"step": 1740000 |
|
}, |
|
{ |
|
"epoch": 9.28, |
|
"learning_rate": 3.614866119015926e-06, |
|
"loss": 1.5542, |
|
"step": 1750000 |
|
}, |
|
{ |
|
"epoch": 9.33, |
|
"learning_rate": 3.3497823008755693e-06, |
|
"loss": 1.5546, |
|
"step": 1760000 |
|
}, |
|
{ |
|
"epoch": 9.39, |
|
"learning_rate": 3.0847249990719284e-06, |
|
"loss": 1.5557, |
|
"step": 1770000 |
|
}, |
|
{ |
|
"epoch": 9.44, |
|
"learning_rate": 2.819667697268287e-06, |
|
"loss": 1.5561, |
|
"step": 1780000 |
|
}, |
|
{ |
|
"epoch": 9.49, |
|
"learning_rate": 2.554583879127931e-06, |
|
"loss": 1.5553, |
|
"step": 1790000 |
|
}, |
|
{ |
|
"epoch": 9.55, |
|
"learning_rate": 2.2895530936610047e-06, |
|
"loss": 1.5558, |
|
"step": 1800000 |
|
}, |
|
{ |
|
"epoch": 9.6, |
|
"learning_rate": 2.0244957918573637e-06, |
|
"loss": 1.554, |
|
"step": 1810000 |
|
}, |
|
{ |
|
"epoch": 9.65, |
|
"learning_rate": 1.759411973717007e-06, |
|
"loss": 1.5543, |
|
"step": 1820000 |
|
}, |
|
{ |
|
"epoch": 9.7, |
|
"learning_rate": 1.494381188250081e-06, |
|
"loss": 1.5553, |
|
"step": 1830000 |
|
}, |
|
{ |
|
"epoch": 9.76, |
|
"learning_rate": 1.2292973701097247e-06, |
|
"loss": 1.5543, |
|
"step": 1840000 |
|
}, |
|
{ |
|
"epoch": 9.81, |
|
"learning_rate": 9.642665846427986e-07, |
|
"loss": 1.5546, |
|
"step": 1850000 |
|
}, |
|
{ |
|
"epoch": 9.86, |
|
"learning_rate": 6.992092828391572e-07, |
|
"loss": 1.5534, |
|
"step": 1860000 |
|
}, |
|
{ |
|
"epoch": 9.92, |
|
"learning_rate": 4.3415198103551603e-07, |
|
"loss": 1.5536, |
|
"step": 1870000 |
|
}, |
|
{ |
|
"epoch": 9.97, |
|
"learning_rate": 1.690681628951597e-07, |
|
"loss": 1.5539, |
|
"step": 1880000 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"eval_bleu": 30.4049, |
|
"eval_gen_len": 66.0487, |
|
"eval_loss": 1.6851532459259033, |
|
"eval_runtime": 2548.9872, |
|
"eval_samples_per_second": 6.734, |
|
"eval_steps_per_second": 0.421, |
|
"step": 1885630 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"step": 1885630, |
|
"total_flos": 5.018247011089908e+18, |
|
"train_loss": 1.743612184965204, |
|
"train_runtime": 420652.6588, |
|
"train_samples_per_second": 215.166, |
|
"train_steps_per_second": 4.483 |
|
} |
|
], |
|
"max_steps": 1885630, |
|
"num_train_epochs": 10, |
|
"total_flos": 5.018247011089908e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|