| { | |
| "best_metric": 0.2722427248954773, | |
| "best_model_checkpoint": "./ckpt/roberta/checkpoint-4000", | |
| "epoch": 4.999781452611641, | |
| "global_step": 17155, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.971728359078986e-05, | |
| "loss": 0.5548, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.94258233751093e-05, | |
| "loss": 0.324, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.9134363159428745e-05, | |
| "loss": 0.2765, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.8842902943748184e-05, | |
| "loss": 0.2655, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.855144272806762e-05, | |
| "loss": 0.26, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.825998251238706e-05, | |
| "loss": 0.2628, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.79685222967065e-05, | |
| "loss": 0.2509, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.767706208102594e-05, | |
| "loss": 0.2694, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.738851646750219e-05, | |
| "loss": 0.284, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.709705625182163e-05, | |
| "loss": 0.2776, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.6805596036141067e-05, | |
| "loss": 0.253, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.6514135820460505e-05, | |
| "loss": 0.2577, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.622267560477995e-05, | |
| "loss": 0.2303, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.593121538909939e-05, | |
| "loss": 0.2214, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.563975517341883e-05, | |
| "loss": 0.2257, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.534829495773827e-05, | |
| "loss": 0.2346, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.505683474205771e-05, | |
| "loss": 0.235, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.476537452637715e-05, | |
| "loss": 0.213, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.447391431069659e-05, | |
| "loss": 0.2286, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.4182454095016036e-05, | |
| "loss": 0.2234, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.9075907468795776, | |
| "eval_loss": 0.29963451623916626, | |
| "eval_runtime": 35.4657, | |
| "eval_samples_per_second": 375.913, | |
| "eval_steps_per_second": 47.003, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.3890993879335475e-05, | |
| "loss": 0.2158, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.3599533663654914e-05, | |
| "loss": 0.1989, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 4.330807344797435e-05, | |
| "loss": 0.2229, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.30166132322938e-05, | |
| "loss": 0.2195, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.272515301661324e-05, | |
| "loss": 0.2054, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.2433692800932676e-05, | |
| "loss": 0.2046, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 4.2142232585252115e-05, | |
| "loss": 0.2019, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 4.185077236957155e-05, | |
| "loss": 0.2014, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.155931215389099e-05, | |
| "loss": 0.2043, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.126785193821044e-05, | |
| "loss": 0.1872, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.0976391722529877e-05, | |
| "loss": 0.1975, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.0684931506849315e-05, | |
| "loss": 0.1949, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.0393471291168754e-05, | |
| "loss": 0.2153, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.01020110754882e-05, | |
| "loss": 0.2092, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.981055085980764e-05, | |
| "loss": 0.2024, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.952200524628388e-05, | |
| "loss": 0.1814, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.923054503060332e-05, | |
| "loss": 0.1695, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.8939084814922766e-05, | |
| "loss": 0.1808, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.8647624599242205e-05, | |
| "loss": 0.161, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.8356164383561644e-05, | |
| "loss": 0.1851, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_accuracy": 0.9154665470123291, | |
| "eval_loss": 0.2722427248954773, | |
| "eval_runtime": 35.4783, | |
| "eval_samples_per_second": 375.779, | |
| "eval_steps_per_second": 46.986, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.806470416788109e-05, | |
| "loss": 0.1787, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.777324395220053e-05, | |
| "loss": 0.1572, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.748178373651997e-05, | |
| "loss": 0.1825, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.719032352083941e-05, | |
| "loss": 0.1839, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.689886330515885e-05, | |
| "loss": 0.1584, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 3.660740308947829e-05, | |
| "loss": 0.1719, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.631594287379773e-05, | |
| "loss": 0.1792, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3.602448265811717e-05, | |
| "loss": 0.1695, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 3.5733022442436606e-05, | |
| "loss": 0.1661, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 3.5441562226756045e-05, | |
| "loss": 0.1797, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 3.515010201107549e-05, | |
| "loss": 0.1666, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 3.485864179539493e-05, | |
| "loss": 0.1768, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 3.456718157971437e-05, | |
| "loss": 0.1662, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 3.4275721364033814e-05, | |
| "loss": 0.177, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.398426114835325e-05, | |
| "loss": 0.1734, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 3.369280093267269e-05, | |
| "loss": 0.1749, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 3.340134071699213e-05, | |
| "loss": 0.1767, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 3.3109880501311576e-05, | |
| "loss": 0.1541, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 3.2818420285631015e-05, | |
| "loss": 0.1706, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.2526960069950453e-05, | |
| "loss": 0.1757, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.9202670454978943, | |
| "eval_loss": 0.28923019766807556, | |
| "eval_runtime": 35.505, | |
| "eval_samples_per_second": 375.497, | |
| "eval_steps_per_second": 46.951, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 3.22354998542699e-05, | |
| "loss": 0.1796, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 3.194403963858934e-05, | |
| "loss": 0.187, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 3.165257942290878e-05, | |
| "loss": 0.1651, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 3.136403380938502e-05, | |
| "loss": 0.1675, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 3.1072573593704465e-05, | |
| "loss": 0.1532, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.0781113378023904e-05, | |
| "loss": 0.1652, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.048965316234334e-05, | |
| "loss": 0.1657, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 3.0198192946662785e-05, | |
| "loss": 0.1477, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 2.9906732730982224e-05, | |
| "loss": 0.1589, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 2.9615272515301663e-05, | |
| "loss": 0.1383, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 2.93238122996211e-05, | |
| "loss": 0.1553, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 2.9032352083940544e-05, | |
| "loss": 0.1275, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 2.8740891868259982e-05, | |
| "loss": 0.1447, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 2.844943165257942e-05, | |
| "loss": 0.1399, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 2.8157971436898867e-05, | |
| "loss": 0.1383, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.7866511221218306e-05, | |
| "loss": 0.1453, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 2.7575051005537744e-05, | |
| "loss": 0.139, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 2.728359078985719e-05, | |
| "loss": 0.1262, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 2.699213057417663e-05, | |
| "loss": 0.1298, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 2.6700670358496068e-05, | |
| "loss": 0.1274, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_accuracy": 0.9189168810844421, | |
| "eval_loss": 0.35566407442092896, | |
| "eval_runtime": 35.4775, | |
| "eval_samples_per_second": 375.788, | |
| "eval_steps_per_second": 46.988, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 2.6409210142815503e-05, | |
| "loss": 0.1338, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 2.611774992713495e-05, | |
| "loss": 0.133, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 2.5826289711454387e-05, | |
| "loss": 0.1295, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.5534829495773826e-05, | |
| "loss": 0.1493, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 2.5243369280093272e-05, | |
| "loss": 0.1317, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 2.495190906441271e-05, | |
| "loss": 0.1327, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 2.466044884873215e-05, | |
| "loss": 0.1458, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.4371903235208396e-05, | |
| "loss": 0.1321, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 2.59, | |
| "learning_rate": 2.4080443019527835e-05, | |
| "loss": 0.1325, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.3788982803847277e-05, | |
| "loss": 0.1427, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.349752258816672e-05, | |
| "loss": 0.1174, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.3206062372486158e-05, | |
| "loss": 0.1368, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.2914602156805597e-05, | |
| "loss": 0.1305, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 2.2626056543281843e-05, | |
| "loss": 0.1335, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 2.2334596327601285e-05, | |
| "loss": 0.1331, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.2043136111920724e-05, | |
| "loss": 0.1528, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 2.1751675896240163e-05, | |
| "loss": 0.1332, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 2.1460215680559602e-05, | |
| "loss": 0.1454, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.1168755464879044e-05, | |
| "loss": 0.1472, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.0877295249198486e-05, | |
| "loss": 0.1361, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_accuracy": 0.9194419384002686, | |
| "eval_loss": 0.2857810854911804, | |
| "eval_runtime": 35.5011, | |
| "eval_samples_per_second": 375.538, | |
| "eval_steps_per_second": 46.956, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 2.0585835033517925e-05, | |
| "loss": 0.1261, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 2.0294374817837367e-05, | |
| "loss": 0.1416, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.0002914602156806e-05, | |
| "loss": 0.143, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 1.9711454386476248e-05, | |
| "loss": 0.1101, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 1.9419994170795687e-05, | |
| "loss": 0.1076, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 1.9128533955115126e-05, | |
| "loss": 0.0947, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 1.8837073739434568e-05, | |
| "loss": 0.1009, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 1.8545613523754007e-05, | |
| "loss": 0.1013, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 1.825415330807345e-05, | |
| "loss": 0.1108, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 1.796269309239289e-05, | |
| "loss": 0.1092, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 1.767123287671233e-05, | |
| "loss": 0.1184, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 1.7379772661031772e-05, | |
| "loss": 0.0937, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "learning_rate": 1.708831244535121e-05, | |
| "loss": 0.1137, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 1.679685222967065e-05, | |
| "loss": 0.0975, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 1.6505392013990092e-05, | |
| "loss": 0.1147, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 1.621393179830953e-05, | |
| "loss": 0.0951, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 1.5922471582628973e-05, | |
| "loss": 0.1167, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 1.5633925969105216e-05, | |
| "loss": 0.1264, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 1.5342465753424658e-05, | |
| "loss": 0.1105, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 1.5051005537744099e-05, | |
| "loss": 0.0935, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "eval_accuracy": 0.9215421676635742, | |
| "eval_loss": 0.33558839559555054, | |
| "eval_runtime": 35.5063, | |
| "eval_samples_per_second": 375.483, | |
| "eval_steps_per_second": 46.949, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 1.4759545322063539e-05, | |
| "loss": 0.1137, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.4468085106382978e-05, | |
| "loss": 0.0945, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 1.417662489070242e-05, | |
| "loss": 0.1118, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 1.388516467502186e-05, | |
| "loss": 0.1174, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 1.35937044593413e-05, | |
| "loss": 0.0992, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 1.3302244243660742e-05, | |
| "loss": 0.1068, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.301078402798018e-05, | |
| "loss": 0.1098, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.2719323812299621e-05, | |
| "loss": 0.1126, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 1.2427863596619061e-05, | |
| "loss": 0.1119, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.2136403380938502e-05, | |
| "loss": 0.0936, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 1.1844943165257944e-05, | |
| "loss": 0.0995, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 1.1553482949577383e-05, | |
| "loss": 0.1152, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 1.126493733605363e-05, | |
| "loss": 0.1191, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 1.097347712037307e-05, | |
| "loss": 0.1116, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 1.068201690469251e-05, | |
| "loss": 0.115, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 1.039055668901195e-05, | |
| "loss": 0.1026, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 1.009909647333139e-05, | |
| "loss": 0.0919, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 4.02, | |
| "learning_rate": 9.80763625765083e-06, | |
| "loss": 0.0885, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 9.516176041970272e-06, | |
| "loss": 0.0731, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 9.224715826289713e-06, | |
| "loss": 0.077, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_accuracy": 0.9283678531646729, | |
| "eval_loss": 0.3291896879673004, | |
| "eval_runtime": 35.4606, | |
| "eval_samples_per_second": 375.967, | |
| "eval_steps_per_second": 47.01, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "learning_rate": 8.933255610609152e-06, | |
| "loss": 0.0731, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 8.641795394928592e-06, | |
| "loss": 0.0821, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 8.350335179248033e-06, | |
| "loss": 0.0879, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 8.058874963567475e-06, | |
| "loss": 0.082, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 7.767414747886914e-06, | |
| "loss": 0.0851, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 7.475954532206354e-06, | |
| "loss": 0.0922, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 4.28, | |
| "learning_rate": 7.1844943165257946e-06, | |
| "loss": 0.0831, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 6.893034100845234e-06, | |
| "loss": 0.0817, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 6.601573885164675e-06, | |
| "loss": 0.0826, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 6.310113669484116e-06, | |
| "loss": 0.0926, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 6.0186534538035565e-06, | |
| "loss": 0.0829, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 4.43, | |
| "learning_rate": 5.727193238122996e-06, | |
| "loss": 0.0874, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 5.435733022442437e-06, | |
| "loss": 0.078, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 5.144272806761877e-06, | |
| "loss": 0.0964, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 4.852812591081318e-06, | |
| "loss": 0.0759, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 4.561352375400757e-06, | |
| "loss": 0.0996, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 4.58, | |
| "learning_rate": 4.269892159720199e-06, | |
| "loss": 0.0835, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 3.978431944039638e-06, | |
| "loss": 0.0869, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 3.6869717283590797e-06, | |
| "loss": 0.0837, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 3.3955115126785197e-06, | |
| "loss": 0.0687, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "eval_accuracy": 0.9291929006576538, | |
| "eval_loss": 0.31212949752807617, | |
| "eval_runtime": 35.4974, | |
| "eval_samples_per_second": 375.577, | |
| "eval_steps_per_second": 46.961, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "learning_rate": 3.1040512969979602e-06, | |
| "loss": 0.0854, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 2.8125910813174003e-06, | |
| "loss": 0.0704, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 2.521130865636841e-06, | |
| "loss": 0.0792, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 2.2296706499562813e-06, | |
| "loss": 0.0777, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 1.9382104342757214e-06, | |
| "loss": 0.0902, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 1.6467502185951619e-06, | |
| "loss": 0.0801, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 1.3552900029146024e-06, | |
| "loss": 0.0896, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 1.0638297872340427e-06, | |
| "loss": 0.0772, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 7.723695715534829e-07, | |
| "loss": 0.0716, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "learning_rate": 4.809093558729233e-07, | |
| "loss": 0.0658, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 1.8944914019236375e-07, | |
| "loss": 0.0888, | |
| "step": 17100 | |
| } | |
| ], | |
| "max_steps": 17155, | |
| "num_train_epochs": 5, | |
| "total_flos": 5.255829891028992e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |