| { | |
| "best_metric": 0.5883459448814392, | |
| "best_model_checkpoint": "../outputs/7b_lora_0.05/checkpoint-3200", | |
| "epoch": 0.9644364074743822, | |
| "global_step": 3200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.247, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.1539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 1.7928, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.2147, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00015, | |
| "loss": 0.9432, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.8265, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.7876, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.7653, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00027, | |
| "loss": 0.7297, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0003, | |
| "loss": 0.6621, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002990677439403356, | |
| "loss": 0.6617, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002981354878806712, | |
| "loss": 0.6567, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00029720323182100684, | |
| "loss": 0.6495, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002962709757613424, | |
| "loss": 0.6454, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029533871970167805, | |
| "loss": 0.6387, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029440646364201366, | |
| "loss": 0.6421, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029347420758234926, | |
| "loss": 0.6382, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00029254195152268487, | |
| "loss": 0.64, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002916096954630205, | |
| "loss": 0.651, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002906774394033561, | |
| "loss": 0.6477, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 0.6271677017211914, | |
| "eval_runtime": 38.9192, | |
| "eval_samples_per_second": 51.388, | |
| "eval_steps_per_second": 1.619, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0002897451833436917, | |
| "loss": 0.6264, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00028881292728402734, | |
| "loss": 0.6315, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00028788067122436294, | |
| "loss": 0.6303, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00028694841516469855, | |
| "loss": 0.6387, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00028601615910503415, | |
| "loss": 0.6267, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00028508390304536976, | |
| "loss": 0.6178, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00028415164698570536, | |
| "loss": 0.6268, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00028321939092604097, | |
| "loss": 0.6212, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00028228713486637663, | |
| "loss": 0.6267, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00028135487880671223, | |
| "loss": 0.6205, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00028042262274704784, | |
| "loss": 0.6217, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00027949036668738344, | |
| "loss": 0.6191, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00027855811062771905, | |
| "loss": 0.6339, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00027762585456805465, | |
| "loss": 0.6272, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00027669359850839026, | |
| "loss": 0.6317, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002757613424487259, | |
| "loss": 0.6142, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002748290863890615, | |
| "loss": 0.6348, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002738968303293971, | |
| "loss": 0.6161, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00027296457426973273, | |
| "loss": 0.6258, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00027203231821006834, | |
| "loss": 0.6176, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 0.6118931770324707, | |
| "eval_runtime": 38.809, | |
| "eval_samples_per_second": 51.534, | |
| "eval_steps_per_second": 1.623, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00027110006215040394, | |
| "loss": 0.616, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00027016780609073954, | |
| "loss": 0.6126, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002692355500310752, | |
| "loss": 0.6292, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002683032939714108, | |
| "loss": 0.6165, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002673710379117464, | |
| "loss": 0.6253, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.000266438781852082, | |
| "loss": 0.6043, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002655065257924176, | |
| "loss": 0.602, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00026457426973275323, | |
| "loss": 0.6207, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00026364201367308883, | |
| "loss": 0.6093, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002627097576134245, | |
| "loss": 0.6087, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00026177750155376004, | |
| "loss": 0.6149, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002608452454940957, | |
| "loss": 0.6247, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002599129894344313, | |
| "loss": 0.6071, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002589807333747669, | |
| "loss": 0.6132, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002580484773151025, | |
| "loss": 0.6248, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002571162212554382, | |
| "loss": 0.6136, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002561839651957738, | |
| "loss": 0.6133, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00025525170913610933, | |
| "loss": 0.6211, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.000254319453076445, | |
| "loss": 0.6241, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002533871970167806, | |
| "loss": 0.6193, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 0.6061509847640991, | |
| "eval_runtime": 38.8987, | |
| "eval_samples_per_second": 51.416, | |
| "eval_steps_per_second": 1.62, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002524549409571162, | |
| "loss": 0.6063, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002515226848974518, | |
| "loss": 0.6095, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00025059042883778746, | |
| "loss": 0.6135, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.000249658172778123, | |
| "loss": 0.6064, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002487259167184586, | |
| "loss": 0.625, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002477936606587943, | |
| "loss": 0.6062, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002468614045991299, | |
| "loss": 0.6116, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0002459291485394655, | |
| "loss": 0.6064, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002449968924798011, | |
| "loss": 0.6225, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002440646364201367, | |
| "loss": 0.621, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002431323803604723, | |
| "loss": 0.622, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00024220012430080793, | |
| "loss": 0.6128, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00024126786824114354, | |
| "loss": 0.6186, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00024033561218147917, | |
| "loss": 0.6143, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00023940335612181477, | |
| "loss": 0.6224, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00023847110006215038, | |
| "loss": 0.5982, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00023753884400248598, | |
| "loss": 0.6107, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002366065879428216, | |
| "loss": 0.6027, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00023567433188315722, | |
| "loss": 0.6086, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00023474207582349283, | |
| "loss": 0.6016, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.6028618216514587, | |
| "eval_runtime": 38.8192, | |
| "eval_samples_per_second": 51.521, | |
| "eval_steps_per_second": 1.623, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00023380981976382846, | |
| "loss": 0.6162, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00023287756370416406, | |
| "loss": 0.618, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00023194530764449967, | |
| "loss": 0.6205, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00023101305158483527, | |
| "loss": 0.61, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002300807955251709, | |
| "loss": 0.6099, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0002291485394655065, | |
| "loss": 0.6107, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00022821628340584211, | |
| "loss": 0.6038, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00022728402734617775, | |
| "loss": 0.6156, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00022635177128651332, | |
| "loss": 0.5985, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00022541951522684896, | |
| "loss": 0.6151, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00022448725916718456, | |
| "loss": 0.6065, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002235550031075202, | |
| "loss": 0.6098, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002226227470478558, | |
| "loss": 0.6095, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00022169049098819143, | |
| "loss": 0.6104, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.000220758234928527, | |
| "loss": 0.6116, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002198259788688626, | |
| "loss": 0.6018, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00021889372280919824, | |
| "loss": 0.613, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00021796146674953385, | |
| "loss": 0.6101, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00021702921068986948, | |
| "loss": 0.6087, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00021609695463020508, | |
| "loss": 0.606, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 0.5999864339828491, | |
| "eval_runtime": 38.8621, | |
| "eval_samples_per_second": 51.464, | |
| "eval_steps_per_second": 1.621, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00021516469857054072, | |
| "loss": 0.6162, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002142324425108763, | |
| "loss": 0.6055, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0002133001864512119, | |
| "loss": 0.6071, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00021236793039154753, | |
| "loss": 0.6127, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00021143567433188314, | |
| "loss": 0.6111, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00021050341827221877, | |
| "loss": 0.6108, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00020957116221255437, | |
| "loss": 0.6036, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00020863890615288995, | |
| "loss": 0.5965, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00020770665009322558, | |
| "loss": 0.5953, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002067743940335612, | |
| "loss": 0.6056, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00020584213797389682, | |
| "loss": 0.6036, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00020490988191423242, | |
| "loss": 0.5897, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00020397762585456806, | |
| "loss": 0.6104, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00020304536979490363, | |
| "loss": 0.6159, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00020211311373523924, | |
| "loss": 0.6044, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00020118085767557487, | |
| "loss": 0.5959, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00020024860161591048, | |
| "loss": 0.6102, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001993163455562461, | |
| "loss": 0.5941, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001983840894965817, | |
| "loss": 0.6033, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019745183343691732, | |
| "loss": 0.605, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 0.5981193780899048, | |
| "eval_runtime": 38.9735, | |
| "eval_samples_per_second": 51.317, | |
| "eval_steps_per_second": 1.616, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00019651957737725292, | |
| "loss": 0.5959, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019558732131758855, | |
| "loss": 0.5907, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019465506525792416, | |
| "loss": 0.5995, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00019372280919825976, | |
| "loss": 0.609, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001927905531385954, | |
| "loss": 0.6117, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.000191858297078931, | |
| "loss": 0.6081, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0001909260410192666, | |
| "loss": 0.6005, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0001899937849596022, | |
| "loss": 0.5991, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018906152889993784, | |
| "loss": 0.5992, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018812927284027345, | |
| "loss": 0.6054, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00018719701678060908, | |
| "loss": 0.6078, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018626476072094468, | |
| "loss": 0.5962, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00018533250466128026, | |
| "loss": 0.5958, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001844002486016159, | |
| "loss": 0.6063, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0001834679925419515, | |
| "loss": 0.603, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00018253573648228713, | |
| "loss": 0.6126, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00018160348042262273, | |
| "loss": 0.5996, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00018067122436295837, | |
| "loss": 0.6068, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017973896830329394, | |
| "loss": 0.6055, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017880671224362955, | |
| "loss": 0.5939, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 0.596312940120697, | |
| "eval_runtime": 39.1962, | |
| "eval_samples_per_second": 51.025, | |
| "eval_steps_per_second": 1.607, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00017787445618396518, | |
| "loss": 0.6049, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017694220012430079, | |
| "loss": 0.5989, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017600994406463642, | |
| "loss": 0.6064, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00017507768800497202, | |
| "loss": 0.6158, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00017414543194530765, | |
| "loss": 0.5992, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00017321317588564323, | |
| "loss": 0.6047, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00017228091982597884, | |
| "loss": 0.6053, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00017134866376631447, | |
| "loss": 0.6072, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00017041640770665007, | |
| "loss": 0.5979, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0001694841516469857, | |
| "loss": 0.6035, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0001685518955873213, | |
| "loss": 0.6015, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00016761963952765691, | |
| "loss": 0.6049, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00016668738346799252, | |
| "loss": 0.5886, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00016575512740832812, | |
| "loss": 0.6108, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00016482287134866376, | |
| "loss": 0.6053, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00016389061528899936, | |
| "loss": 0.6172, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.000162958359229335, | |
| "loss": 0.6019, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00016202610316967057, | |
| "loss": 0.5979, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001610938471100062, | |
| "loss": 0.5978, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0001601615910503418, | |
| "loss": 0.6038, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.5952789187431335, | |
| "eval_runtime": 38.92, | |
| "eval_samples_per_second": 51.387, | |
| "eval_steps_per_second": 1.619, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015922933499067744, | |
| "loss": 0.6076, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015829707893101304, | |
| "loss": 0.5901, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015736482287134865, | |
| "loss": 0.6019, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015643256681168425, | |
| "loss": 0.6007, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00015550031075201986, | |
| "loss": 0.5994, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001545680546923555, | |
| "loss": 0.5997, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0001536357986326911, | |
| "loss": 0.606, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00015270354257302673, | |
| "loss": 0.5983, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00015177128651336233, | |
| "loss": 0.5898, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00015083903045369796, | |
| "loss": 0.6042, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00014990677439403354, | |
| "loss": 0.5931, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00014897451833436915, | |
| "loss": 0.5964, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00014804226227470478, | |
| "loss": 0.6073, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00014711000621504038, | |
| "loss": 0.5911, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.000146177750155376, | |
| "loss": 0.5921, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001452454940957116, | |
| "loss": 0.6007, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00014431323803604723, | |
| "loss": 0.5974, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00014338098197638283, | |
| "loss": 0.6019, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00014244872591671843, | |
| "loss": 0.6049, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00014151646985705407, | |
| "loss": 0.5953, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 0.5934386253356934, | |
| "eval_runtime": 38.9572, | |
| "eval_samples_per_second": 51.338, | |
| "eval_steps_per_second": 1.617, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00014058421379738967, | |
| "loss": 0.597, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00013965195773772528, | |
| "loss": 0.6122, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001387197016780609, | |
| "loss": 0.6017, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0001377874456183965, | |
| "loss": 0.6007, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00013685518955873212, | |
| "loss": 0.5982, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00013592293349906772, | |
| "loss": 0.6025, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00013499067743940335, | |
| "loss": 0.5958, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00013405842137973896, | |
| "loss": 0.5963, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00013312616532007456, | |
| "loss": 0.6054, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0001321939092604102, | |
| "loss": 0.5936, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00013126165320074577, | |
| "loss": 0.5929, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0001303293971410814, | |
| "loss": 0.602, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.000129397141081417, | |
| "loss": 0.6012, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00012846488502175262, | |
| "loss": 0.5999, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00012753262896208825, | |
| "loss": 0.5978, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00012660037290242385, | |
| "loss": 0.6024, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00012566811684275946, | |
| "loss": 0.5854, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001247358607830951, | |
| "loss": 0.5979, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001238036047234307, | |
| "loss": 0.5964, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001228713486637663, | |
| "loss": 0.6042, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 0.5928096771240234, | |
| "eval_runtime": 38.9501, | |
| "eval_samples_per_second": 51.348, | |
| "eval_steps_per_second": 1.617, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00012193909260410192, | |
| "loss": 0.6045, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00012100683654443754, | |
| "loss": 0.5995, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00012007458048477315, | |
| "loss": 0.6149, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00011914232442510874, | |
| "loss": 0.5979, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00011821006836544436, | |
| "loss": 0.5905, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00011727781230577998, | |
| "loss": 0.5985, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00011634555624611559, | |
| "loss": 0.6088, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0001154133001864512, | |
| "loss": 0.6097, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011448104412678682, | |
| "loss": 0.6012, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011354878806712241, | |
| "loss": 0.603, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00011261653200745803, | |
| "loss": 0.5894, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00011168427594779365, | |
| "loss": 0.5879, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00011075201988812926, | |
| "loss": 0.602, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00010981976382846487, | |
| "loss": 0.5899, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00010888750776880049, | |
| "loss": 0.5918, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0001079552517091361, | |
| "loss": 0.5957, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00010702299564947172, | |
| "loss": 0.5982, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00010609073958980733, | |
| "loss": 0.5832, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00010515848353014293, | |
| "loss": 0.5965, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00010422622747047854, | |
| "loss": 0.5968, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 0.5914697647094727, | |
| "eval_runtime": 38.9209, | |
| "eval_samples_per_second": 51.386, | |
| "eval_steps_per_second": 1.619, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00010329397141081416, | |
| "loss": 0.5961, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00010236171535114978, | |
| "loss": 0.591, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00010142945929148539, | |
| "loss": 0.6009, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.000100497203231821, | |
| "loss": 0.581, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.956494717215662e-05, | |
| "loss": 0.58, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.863269111249221e-05, | |
| "loss": 0.5942, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 9.770043505282783e-05, | |
| "loss": 0.6004, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.676817899316345e-05, | |
| "loss": 0.6008, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.583592293349906e-05, | |
| "loss": 0.5915, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 9.490366687383467e-05, | |
| "loss": 0.5905, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.397141081417029e-05, | |
| "loss": 0.6123, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.30391547545059e-05, | |
| "loss": 0.5946, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.21068986948415e-05, | |
| "loss": 0.5816, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.117464263517712e-05, | |
| "loss": 0.5996, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 9.024238657551272e-05, | |
| "loss": 0.5959, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.931013051584834e-05, | |
| "loss": 0.6013, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 8.837787445618396e-05, | |
| "loss": 0.5863, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.744561839651957e-05, | |
| "loss": 0.6047, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.651336233685518e-05, | |
| "loss": 0.601, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 8.55811062771908e-05, | |
| "loss": 0.599, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.5905566215515137, | |
| "eval_runtime": 38.9566, | |
| "eval_samples_per_second": 51.339, | |
| "eval_steps_per_second": 1.617, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.46488502175264e-05, | |
| "loss": 0.5969, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.371659415786201e-05, | |
| "loss": 0.5864, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 8.278433809819763e-05, | |
| "loss": 0.5924, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.185208203853325e-05, | |
| "loss": 0.6041, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 8.091982597886885e-05, | |
| "loss": 0.5869, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.998756991920447e-05, | |
| "loss": 0.588, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 7.905531385954009e-05, | |
| "loss": 0.5971, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.812305779987568e-05, | |
| "loss": 0.5946, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.71908017402113e-05, | |
| "loss": 0.5881, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.625854568054692e-05, | |
| "loss": 0.6019, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.532628962088252e-05, | |
| "loss": 0.5923, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.439403356121814e-05, | |
| "loss": 0.5933, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 7.346177750155375e-05, | |
| "loss": 0.602, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.252952144188937e-05, | |
| "loss": 0.6092, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.159726538222498e-05, | |
| "loss": 0.5907, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 7.066500932256059e-05, | |
| "loss": 0.5993, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 6.97327532628962e-05, | |
| "loss": 0.5954, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.880049720323181e-05, | |
| "loss": 0.6, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.786824114356743e-05, | |
| "loss": 0.603, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.693598508390303e-05, | |
| "loss": 0.5915, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 0.5895615220069885, | |
| "eval_runtime": 38.9648, | |
| "eval_samples_per_second": 51.328, | |
| "eval_steps_per_second": 1.617, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.600372902423865e-05, | |
| "loss": 0.5956, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.507147296457427e-05, | |
| "loss": 0.5891, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 6.413921690490988e-05, | |
| "loss": 0.5896, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.320696084524548e-05, | |
| "loss": 0.5994, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.22747047855811e-05, | |
| "loss": 0.5935, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.134244872591672e-05, | |
| "loss": 0.5937, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.041019266625232e-05, | |
| "loss": 0.5925, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.947793660658794e-05, | |
| "loss": 0.584, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.8545680546923546e-05, | |
| "loss": 0.5897, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 5.7613424487259164e-05, | |
| "loss": 0.5952, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.6681168427594776e-05, | |
| "loss": 0.5935, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.574891236793039e-05, | |
| "loss": 0.5965, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.490988191423244e-05, | |
| "loss": 0.6008, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.397762585456805e-05, | |
| "loss": 0.6001, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.304536979490367e-05, | |
| "loss": 0.5923, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.211311373523927e-05, | |
| "loss": 0.5929, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 5.118085767557489e-05, | |
| "loss": 0.5931, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 5.02486016159105e-05, | |
| "loss": 0.5961, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.931634555624611e-05, | |
| "loss": 0.5871, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.8384089496581725e-05, | |
| "loss": 0.5975, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 0.5893495082855225, | |
| "eval_runtime": 38.9212, | |
| "eval_samples_per_second": 51.386, | |
| "eval_steps_per_second": 1.619, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.745183343691734e-05, | |
| "loss": 0.6009, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.651957737725295e-05, | |
| "loss": 0.5906, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.558732131758856e-05, | |
| "loss": 0.5948, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.465506525792417e-05, | |
| "loss": 0.6, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.372280919825978e-05, | |
| "loss": 0.5898, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.27905531385954e-05, | |
| "loss": 0.6005, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 4.1858297078931006e-05, | |
| "loss": 0.5949, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 4.0926041019266625e-05, | |
| "loss": 0.6213, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.9993784959602236e-05, | |
| "loss": 0.5966, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.906152889993784e-05, | |
| "loss": 0.5955, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.812927284027346e-05, | |
| "loss": 0.6001, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.719701678060907e-05, | |
| "loss": 0.5951, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.626476072094468e-05, | |
| "loss": 0.5946, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.5332504661280294e-05, | |
| "loss": 0.6006, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.4400248601615906e-05, | |
| "loss": 0.593, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.346799254195152e-05, | |
| "loss": 0.5961, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.2535736482287136e-05, | |
| "loss": 0.579, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.160348042262274e-05, | |
| "loss": 0.6025, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.067122436295836e-05, | |
| "loss": 0.601, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 2.973896830329397e-05, | |
| "loss": 0.5875, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 0.5886192917823792, | |
| "eval_runtime": 38.9814, | |
| "eval_samples_per_second": 51.306, | |
| "eval_steps_per_second": 1.616, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.8806712243629582e-05, | |
| "loss": 0.5942, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.7874456183965194e-05, | |
| "loss": 0.5854, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.6942200124300805e-05, | |
| "loss": 0.6094, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.600994406463642e-05, | |
| "loss": 0.5852, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.507768800497203e-05, | |
| "loss": 0.5987, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.414543194530764e-05, | |
| "loss": 0.5986, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.3213175885643255e-05, | |
| "loss": 0.5948, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.228091982597887e-05, | |
| "loss": 0.5955, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.1348663766314478e-05, | |
| "loss": 0.5843, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.041640770665009e-05, | |
| "loss": 0.5928, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.9484151646985705e-05, | |
| "loss": 0.6071, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.8551895587321316e-05, | |
| "loss": 0.5952, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.7619639527656928e-05, | |
| "loss": 0.5893, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.668738346799254e-05, | |
| "loss": 0.5913, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.575512740832815e-05, | |
| "loss": 0.5957, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.4822871348663764e-05, | |
| "loss": 0.5921, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.3890615288999376e-05, | |
| "loss": 0.5943, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.295835922933499e-05, | |
| "loss": 0.598, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.2026103169670601e-05, | |
| "loss": 0.5911, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.1093847110006214e-05, | |
| "loss": 0.5963, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 0.5883459448814392, | |
| "eval_runtime": 38.935, | |
| "eval_samples_per_second": 51.368, | |
| "eval_steps_per_second": 1.618, | |
| "step": 3200 | |
| } | |
| ], | |
| "max_steps": 3318, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.0078203805888938e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |