| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 90.0, | |
| "global_step": 29790, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00013193067062605056, | |
| "loss": 17.6929, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00011254053736637465, | |
| "loss": 2.9597, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 8.317464938377179e-05, | |
| "loss": 2.8924, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.04999004691124e-05, | |
| "loss": 2.854, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.1934390180170752e-05, | |
| "loss": 2.7631, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.963303752660306e-06, | |
| "loss": 2.827, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 6.665901596802237e-07, | |
| "loss": 2.7348, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.2792697375844372e-05, | |
| "loss": 2.5285, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.758865334885973e-05, | |
| "loss": 2.532, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 6.942506914238186e-05, | |
| "loss": 2.5207, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 0.00010107417071793643, | |
| "loss": 2.5964, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00012535070970483918, | |
| "loss": 2.651, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 0.00013674321963112474, | |
| "loss": 2.6082, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0001326652759440951, | |
| "loss": 2.4929, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.00011404268812251294, | |
| "loss": 2.4281, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 8.510331453017784e-05, | |
| "loss": 2.4293, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.2417218031482405e-05, | |
| "loss": 2.4101, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 2.3405074409295983e-05, | |
| "loss": 2.3587, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 4.653467399454465e-06, | |
| "loss": 2.307, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 4.1954639981762966e-07, | |
| "loss": 2.3605, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "learning_rate": 1.1664532186009215e-05, | |
| "loss": 2.137, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 3.5835492391032385e-05, | |
| "loss": 2.0627, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 6.744492993645014e-05, | |
| "loss": 2.1204, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "learning_rate": 9.931660131723702e-05, | |
| "loss": 2.1823, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.77, | |
| "learning_rate": 0.00012421472847147613, | |
| "loss": 2.2277, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.000136486726691794, | |
| "loss": 2.2512, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 0.00013334650250861535, | |
| "loss": 2.0589, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 0.00011550697633903009, | |
| "loss": 2.0364, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 8.701822922681755e-05, | |
| "loss": 2.079, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 5.4348018978061915e-05, | |
| "loss": 2.0451, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 2.4913414743980736e-05, | |
| "loss": 2.0148, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 5.396910863624203e-06, | |
| "loss": 2.0322, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 2.2931013159956905e-07, | |
| "loss": 2.0037, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 1.0583805241907789e-05, | |
| "loss": 1.7858, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 3.410963059878637e-05, | |
| "loss": 1.7749, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 6.546575312706341e-05, | |
| "loss": 1.753, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 9.753343905259311e-05, | |
| "loss": 1.8774, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 0.00012303240942344423, | |
| "loss": 1.8664, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 0.0001361736709920872, | |
| "loss": 1.9253, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 0.00013397378272625676, | |
| "loss": 1.895, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.00011693218198091279, | |
| "loss": 1.6965, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 8.891779797974934e-05, | |
| "loss": 1.7647, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 5.629069457859385e-05, | |
| "loss": 1.7246, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 2.645815444528567e-05, | |
| "loss": 1.7252, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 6.193014713115989e-06, | |
| "loss": 1.7153, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 9.603985859484616e-08, | |
| "loss": 1.7007, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 9.55141699790193e-06, | |
| "loss": 1.5635, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 3.2412505948464725e-05, | |
| "loss": 1.4871, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 6.348918775091967e-05, | |
| "loss": 1.4965, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 9.572616964271242e-05, | |
| "loss": 1.5202, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.00012180473766095787, | |
| "loss": 1.5508, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 0.0001358043133678906, | |
| "loss": 1.658, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 0.0001345465939513953, | |
| "loss": 1.6614, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 0.0001183171175764834, | |
| "loss": 1.4421, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 9.080043808116885e-05, | |
| "loss": 1.4517, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 5.824362620893997e-05, | |
| "loss": 1.5004, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 2.803800644656531e-05, | |
| "loss": 1.4732, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 7.041115639600712e-06, | |
| "loss": 1.3825, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 1.9846620691268856e-08, | |
| "loss": 1.3723, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 8.568227632876734e-06, | |
| "loss": 1.3401, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 3.074553247281859e-05, | |
| "loss": 1.2335, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 9.35, | |
| "learning_rate": 6.151688066888818e-05, | |
| "loss": 1.211, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 9.389629889221367e-05, | |
| "loss": 1.2744, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 9.65, | |
| "learning_rate": 0.00012053273607180507, | |
| "loss": 1.3462, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 0.0001353789615654724, | |
| "loss": 1.3833, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 0.00013506445892160198, | |
| "loss": 1.383, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 10.11, | |
| "learning_rate": 1.3445492880161939e-06, | |
| "loss": 1.2022, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 10.26, | |
| "learning_rate": 1.1808914090066666e-06, | |
| "loss": 1.1142, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 10.41, | |
| "learning_rate": 9.048790708431603e-07, | |
| "loss": 1.1743, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 5.791749433756745e-07, | |
| "loss": 1.1411, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 10.71, | |
| "learning_rate": 2.7772314933464675e-07, | |
| "loss": 1.2239, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "learning_rate": 6.896184033086834e-08, | |
| "loss": 1.1843, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "learning_rate": 2.8578527430069923e-10, | |
| "loss": 1.1689, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 8.568227632876734e-08, | |
| "loss": 1.105, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 3.074553247281864e-07, | |
| "loss": 1.1371, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 11.46, | |
| "learning_rate": 6.151688066888805e-07, | |
| "loss": 1.1963, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 9.389629889221367e-07, | |
| "loss": 1.153, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 11.76, | |
| "learning_rate": 1.2053273607180523e-06, | |
| "loss": 1.1951, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 11.92, | |
| "learning_rate": 1.353789615654724e-06, | |
| "loss": 1.1274, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 12.07, | |
| "learning_rate": 1.363372539869449e-07, | |
| "loss": 1.1804, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 12.22, | |
| "learning_rate": 1.2362930050095064e-07, | |
| "loss": 1.1455, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 12.37, | |
| "learning_rate": 9.842812692084315e-08, | |
| "loss": 1.1767, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 12.52, | |
| "learning_rate": 6.645511813249419e-08, | |
| "loss": 1.147, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 12.67, | |
| "learning_rate": 3.496905867845774e-08, | |
| "loss": 1.114, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 12.82, | |
| "learning_rate": 1.1118181719517309e-08, | |
| "loss": 1.1379, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 12.97, | |
| "learning_rate": 3.173163117047257e-10, | |
| "loss": 1.1261, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 3.459977149963379, | |
| "eval_runtime": 0.891, | |
| "eval_samples_per_second": 76.319, | |
| "eval_steps_per_second": 76.319, | |
| "step": 8619 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 5.0185668342927494e-09, | |
| "loss": 1.1202, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 2.415461538642524e-08, | |
| "loss": 1.1387, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 13.42, | |
| "learning_rate": 5.338103337974863e-08, | |
| "loss": 1.1257, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 8.606259068723572e-08, | |
| "loss": 1.1419, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 1.1477964205183373e-07, | |
| "loss": 1.1491, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 1.330125980932328e-07, | |
| "loss": 1.141, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 3.4634451866149902, | |
| "eval_runtime": 0.8581, | |
| "eval_samples_per_second": 79.247, | |
| "eval_steps_per_second": 79.247, | |
| "step": 9282 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 1.3662205797010195e-07, | |
| "loss": 1.1135, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 1.2497725716841956e-07, | |
| "loss": 1.1462, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 1.0049124874956241e-07, | |
| "loss": 1.1353, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 6.876501764792728e-08, | |
| "loss": 1.1573, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 3.700132283557427e-08, | |
| "loss": 1.1477, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 1.2411428614983945e-08, | |
| "loss": 1.0973, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 5.779420298980625e-10, | |
| "loss": 1.1278, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 3.4664907455444336, | |
| "eval_runtime": 0.883, | |
| "eval_samples_per_second": 77.009, | |
| "eval_steps_per_second": 77.009, | |
| "step": 9945 | |
| }, | |
| { | |
| "epoch": 15.08, | |
| "learning_rate": 4.187401906767171e-09, | |
| "loss": 1.125, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 15.23, | |
| "learning_rate": 2.2420357948166246e-08, | |
| "loss": 1.1384, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 15.38, | |
| "learning_rate": 5.1137409312764306e-08, | |
| "loss": 1.1209, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 15.54, | |
| "learning_rate": 8.381896662025135e-08, | |
| "loss": 1.1044, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 15.69, | |
| "learning_rate": 1.1304538461357478e-07, | |
| "loss": 1.1637, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 1.3218143316570722e-07, | |
| "loss": 1.1661, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 15.99, | |
| "learning_rate": 1.368826836882953e-07, | |
| "loss": 1.1183, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 3.4696619510650635, | |
| "eval_runtime": 0.872, | |
| "eval_samples_per_second": 77.979, | |
| "eval_steps_per_second": 77.979, | |
| "step": 10608 | |
| }, | |
| { | |
| "epoch": 16.14, | |
| "learning_rate": 1.2608181828048274e-07, | |
| "loss": 1.1561, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 16.29, | |
| "learning_rate": 1.0223094132154226e-07, | |
| "loss": 1.1467, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 7.074488186750591e-08, | |
| "loss": 1.1874, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 16.59, | |
| "learning_rate": 3.8771873079156884e-08, | |
| "loss": 1.1281, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 16.74, | |
| "learning_rate": 1.3570699499049336e-08, | |
| "loss": 1.0814, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 8.627460130551071e-10, | |
| "loss": 1.1048, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 3.4714086055755615, | |
| "eval_runtime": 0.874, | |
| "eval_samples_per_second": 77.801, | |
| "eval_steps_per_second": 77.801, | |
| "step": 11271 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "learning_rate": 3.5330803651032965e-09, | |
| "loss": 1.1379, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 17.19, | |
| "learning_rate": 2.0975460526287258e-08, | |
| "loss": 1.1625, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 17.35, | |
| "learning_rate": 4.922996891933192e-08, | |
| "loss": 1.1556, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 8.188202660552875e-08, | |
| "loss": 1.1082, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 17.65, | |
| "learning_rate": 1.115186855828889e-07, | |
| "loss": 1.1591, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 1.3141157932507567e-07, | |
| "loss": 1.119, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 17.95, | |
| "learning_rate": 1.3704445380800497e-07, | |
| "loss": 1.1061, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 3.4751551151275635, | |
| "eval_runtime": 0.87, | |
| "eval_samples_per_second": 78.161, | |
| "eval_steps_per_second": 78.161, | |
| "step": 11934 | |
| }, | |
| { | |
| "epoch": 18.1, | |
| "learning_rate": 1.2713848593130804e-07, | |
| "loss": 1.1182, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "learning_rate": 1.0394261282124642e-07, | |
| "loss": 1.1469, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 7.272295898605559e-08, | |
| "loss": 1.1398, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 18.55, | |
| "learning_rate": 4.05672759158415e-08, | |
| "loss": 1.0718, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 18.7, | |
| "learning_rate": 1.4775820423167982e-08, | |
| "loss": 1.1535, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 18.85, | |
| "learning_rate": 1.2039882169440381e-09, | |
| "loss": 1.1471, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 3.4772818088531494, | |
| "eval_runtime": 0.871, | |
| "eval_samples_per_second": 78.07, | |
| "eval_steps_per_second": 78.07, | |
| "step": 12597 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.9329721396952097e-09, | |
| "loss": 1.1334, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 19.16, | |
| "learning_rate": 1.9570243547781353e-08, | |
| "loss": 1.1311, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 19.31, | |
| "learning_rate": 4.733866750445838e-08, | |
| "loss": 1.129, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 19.46, | |
| "learning_rate": 7.993402009629649e-08, | |
| "loss": 1.0708, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 19.61, | |
| "learning_rate": 1.0995622699438409e-07, | |
| "loss": 1.1266, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 19.76, | |
| "learning_rate": 1.3058939130244216e-07, | |
| "loss": 1.146, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 19.91, | |
| "learning_rate": 1.3716110242414843e-07, | |
| "loss": 1.1402, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 3.4797611236572266, | |
| "eval_runtime": 0.848, | |
| "eval_samples_per_second": 80.192, | |
| "eval_steps_per_second": 80.192, | |
| "step": 13260 | |
| }, | |
| { | |
| "epoch": 20.06, | |
| "learning_rate": 1.2830956053906914e-07, | |
| "loss": 1.1516, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 20.21, | |
| "learning_rate": 1.0590224609743171e-07, | |
| "loss": 1.1088, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 20.36, | |
| "learning_rate": 7.502625830800328e-08, | |
| "loss": 1.1331, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 20.51, | |
| "learning_rate": 4.269132667061271e-08, | |
| "loss": 1.157, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 20.66, | |
| "learning_rate": 1.6238402532934746e-08, | |
| "loss": 1.1155, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 20.81, | |
| "learning_rate": 1.673053844704988e-09, | |
| "loss": 1.1693, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 20.97, | |
| "learning_rate": 2.3020300149297553e-09, | |
| "loss": 1.0847, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 3.4811391830444336, | |
| "eval_runtime": 0.8641, | |
| "eval_samples_per_second": 78.699, | |
| "eval_steps_per_second": 78.699, | |
| "step": 13923 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 1.7982535520914407e-08, | |
| "loss": 1.1415, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 21.27, | |
| "learning_rate": 4.515464856300149e-08, | |
| "loss": 1.1699, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 21.42, | |
| "learning_rate": 7.764952480614377e-08, | |
| "loss": 1.0972, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 21.57, | |
| "learning_rate": 1.0808990091715443e-07, | |
| "loss": 1.1351, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 21.72, | |
| "learning_rate": 1.295649436664554e-07, | |
| "loss": 1.1021, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 21.87, | |
| "learning_rate": 1.3719920609842196e-07, | |
| "loss": 1.1462, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 3.48413348197937, | |
| "eval_runtime": 0.887, | |
| "eval_samples_per_second": 76.663, | |
| "eval_steps_per_second": 76.663, | |
| "step": 14586 | |
| }, | |
| { | |
| "epoch": 22.02, | |
| "learning_rate": 1.292594929888637e-07, | |
| "loss": 1.1323, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 22.17, | |
| "learning_rate": 1.0754834557415543e-07, | |
| "loss": 1.1255, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 22.32, | |
| "learning_rate": 7.699481330029191e-08, | |
| "loss": 1.1254, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 22.47, | |
| "learning_rate": 4.453541907189201e-08, | |
| "loss": 1.1578, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 1.7539370793205484e-08, | |
| "loss": 1.1509, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 22.78, | |
| "learning_rate": 2.135541078398113e-09, | |
| "loss": 1.096, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 22.93, | |
| "learning_rate": 1.821038434527568e-09, | |
| "loss": 1.1107, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 3.485179901123047, | |
| "eval_runtime": 0.876, | |
| "eval_samples_per_second": 77.624, | |
| "eval_steps_per_second": 77.624, | |
| "step": 15249 | |
| }, | |
| { | |
| "epoch": 23.08, | |
| "learning_rate": 1.6667263928194815e-08, | |
| "loss": 1.1112, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "learning_rate": 4.330370110778617e-08, | |
| "loss": 1.0894, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 23.38, | |
| "learning_rate": 7.568311933111189e-08, | |
| "loss": 1.1571, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 23.53, | |
| "learning_rate": 1.0645446752718106e-07, | |
| "loss": 1.0807, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 1.286317723671232e-07, | |
| "loss": 1.1122, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 23.83, | |
| "learning_rate": 1.3718015337930875e-07, | |
| "loss": 1.2016, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 23.98, | |
| "learning_rate": 1.301588843603994e-07, | |
| "loss": 1.1192, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 3.487265110015869, | |
| "eval_runtime": 1.004, | |
| "eval_samples_per_second": 67.732, | |
| "eval_steps_per_second": 67.732, | |
| "step": 15912 | |
| }, | |
| { | |
| "epoch": 24.13, | |
| "learning_rate": 1.0916199355343483e-07, | |
| "loss": 1.1713, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 24.28, | |
| "learning_rate": 7.895637379105998e-08, | |
| "loss": 1.1412, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 24.43, | |
| "learning_rate": 4.639956191883156e-08, | |
| "loss": 1.1021, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "learning_rate": 1.8882882423516715e-08, | |
| "loss": 1.1353, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 24.74, | |
| "learning_rate": 2.653406048604756e-09, | |
| "loss": 1.0801, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 1.3956866321093081e-09, | |
| "loss": 1.0868, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 3.487858295440674, | |
| "eval_runtime": 0.854, | |
| "eval_samples_per_second": 79.625, | |
| "eval_steps_per_second": 79.625, | |
| "step": 16575 | |
| }, | |
| { | |
| "epoch": 25.04, | |
| "learning_rate": 1.539526233904202e-08, | |
| "loss": 1.0812, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 25.19, | |
| "learning_rate": 4.1473830357287196e-08, | |
| "loss": 1.104, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 25.34, | |
| "learning_rate": 7.371081224908017e-08, | |
| "loss": 1.0943, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 25.49, | |
| "learning_rate": 1.0478749405153535e-07, | |
| "loss": 1.097, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 25.64, | |
| "learning_rate": 1.2764858300209813e-07, | |
| "loss": 1.1316, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 25.79, | |
| "learning_rate": 1.3710396014140516e-07, | |
| "loss": 1.1679, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 25.94, | |
| "learning_rate": 1.31006985286884e-07, | |
| "loss": 1.1313, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 3.489774703979492, | |
| "eval_runtime": 0.859, | |
| "eval_samples_per_second": 79.161, | |
| "eval_steps_per_second": 79.161, | |
| "step": 17238 | |
| }, | |
| { | |
| "epoch": 26.09, | |
| "learning_rate": 1.1100177565244e-07, | |
| "loss": 1.1454, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 8.123384073832201e-08, | |
| "loss": 1.0682, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 4.859766378694414e-08, | |
| "loss": 1.1414, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 26.55, | |
| "learning_rate": 2.050258742073295e-08, | |
| "loss": 1.146, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 26.7, | |
| "learning_rate": 3.326994962912756e-09, | |
| "loss": 1.145, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 26.85, | |
| "learning_rate": 9.702355760016704e-10, | |
| "loss": 1.1254, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 1.3967360831826574e-08, | |
| "loss": 1.1033, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 3.491461992263794, | |
| "eval_runtime": 0.878, | |
| "eval_samples_per_second": 77.447, | |
| "eval_steps_per_second": 77.447, | |
| "step": 17901 | |
| }, | |
| { | |
| "epoch": 27.15, | |
| "learning_rate": 3.936765275044558e-08, | |
| "loss": 1.1389, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 27.3, | |
| "learning_rate": 7.140452090629836e-08, | |
| "loss": 1.1195, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 27.45, | |
| "learning_rate": 1.0280468285978317e-07, | |
| "loss": 1.0567, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 27.6, | |
| "learning_rate": 1.2643940663167218e-07, | |
| "loss": 1.1261, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "learning_rate": 1.369429361019015e-07, | |
| "loss": 1.1393, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 27.9, | |
| "learning_rate": 1.3193067062605075e-07, | |
| "loss": 1.1578, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_loss": 3.4938805103302, | |
| "eval_runtime": 0.864, | |
| "eval_samples_per_second": 78.704, | |
| "eval_steps_per_second": 78.704, | |
| "step": 18564 | |
| }, | |
| { | |
| "epoch": 28.05, | |
| "learning_rate": 1.1254053736637487e-07, | |
| "loss": 1.136, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 28.21, | |
| "learning_rate": 8.317464938377186e-08, | |
| "loss": 1.102, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 28.36, | |
| "learning_rate": 5.0499900469112783e-08, | |
| "loss": 1.1325, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 28.51, | |
| "learning_rate": 2.193439018017092e-08, | |
| "loss": 1.1511, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 28.66, | |
| "learning_rate": 3.963303752660322e-09, | |
| "loss": 1.118, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 28.81, | |
| "learning_rate": 6.66590159680239e-10, | |
| "loss": 1.1024, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.2792697375844275e-08, | |
| "loss": 1.0987, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_loss": 3.4947092533111572, | |
| "eval_runtime": 0.879, | |
| "eval_samples_per_second": 77.363, | |
| "eval_steps_per_second": 77.363, | |
| "step": 19227 | |
| }, | |
| { | |
| "epoch": 29.11, | |
| "learning_rate": 3.7294625797960914e-08, | |
| "loss": 1.135, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 29.26, | |
| "learning_rate": 6.909504912431355e-08, | |
| "loss": 1.1308, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 29.41, | |
| "learning_rate": 1.0078308218564023e-07, | |
| "loss": 1.0927, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 29.56, | |
| "learning_rate": 1.2516463805405508e-07, | |
| "loss": 1.1707, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 29.71, | |
| "learning_rate": 1.367044084314665e-07, | |
| "loss": 1.1217, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 29.86, | |
| "learning_rate": 1.3278253644438908e-07, | |
| "loss": 1.0779, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_loss": 3.497239112854004, | |
| "eval_runtime": 0.879, | |
| "eval_samples_per_second": 77.362, | |
| "eval_steps_per_second": 77.362, | |
| "step": 19890 | |
| }, | |
| { | |
| "epoch": 60.12, | |
| "learning_rate": 8.693541350698569e-09, | |
| "loss": 1.5417, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 60.42, | |
| "learning_rate": 6.223106707028002e-08, | |
| "loss": 1.3927, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 60.73, | |
| "learning_rate": 1.2172156539717049e-07, | |
| "loss": 1.3567, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_loss": 3.4576382637023926, | |
| "eval_runtime": 0.952, | |
| "eval_samples_per_second": 35.715, | |
| "eval_steps_per_second": 35.715, | |
| "step": 20191 | |
| }, | |
| { | |
| "epoch": 61.03, | |
| "learning_rate": 1.3426435048201084e-07, | |
| "loss": 1.3891, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 61.33, | |
| "learning_rate": 8.877437479246501e-08, | |
| "loss": 1.3829, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 61.63, | |
| "learning_rate": 2.5454714388004032e-08, | |
| "loss": 1.3482, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 61.93, | |
| "learning_rate": 2.6594266338289214e-10, | |
| "loss": 1.3278, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_loss": 3.452810525894165, | |
| "eval_runtime": 0.964, | |
| "eval_samples_per_second": 35.269, | |
| "eval_steps_per_second": 35.269, | |
| "step": 20522 | |
| }, | |
| { | |
| "epoch": 62.24, | |
| "learning_rate": 3.54693620295034e-08, | |
| "loss": 1.3495, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 62.54, | |
| "learning_rate": 9.995293681528824e-08, | |
| "loss": 1.3372, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 62.84, | |
| "learning_rate": 1.3672745077248097e-07, | |
| "loss": 1.3292, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_loss": 3.4468021392822266, | |
| "eval_runtime": 0.9878, | |
| "eval_samples_per_second": 34.42, | |
| "eval_steps_per_second": 34.42, | |
| "step": 20853 | |
| }, | |
| { | |
| "epoch": 63.14, | |
| "learning_rate": 1.1329236813994995e-07, | |
| "loss": 1.3209, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 63.44, | |
| "learning_rate": 5.035911808981744e-08, | |
| "loss": 1.3127, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 63.75, | |
| "learning_rate": 3.5467727381560775e-09, | |
| "loss": 1.3285, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_loss": 3.443075180053711, | |
| "eval_runtime": 0.9684, | |
| "eval_samples_per_second": 35.111, | |
| "eval_steps_per_second": 35.111, | |
| "step": 21184 | |
| }, | |
| { | |
| "epoch": 64.05, | |
| "learning_rate": 1.4227090415615305e-08, | |
| "loss": 1.2899, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 64.35, | |
| "learning_rate": 7.296103279743161e-08, | |
| "loss": 1.3259, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 64.65, | |
| "learning_rate": 1.2784078685324094e-07, | |
| "loss": 1.308, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 64.95, | |
| "learning_rate": 1.303647894806954e-07, | |
| "loss": 1.3032, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_loss": 3.437013626098633, | |
| "eval_runtime": 0.9607, | |
| "eval_samples_per_second": 35.392, | |
| "eval_steps_per_second": 35.392, | |
| "step": 21515 | |
| }, | |
| { | |
| "epoch": 65.26, | |
| "learning_rate": 7.830238067025156e-08, | |
| "loss": 1.2946, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 65.56, | |
| "learning_rate": 1.766521352829689e-08, | |
| "loss": 1.3209, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 65.86, | |
| "learning_rate": 2.043130777021614e-09, | |
| "loss": 1.318, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_loss": 3.4345176219940186, | |
| "eval_runtime": 0.9583, | |
| "eval_samples_per_second": 35.479, | |
| "eval_steps_per_second": 35.479, | |
| "step": 21846 | |
| }, | |
| { | |
| "epoch": 66.16, | |
| "learning_rate": 4.5242597940677724e-08, | |
| "loss": 1.2637, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 66.47, | |
| "learning_rate": 1.090848418327998e-07, | |
| "loss": 1.2813, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 66.77, | |
| "learning_rate": 1.3714744085178092e-07, | |
| "loss": 1.3003, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_loss": 3.428901195526123, | |
| "eval_runtime": 0.9557, | |
| "eval_samples_per_second": 35.575, | |
| "eval_steps_per_second": 35.575, | |
| "step": 22177 | |
| }, | |
| { | |
| "epoch": 67.07, | |
| "learning_rate": 1.0462926495336562e-07, | |
| "loss": 1.3045, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 67.37, | |
| "learning_rate": 4.026918856301729e-08, | |
| "loss": 1.2654, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 67.67, | |
| "learning_rate": 9.472826654548543e-10, | |
| "loss": 1.2689, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 67.98, | |
| "learning_rate": 2.141541401022131e-08, | |
| "loss": 1.3202, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_loss": 3.427440881729126, | |
| "eval_runtime": 0.958, | |
| "eval_samples_per_second": 35.49, | |
| "eval_steps_per_second": 35.49, | |
| "step": 22508 | |
| }, | |
| { | |
| "epoch": 68.28, | |
| "learning_rate": 8.358428206955252e-08, | |
| "loss": 1.3008, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 68.58, | |
| "learning_rate": 1.3251035932481603e-07, | |
| "loss": 1.2628, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 68.88, | |
| "learning_rate": 1.2495381600320813e-07, | |
| "loss": 1.2643, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_loss": 3.4231972694396973, | |
| "eval_runtime": 0.9561, | |
| "eval_samples_per_second": 35.563, | |
| "eval_steps_per_second": 35.563, | |
| "step": 22839 | |
| }, | |
| { | |
| "epoch": 69.18, | |
| "learning_rate": 6.759296488244086e-08, | |
| "loss": 1.2717, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 69.49, | |
| "learning_rate": 1.1122110047934364e-08, | |
| "loss": 1.2759, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 69.79, | |
| "learning_rate": 5.44899573655199e-09, | |
| "loss": 1.2862, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_loss": 3.4223098754882812, | |
| "eval_runtime": 1.0568, | |
| "eval_samples_per_second": 32.174, | |
| "eval_steps_per_second": 32.174, | |
| "step": 23170 | |
| }, | |
| { | |
| "epoch": 70.09, | |
| "learning_rate": 5.492884226688333e-08, | |
| "loss": 1.2962, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 70.39, | |
| "learning_rate": 1.1675016817694061e-07, | |
| "loss": 1.2762, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 70.69, | |
| "learning_rate": 1.3601739630719386e-07, | |
| "loss": 1.2783, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "learning_rate": 9.570255892993473e-08, | |
| "loss": 1.2597, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_loss": 3.418621063232422, | |
| "eval_runtime": 1.0452, | |
| "eval_samples_per_second": 32.531, | |
| "eval_steps_per_second": 32.531, | |
| "step": 23501 | |
| }, | |
| { | |
| "epoch": 71.3, | |
| "learning_rate": 3.143505458484596e-08, | |
| "loss": 1.3153, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 71.6, | |
| "learning_rate": 1.3141045706995258e-11, | |
| "loss": 1.245, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 71.9, | |
| "learning_rate": 2.920683930724396e-08, | |
| "loss": 1.2426, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_loss": 3.4176230430603027, | |
| "eval_runtime": 1.0483, | |
| "eval_samples_per_second": 32.434, | |
| "eval_steps_per_second": 32.434, | |
| "step": 23832 | |
| }, | |
| { | |
| "epoch": 72.21, | |
| "learning_rate": 9.32153777956087e-08, | |
| "loss": 1.276, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 72.51, | |
| "learning_rate": 1.3546936727073083e-07, | |
| "loss": 1.2707, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 72.81, | |
| "learning_rate": 1.1862562768173958e-07, | |
| "loss": 1.2539, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_loss": 3.4151535034179688, | |
| "eval_runtime": 1.0259, | |
| "eval_samples_per_second": 33.143, | |
| "eval_steps_per_second": 33.143, | |
| "step": 24163 | |
| }, | |
| { | |
| "epoch": 73.11, | |
| "learning_rate": 5.7570298965124436e-08, | |
| "loss": 1.2827, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 73.41, | |
| "learning_rate": 6.262786177113756e-09, | |
| "loss": 1.2277, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 73.72, | |
| "learning_rate": 1.0047581324385604e-08, | |
| "loss": 1.2604, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_loss": 3.414668083190918, | |
| "eval_runtime": 1.0049, | |
| "eval_samples_per_second": 33.834, | |
| "eval_steps_per_second": 33.834, | |
| "step": 24494 | |
| }, | |
| { | |
| "epoch": 74.02, | |
| "learning_rate": 6.55797626990514e-08, | |
| "loss": 1.2588, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 74.32, | |
| "learning_rate": 1.2378116576678553e-07, | |
| "loss": 1.2695, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 74.62, | |
| "learning_rate": 1.3321462445238648e-07, | |
| "loss": 1.2576, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 74.92, | |
| "learning_rate": 8.554304797283439e-08, | |
| "loss": 1.263, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_loss": 3.412790298461914, | |
| "eval_runtime": 1.012, | |
| "eval_samples_per_second": 33.597, | |
| "eval_steps_per_second": 33.597, | |
| "step": 24825 | |
| }, | |
| { | |
| "epoch": 75.23, | |
| "learning_rate": 2.2897564912636232e-08, | |
| "loss": 1.2362, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 75.53, | |
| "learning_rate": 6.429250232458032e-10, | |
| "loss": 1.2653, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 75.83, | |
| "learning_rate": 3.844730720753521e-08, | |
| "loss": 1.2642, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_loss": 3.412682294845581, | |
| "eval_runtime": 1.006, | |
| "eval_samples_per_second": 33.797, | |
| "eval_steps_per_second": 33.797, | |
| "step": 25156 | |
| }, | |
| { | |
| "epoch": 76.13, | |
| "learning_rate": 1.0289999999999885e-07, | |
| "loss": 1.2254, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 76.44, | |
| "learning_rate": 1.370390800033334e-07, | |
| "loss": 1.2543, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 76.74, | |
| "learning_rate": 1.106931521097187e-07, | |
| "loss": 1.2694, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_loss": 3.4108803272247314, | |
| "eval_runtime": 1.004, | |
| "eval_samples_per_second": 33.865, | |
| "eval_steps_per_second": 33.865, | |
| "step": 25487 | |
| }, | |
| { | |
| "epoch": 77.04, | |
| "learning_rate": 4.7146188818785276e-08, | |
| "loss": 1.25, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 77.34, | |
| "learning_rate": 2.559648997196144e-09, | |
| "loss": 1.2614, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 77.64, | |
| "learning_rate": 1.6338171238500445e-08, | |
| "loss": 1.2549, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 77.95, | |
| "learning_rate": 7.63045897109416e-08, | |
| "loss": 1.2251, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_loss": 3.4106197357177734, | |
| "eval_runtime": 1.0035, | |
| "eval_samples_per_second": 33.882, | |
| "eval_steps_per_second": 33.882, | |
| "step": 25818 | |
| }, | |
| { | |
| "epoch": 78.25, | |
| "learning_rate": 1.2946185514557884e-07, | |
| "loss": 1.2965, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 78.55, | |
| "learning_rate": 1.288307033641468e-07, | |
| "loss": 1.2137, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 78.85, | |
| "learning_rate": 7.496893292971942e-08, | |
| "loss": 1.2673, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_loss": 3.409691333770752, | |
| "eval_runtime": 1.0062, | |
| "eval_samples_per_second": 33.792, | |
| "eval_steps_per_second": 33.792, | |
| "step": 26149 | |
| }, | |
| { | |
| "epoch": 79.15, | |
| "learning_rate": 1.5478434602829786e-08, | |
| "loss": 1.225, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 79.46, | |
| "learning_rate": 2.9356495179890543e-09, | |
| "loss": 1.2545, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 79.76, | |
| "learning_rate": 4.842562520753367e-08, | |
| "loss": 1.233, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_loss": 3.409552574157715, | |
| "eval_runtime": 1.0059, | |
| "eval_samples_per_second": 33.8, | |
| "eval_steps_per_second": 33.8, | |
| "step": 26480 | |
| }, | |
| { | |
| "epoch": 80.06, | |
| "learning_rate": 1.1174528561199565e-07, | |
| "loss": 1.2286, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 80.36, | |
| "learning_rate": 1.3693405733661706e-07, | |
| "loss": 1.2464, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 80.66, | |
| "learning_rate": 1.0173063797049695e-07, | |
| "loss": 1.2497, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 80.97, | |
| "learning_rate": 3.7247063184712124e-08, | |
| "loss": 1.2408, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_loss": 3.4087181091308594, | |
| "eval_runtime": 1.0321, | |
| "eval_samples_per_second": 32.942, | |
| "eval_steps_per_second": 32.942, | |
| "step": 26811 | |
| }, | |
| { | |
| "epoch": 81.27, | |
| "learning_rate": 4.725492275192098e-10, | |
| "loss": 1.2461, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 81.57, | |
| "learning_rate": 2.3400433722385994e-08, | |
| "loss": 1.2495, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 81.87, | |
| "learning_rate": 8.619280748313942e-08, | |
| "loss": 1.2579, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_loss": 3.408783435821533, | |
| "eval_runtime": 1.0924, | |
| "eval_samples_per_second": 31.123, | |
| "eval_steps_per_second": 31.123, | |
| "step": 27142 | |
| }, | |
| { | |
| "epoch": 82.18, | |
| "learning_rate": 1.3343703098390236e-07, | |
| "loss": 1.2153, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 82.48, | |
| "learning_rate": 1.233796611423087e-07, | |
| "loss": 1.2398, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 82.78, | |
| "learning_rate": 6.490918819320101e-08, | |
| "loss": 1.2346, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_loss": 3.408099412918091, | |
| "eval_runtime": 1.0406, | |
| "eval_samples_per_second": 32.673, | |
| "eval_steps_per_second": 32.673, | |
| "step": 27473 | |
| }, | |
| { | |
| "epoch": 83.08, | |
| "learning_rate": 9.700576468258166e-09, | |
| "loss": 1.2543, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 83.38, | |
| "learning_rate": 6.546026505537958e-09, | |
| "loss": 1.247, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 83.69, | |
| "learning_rate": 5.823346268095307e-08, | |
| "loss": 1.2225, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 83.99, | |
| "learning_rate": 1.190826247529784e-07, | |
| "loss": 1.2298, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_loss": 3.4082374572753906, | |
| "eval_runtime": 1.0242, | |
| "eval_samples_per_second": 33.197, | |
| "eval_steps_per_second": 33.197, | |
| "step": 27804 | |
| }, | |
| { | |
| "epoch": 84.29, | |
| "learning_rate": 1.3531631337483422e-07, | |
| "loss": 1.2426, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 84.59, | |
| "learning_rate": 9.258753872080096e-08, | |
| "loss": 1.2389, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 84.89, | |
| "learning_rate": 2.865908591672022e-08, | |
| "loss": 1.219, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_loss": 3.407871961593628, | |
| "eval_runtime": 0.9538, | |
| "eval_samples_per_second": 35.648, | |
| "eval_steps_per_second": 35.648, | |
| "step": 28135 | |
| }, | |
| { | |
| "epoch": 85.2, | |
| "learning_rate": 2.956617282787915e-11, | |
| "loss": 1.2712, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 85.5, | |
| "learning_rate": 3.2001142050499094e-08, | |
| "loss": 1.2184, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 85.8, | |
| "learning_rate": 9.631801263387146e-08, | |
| "loss": 1.2515, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_loss": 3.4080073833465576, | |
| "eval_runtime": 0.951, | |
| "eval_samples_per_second": 35.752, | |
| "eval_steps_per_second": 35.752, | |
| "step": 28466 | |
| }, | |
| { | |
| "epoch": 86.1, | |
| "learning_rate": 1.361382913144042e-07, | |
| "loss": 1.2196, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 86.4, | |
| "learning_rate": 1.162696600432059e-07, | |
| "loss": 1.2085, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 86.71, | |
| "learning_rate": 5.427159389331479e-08, | |
| "loss": 1.2316, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_loss": 3.408378839492798, | |
| "eval_runtime": 0.9581, | |
| "eval_samples_per_second": 35.486, | |
| "eval_steps_per_second": 35.486, | |
| "step": 28797 | |
| }, | |
| { | |
| "epoch": 87.01, | |
| "learning_rate": 4.936669277050985e-09, | |
| "loss": 1.2578, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 87.31, | |
| "learning_rate": 1.1866046596701257e-08, | |
| "loss": 1.24, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 87.61, | |
| "learning_rate": 6.893568909023435e-08, | |
| "loss": 1.2342, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 87.92, | |
| "learning_rate": 1.2570865668292598e-07, | |
| "loss": 1.2085, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_loss": 3.4085471630096436, | |
| "eval_runtime": 1.0334, | |
| "eval_samples_per_second": 32.901, | |
| "eval_steps_per_second": 32.901, | |
| "step": 29128 | |
| }, | |
| { | |
| "epoch": 88.22, | |
| "learning_rate": 1.32010204287465e-07, | |
| "loss": 1.2504, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 88.52, | |
| "learning_rate": 8.227115773311707e-08, | |
| "loss": 1.2419, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 88.82, | |
| "learning_rate": 2.0449831823058302e-08, | |
| "loss": 1.2334, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_loss": 3.4085144996643066, | |
| "eval_runtime": 1.0283, | |
| "eval_samples_per_second": 33.063, | |
| "eval_steps_per_second": 33.063, | |
| "step": 29459 | |
| }, | |
| { | |
| "epoch": 89.12, | |
| "learning_rate": 1.1826036928064389e-09, | |
| "loss": 1.2213, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 89.43, | |
| "learning_rate": 4.088198736612909e-08, | |
| "loss": 1.2165, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 89.73, | |
| "learning_rate": 1.0519885794950143e-07, | |
| "loss": 1.2263, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_loss": 3.408367156982422, | |
| "eval_runtime": 1.0186, | |
| "eval_samples_per_second": 33.38, | |
| "eval_steps_per_second": 33.38, | |
| "step": 29790 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "step": 29790, | |
| "total_flos": 1.037068075008e+16, | |
| "train_loss": 0.13739024364296004, | |
| "train_runtime": 461.3754, | |
| "train_samples_per_second": 64.568, | |
| "train_steps_per_second": 64.568 | |
| } | |
| ], | |
| "max_steps": 29790, | |
| "num_train_epochs": 90, | |
| "total_flos": 1.037068075008e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |