| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 2.0707900524139404, | |
| "learning_rate": 0.004961538461538462, | |
| "loss": 0.8561, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 0.9913710951805115, | |
| "learning_rate": 0.004923076923076923, | |
| "loss": 0.6755, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 1.5771081447601318, | |
| "learning_rate": 0.004884615384615385, | |
| "loss": 0.4032, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 1.9519121646881104, | |
| "learning_rate": 0.004846153846153846, | |
| "loss": 0.3903, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 2.557398796081543, | |
| "learning_rate": 0.004807692307692308, | |
| "loss": 0.5472, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 2.4644172191619873, | |
| "learning_rate": 0.0047692307692307695, | |
| "loss": 0.3894, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 1.2416399717330933, | |
| "learning_rate": 0.004730769230769231, | |
| "loss": 0.1827, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 0.8515920639038086, | |
| "learning_rate": 0.004692307692307693, | |
| "loss": 0.3148, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 0.227506622672081, | |
| "learning_rate": 0.004653846153846154, | |
| "loss": 0.237, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 2.7295713424682617, | |
| "learning_rate": 0.004615384615384616, | |
| "loss": 0.4501, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 1.2349276542663574, | |
| "learning_rate": 0.0045769230769230765, | |
| "loss": 0.6825, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 3.311713933944702, | |
| "learning_rate": 0.004538461538461539, | |
| "loss": 0.4085, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.20723728835582733, | |
| "learning_rate": 0.0045000000000000005, | |
| "loss": 0.1292, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_runtime": 0.7521, | |
| "eval_samples_per_second": 176.836, | |
| "eval_steps_per_second": 22.603, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0769230769230769, | |
| "grad_norm": 1.5258536338806152, | |
| "learning_rate": 0.004461538461538462, | |
| "loss": 0.3389, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 2.0288751125335693, | |
| "learning_rate": 0.004423076923076923, | |
| "loss": 0.2397, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.03801692649722099, | |
| "learning_rate": 0.004384615384615384, | |
| "loss": 0.162, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3076923076923077, | |
| "grad_norm": 0.1472761183977127, | |
| "learning_rate": 0.004346153846153846, | |
| "loss": 0.2687, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.3846153846153846, | |
| "grad_norm": 4.054047107696533, | |
| "learning_rate": 0.004307692307692308, | |
| "loss": 0.6044, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.4615384615384617, | |
| "grad_norm": 1.6007931232452393, | |
| "learning_rate": 0.004269230769230769, | |
| "loss": 0.6124, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.15122832357883453, | |
| "learning_rate": 0.004230769230769231, | |
| "loss": 0.4298, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6153846153846154, | |
| "grad_norm": 1.2161375284194946, | |
| "learning_rate": 0.004192307692307692, | |
| "loss": 0.5844, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.6923076923076923, | |
| "grad_norm": 7.478526592254639, | |
| "learning_rate": 0.004153846153846154, | |
| "loss": 1.2806, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.7692307692307692, | |
| "grad_norm": 1.2232049703598022, | |
| "learning_rate": 0.004115384615384615, | |
| "loss": 0.9687, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 1.4465281963348389, | |
| "learning_rate": 0.004076923076923077, | |
| "loss": 0.4883, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 3.471082925796509, | |
| "learning_rate": 0.0040384615384615385, | |
| "loss": 0.6709, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.699213981628418, | |
| "learning_rate": 0.004, | |
| "loss": 0.6404, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_runtime": 0.7652, | |
| "eval_samples_per_second": 173.8, | |
| "eval_steps_per_second": 22.215, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.076923076923077, | |
| "grad_norm": 1.1869909763336182, | |
| "learning_rate": 0.003961538461538462, | |
| "loss": 0.6565, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 2.2662851810455322, | |
| "learning_rate": 0.003923076923076923, | |
| "loss": 0.3753, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.230769230769231, | |
| "grad_norm": 3.587059736251831, | |
| "learning_rate": 0.003884615384615385, | |
| "loss": 0.9706, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 1.530928611755371, | |
| "learning_rate": 0.0038461538461538464, | |
| "loss": 1.2593, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.3846153846153846, | |
| "grad_norm": 1.0865129232406616, | |
| "learning_rate": 0.0038076923076923075, | |
| "loss": 0.9166, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 2.3256101608276367, | |
| "learning_rate": 0.003769230769230769, | |
| "loss": 1.1882, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.5384615384615383, | |
| "grad_norm": 0.5831055045127869, | |
| "learning_rate": 0.003730769230769231, | |
| "loss": 1.2764, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.6153846153846154, | |
| "grad_norm": 0.9471529126167297, | |
| "learning_rate": 0.0036923076923076927, | |
| "loss": 1.349, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.6923076923076925, | |
| "grad_norm": 0.6033434867858887, | |
| "learning_rate": 0.003653846153846154, | |
| "loss": 1.1626, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": 0.322643518447876, | |
| "learning_rate": 0.0036153846153846154, | |
| "loss": 1.1705, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.8461538461538463, | |
| "grad_norm": 0.6473853588104248, | |
| "learning_rate": 0.003576923076923077, | |
| "loss": 1.1492, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.9230769230769234, | |
| "grad_norm": 0.4563555121421814, | |
| "learning_rate": 0.003538461538461539, | |
| "loss": 1.1009, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.6773648858070374, | |
| "learning_rate": 0.0034999999999999996, | |
| "loss": 1.1322, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_runtime": 0.7629, | |
| "eval_samples_per_second": 174.339, | |
| "eval_steps_per_second": 22.284, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 0.499421089887619, | |
| "learning_rate": 0.0034615384615384616, | |
| "loss": 1.0926, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.1538461538461537, | |
| "grad_norm": 0.20487019419670105, | |
| "learning_rate": 0.003423076923076923, | |
| "loss": 1.129, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.230769230769231, | |
| "grad_norm": 0.5652111172676086, | |
| "learning_rate": 0.003384615384615385, | |
| "loss": 1.0965, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.3076923076923075, | |
| "grad_norm": 0.5159160494804382, | |
| "learning_rate": 0.003346153846153846, | |
| "loss": 1.0865, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.3846153846153846, | |
| "grad_norm": 0.5972450971603394, | |
| "learning_rate": 0.0033076923076923075, | |
| "loss": 1.1468, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.4615384615384617, | |
| "grad_norm": 0.4497612714767456, | |
| "learning_rate": 0.0032692307692307695, | |
| "loss": 1.0972, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.5384615384615383, | |
| "grad_norm": 0.8494599461555481, | |
| "learning_rate": 0.003230769230769231, | |
| "loss": 1.1196, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.6153846153846154, | |
| "grad_norm": 0.21025516092777252, | |
| "learning_rate": 0.003192307692307692, | |
| "loss": 1.1336, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.6923076923076925, | |
| "grad_norm": 0.5746878385543823, | |
| "learning_rate": 0.0031538461538461538, | |
| "loss": 1.0988, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.769230769230769, | |
| "grad_norm": 0.20434798300266266, | |
| "learning_rate": 0.0031153846153846153, | |
| "loss": 1.1101, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 0.15725131332874298, | |
| "learning_rate": 0.0030769230769230774, | |
| "loss": 1.1133, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.9230769230769234, | |
| "grad_norm": 0.12141856551170349, | |
| "learning_rate": 0.0030384615384615385, | |
| "loss": 1.0987, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.1281518936157227, | |
| "learning_rate": 0.003, | |
| "loss": 1.1021, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_runtime": 0.7744, | |
| "eval_samples_per_second": 171.736, | |
| "eval_steps_per_second": 21.951, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 4.076923076923077, | |
| "grad_norm": 0.5692263841629028, | |
| "learning_rate": 0.0029615384615384616, | |
| "loss": 1.1032, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.153846153846154, | |
| "grad_norm": 0.21811030805110931, | |
| "learning_rate": 0.002923076923076923, | |
| "loss": 1.096, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.230769230769231, | |
| "grad_norm": 0.44653287529945374, | |
| "learning_rate": 0.0028846153846153843, | |
| "loss": 1.0986, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.3076923076923075, | |
| "grad_norm": 0.4496428966522217, | |
| "learning_rate": 0.002846153846153846, | |
| "loss": 1.1244, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.384615384615385, | |
| "grad_norm": 0.34072381258010864, | |
| "learning_rate": 0.002807692307692308, | |
| "loss": 1.0982, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.461538461538462, | |
| "grad_norm": 0.617884635925293, | |
| "learning_rate": 0.0027692307692307695, | |
| "loss": 1.1137, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.538461538461538, | |
| "grad_norm": 0.3251841068267822, | |
| "learning_rate": 0.0027307692307692306, | |
| "loss": 1.1054, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 0.11284901946783066, | |
| "learning_rate": 0.002692307692307692, | |
| "loss": 1.0981, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.6923076923076925, | |
| "grad_norm": 0.802207887172699, | |
| "learning_rate": 0.0026538461538461538, | |
| "loss": 1.1134, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.769230769230769, | |
| "grad_norm": 0.22614385187625885, | |
| "learning_rate": 0.0026153846153846158, | |
| "loss": 1.1155, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.846153846153846, | |
| "grad_norm": 0.3756657838821411, | |
| "learning_rate": 0.002576923076923077, | |
| "loss": 1.1113, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "grad_norm": 0.6828984618186951, | |
| "learning_rate": 0.0025384615384615385, | |
| "loss": 1.1249, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.2701197862625122, | |
| "learning_rate": 0.0025, | |
| "loss": 1.102, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_runtime": 0.7836, | |
| "eval_samples_per_second": 169.724, | |
| "eval_steps_per_second": 21.694, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 5.076923076923077, | |
| "grad_norm": 0.30358830094337463, | |
| "learning_rate": 0.0024615384615384616, | |
| "loss": 1.1044, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.153846153846154, | |
| "grad_norm": 0.42961689829826355, | |
| "learning_rate": 0.002423076923076923, | |
| "loss": 1.0977, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 5.230769230769231, | |
| "grad_norm": 0.24340471625328064, | |
| "learning_rate": 0.0023846153846153848, | |
| "loss": 1.1379, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 5.3076923076923075, | |
| "grad_norm": 0.9648124575614929, | |
| "learning_rate": 0.0023461538461538463, | |
| "loss": 1.1314, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 5.384615384615385, | |
| "grad_norm": 0.6379570960998535, | |
| "learning_rate": 0.002307692307692308, | |
| "loss": 1.1104, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.461538461538462, | |
| "grad_norm": 0.32133665680885315, | |
| "learning_rate": 0.0022692307692307695, | |
| "loss": 1.1061, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 5.538461538461538, | |
| "grad_norm": 0.314644455909729, | |
| "learning_rate": 0.002230769230769231, | |
| "loss": 1.1035, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 5.615384615384615, | |
| "grad_norm": 0.4097970128059387, | |
| "learning_rate": 0.002192307692307692, | |
| "loss": 1.1035, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 5.6923076923076925, | |
| "grad_norm": 0.3651571273803711, | |
| "learning_rate": 0.002153846153846154, | |
| "loss": 1.1071, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 5.769230769230769, | |
| "grad_norm": 0.30447086691856384, | |
| "learning_rate": 0.0021153846153846153, | |
| "loss": 1.1048, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.846153846153846, | |
| "grad_norm": 0.35882461071014404, | |
| "learning_rate": 0.002076923076923077, | |
| "loss": 1.106, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 5.923076923076923, | |
| "grad_norm": 0.6777219772338867, | |
| "learning_rate": 0.0020384615384615385, | |
| "loss": 1.101, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 1.031847357749939, | |
| "learning_rate": 0.002, | |
| "loss": 1.1027, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_runtime": 0.7774, | |
| "eval_samples_per_second": 171.09, | |
| "eval_steps_per_second": 21.869, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 6.076923076923077, | |
| "grad_norm": 0.43265023827552795, | |
| "learning_rate": 0.0019615384615384616, | |
| "loss": 1.104, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 0.4353933334350586, | |
| "learning_rate": 0.0019230769230769232, | |
| "loss": 1.099, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 6.230769230769231, | |
| "grad_norm": 0.11455998569726944, | |
| "learning_rate": 0.0018846153846153845, | |
| "loss": 1.0985, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 6.3076923076923075, | |
| "grad_norm": 0.1155104711651802, | |
| "learning_rate": 0.0018461538461538463, | |
| "loss": 1.1026, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 6.384615384615385, | |
| "grad_norm": 0.44076037406921387, | |
| "learning_rate": 0.0018076923076923077, | |
| "loss": 1.0985, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 6.461538461538462, | |
| "grad_norm": 0.5386171936988831, | |
| "learning_rate": 0.0017692307692307695, | |
| "loss": 1.1025, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 6.538461538461538, | |
| "grad_norm": 0.611710786819458, | |
| "learning_rate": 0.0017307692307692308, | |
| "loss": 1.0992, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.615384615384615, | |
| "grad_norm": 0.2715957760810852, | |
| "learning_rate": 0.0016923076923076924, | |
| "loss": 1.1008, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 6.6923076923076925, | |
| "grad_norm": 0.4223721921443939, | |
| "learning_rate": 0.0016538461538461537, | |
| "loss": 1.089, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 6.769230769230769, | |
| "grad_norm": 0.14638401567935944, | |
| "learning_rate": 0.0016153846153846155, | |
| "loss": 1.1237, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 6.846153846153846, | |
| "grad_norm": 0.32549309730529785, | |
| "learning_rate": 0.0015769230769230769, | |
| "loss": 1.1031, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 6.923076923076923, | |
| "grad_norm": 0.4604528844356537, | |
| "learning_rate": 0.0015384615384615387, | |
| "loss": 1.1001, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.5566179156303406, | |
| "learning_rate": 0.0015, | |
| "loss": 1.0954, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_runtime": 0.7823, | |
| "eval_samples_per_second": 170.021, | |
| "eval_steps_per_second": 21.732, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 7.076923076923077, | |
| "grad_norm": 0.5109624266624451, | |
| "learning_rate": 0.0014615384615384616, | |
| "loss": 1.1043, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 7.153846153846154, | |
| "grad_norm": 0.5437686443328857, | |
| "learning_rate": 0.001423076923076923, | |
| "loss": 1.1055, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 7.230769230769231, | |
| "grad_norm": 0.6647012233734131, | |
| "learning_rate": 0.0013846153846153847, | |
| "loss": 1.1021, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 7.3076923076923075, | |
| "grad_norm": 0.4888548254966736, | |
| "learning_rate": 0.001346153846153846, | |
| "loss": 1.0968, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 7.384615384615385, | |
| "grad_norm": 0.26103150844573975, | |
| "learning_rate": 0.0013076923076923079, | |
| "loss": 1.104, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 7.461538461538462, | |
| "grad_norm": 0.2501744031906128, | |
| "learning_rate": 0.0012692307692307692, | |
| "loss": 1.1008, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 7.538461538461538, | |
| "grad_norm": 0.37639835476875305, | |
| "learning_rate": 0.0012307692307692308, | |
| "loss": 1.0998, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 7.615384615384615, | |
| "grad_norm": 0.23087725043296814, | |
| "learning_rate": 0.0011923076923076924, | |
| "loss": 1.0979, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 7.6923076923076925, | |
| "grad_norm": 0.3334718644618988, | |
| "learning_rate": 0.001153846153846154, | |
| "loss": 1.1068, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.769230769230769, | |
| "grad_norm": 0.5154008865356445, | |
| "learning_rate": 0.0011153846153846155, | |
| "loss": 1.099, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 7.846153846153846, | |
| "grad_norm": 0.2505805492401123, | |
| "learning_rate": 0.001076923076923077, | |
| "loss": 1.0985, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 7.923076923076923, | |
| "grad_norm": 0.47592583298683167, | |
| "learning_rate": 0.0010384615384615384, | |
| "loss": 1.0968, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.4868021309375763, | |
| "learning_rate": 0.001, | |
| "loss": 1.1047, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_runtime": 0.7757, | |
| "eval_samples_per_second": 171.462, | |
| "eval_steps_per_second": 21.916, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 8.076923076923077, | |
| "grad_norm": 0.12491131573915482, | |
| "learning_rate": 0.0009615384615384616, | |
| "loss": 1.0981, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 8.153846153846153, | |
| "grad_norm": 0.23577113449573517, | |
| "learning_rate": 0.0009230769230769232, | |
| "loss": 1.0998, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 8.23076923076923, | |
| "grad_norm": 0.12919014692306519, | |
| "learning_rate": 0.0008846153846153847, | |
| "loss": 1.098, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 8.307692307692308, | |
| "grad_norm": 0.11554103344678879, | |
| "learning_rate": 0.0008461538461538462, | |
| "loss": 1.099, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 8.384615384615385, | |
| "grad_norm": 0.3568715751171112, | |
| "learning_rate": 0.0008076923076923078, | |
| "loss": 1.0935, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 8.461538461538462, | |
| "grad_norm": 0.4273003041744232, | |
| "learning_rate": 0.0007692307692307693, | |
| "loss": 1.1025, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 8.538461538461538, | |
| "grad_norm": 0.11346741020679474, | |
| "learning_rate": 0.0007307692307692308, | |
| "loss": 1.1079, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 8.615384615384615, | |
| "grad_norm": 0.5924614667892456, | |
| "learning_rate": 0.0006923076923076924, | |
| "loss": 1.095, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 8.692307692307692, | |
| "grad_norm": 0.8924316763877869, | |
| "learning_rate": 0.0006538461538461539, | |
| "loss": 1.0969, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 8.76923076923077, | |
| "grad_norm": 0.14277611672878265, | |
| "learning_rate": 0.0006153846153846154, | |
| "loss": 1.112, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 8.846153846153847, | |
| "grad_norm": 0.29049235582351685, | |
| "learning_rate": 0.000576923076923077, | |
| "loss": 1.0914, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 8.923076923076923, | |
| "grad_norm": 0.5114134550094604, | |
| "learning_rate": 0.0005384615384615385, | |
| "loss": 1.1061, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 1.142321228981018, | |
| "learning_rate": 0.0005, | |
| "loss": 1.1105, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_runtime": 0.781, | |
| "eval_samples_per_second": 170.284, | |
| "eval_steps_per_second": 21.766, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 9.076923076923077, | |
| "grad_norm": 0.12881995737552643, | |
| "learning_rate": 0.0004615384615384616, | |
| "loss": 1.0994, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 9.153846153846153, | |
| "grad_norm": 0.12638165056705475, | |
| "learning_rate": 0.0004230769230769231, | |
| "loss": 1.0982, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 9.23076923076923, | |
| "grad_norm": 0.13503584265708923, | |
| "learning_rate": 0.00038461538461538467, | |
| "loss": 1.0996, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 9.307692307692308, | |
| "grad_norm": 0.23928503692150116, | |
| "learning_rate": 0.0003461538461538462, | |
| "loss": 1.1, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 9.384615384615385, | |
| "grad_norm": 0.14712156355381012, | |
| "learning_rate": 0.0003076923076923077, | |
| "loss": 1.1033, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 9.461538461538462, | |
| "grad_norm": 0.603887140750885, | |
| "learning_rate": 0.0002692307692307693, | |
| "loss": 1.0979, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 9.538461538461538, | |
| "grad_norm": 0.34505996108055115, | |
| "learning_rate": 0.0002307692307692308, | |
| "loss": 1.0977, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 9.615384615384615, | |
| "grad_norm": 0.11722344160079956, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 1.1001, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 9.692307692307692, | |
| "grad_norm": 0.33938324451446533, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 1.0988, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 9.76923076923077, | |
| "grad_norm": 0.1380094438791275, | |
| "learning_rate": 0.0001153846153846154, | |
| "loss": 1.1004, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 9.846153846153847, | |
| "grad_norm": 0.2527919411659241, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.0999, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 9.923076923076923, | |
| "grad_norm": 0.316256582736969, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 1.0984, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.4816994071006775, | |
| "learning_rate": 0.0, | |
| "loss": 1.0979, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_runtime": 0.7911, | |
| "eval_samples_per_second": 168.13, | |
| "eval_steps_per_second": 21.49, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1300, | |
| "total_flos": 8.400578669044531e+17, | |
| "train_loss": 0.9780362775692573, | |
| "train_runtime": 138.3381, | |
| "train_samples_per_second": 74.744, | |
| "train_steps_per_second": 9.397 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1300, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.400578669044531e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |